|
创作新主题 |
社区所有版块导航
DATA
| docker Elasticsearch |
WEB开发
| linux MongoDB Redis DATABASE NGINX 其他Web框架 web工具 zookeeper tornado NoSql Bootstrap js peewee Git bottle IE MQ Jquery |
机器学习
| 机器学习算法 |
产品
| 短视频 |
印度
| 印度 |
一周十大热门主题
点击阅读原文访问arxivdaily.com，涵盖CS|物理|数学|经济|统计|金融|生物|电气领域，更有搜索、收藏等功能！
cs.LG 方向，今日共计114篇
大模型相关(15篇)
【1】Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation
标题：大型语言模型破解：量化使用LLM进行文本注释的隐藏风险
链接：https://arxiv.org/abs/2509.08825
摘要：大型语言模型（LLM）正在通过实现数据注释和文本分析等劳动密集型任务的自动化来迅速改变社会科学研究。然而，LLM的输出变化很大，这取决于研究人员所做的实施选择（例如，模型选择、提示策略或温度设置）。这种变化可能会引入系统偏差和随机误差，这些偏差和误差会传播到下游分析并导致I型、II型、S型或M型误差。我们称之为LLM黑客攻击。 我们通过使用18种不同的模型复制来自21项已发表的社会科学研究的37个数据注释任务来量化LLM黑客攻击的风险。分析1300万个LLM标签，我们测试了2，361个现实假设，以衡量合理的研究人员选择如何影响统计结论。我们发现基于LLM注释数据的不正确结论，大约有三分之一的最先进模型假设，以及一半的小语言模型假设。虽然我们的研究结果表明，更高的任务性能和更好的通用模型功能降低了LLM黑客攻击的风险，但即使是高度准确的模型也不能完全消除它。LLM黑客攻击的风险随着效应大小的增加而降低，这表明需要对接近显著性阈值的结果进行更严格的验证。我们对LLM黑客攻击缓解技术的广泛分析强调了人类注释在减少假阳性发现和改进模型选择方面的重要性。令人惊讶的是，常见的回归估计器校正技术在降低LLM黑客风险方面基本上是无效的，因为它们严重权衡了I型与II型错误。 除了偶然的错误，我们发现故意的LLM黑客攻击是不可接受的简单。只有很少的LLM和少量的即时释义，任何东西都可以被呈现为具有统计学意义。
摘要：Large language models (LLMs) are rapidly transforming social science research by enabling the automation of labor-intensive tasks like data annotation and text analysis. However, LLM outputs vary significantly depending on the implementation choices made by researchers (e.g., model selection, prompting strategy, or temperature settings). Such variation can introduce systematic biases and random errors, which propagate to downstream analyses and cause Type I, Type II, Type S, or Type M errors. We call this LLM hacking. We quantify the risk of LLM hacking by replicating 37 data annotation tasks from 21 published social science research studies with 18 different models. Analyzing 13 million LLM labels, we test 2,361 realistic hypotheses to measure how plausible researcher choices affect statistical conclusions. We find incorrect conclusions based on LLM-annotated data in approximately one in three hypotheses for state-of-the-art models, and in half the hypotheses for small language models. While our findings show that higher task performance and better general model capabilities reduce LLM hacking risk, even highly accurate models do not completely eliminate it. The risk of LLM hacking decreases as effect sizes increase, indicating the need for more rigorous verification of findings near significance thresholds. Our extensive analysis of LLM hacking mitigation techniques emphasizes the importance of human annotations in reducing false positive findings and improving model selection. Surprisingly, common regression estimator correction techniques are largely ineffective in reducing LLM hacking risk, as they heavily trade off Type I vs. Type II errors. Beyond accidental errors, we find that intentional LLM hacking is unacceptably simple. With few LLMs and just a handful of prompt paraphrases, anything can be presented as statistically significant.
【2】AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
标题：AgentGym-RL：通过多轮强化学习训练LLM代理进行长期决策
链接：https://arxiv.org/abs/2509.08755
备注：preprint, 39 pages, 16 figures. Project: this https URL. Framework and Code: this https URL, this https URL
摘要：开发能够做出一系列智能决策以解决复杂的现实任务的自主LLM代理是一个快速发展的前沿。与人类的认知发展一样，智能体也需要通过探索和与环境的交互来获得知识和技能。尽管取得了进展，但社区仍然缺乏一个统一的交互式强化学习（RL）框架，可以有效地从头开始训练这些代理-而不依赖于监督微调（SFT）-在多样化和现实的环境中。为了弥合这一差距，我们引入了AgentGym-RL，一个新的框架，通过RL训练LLM代理进行多轮交互式决策。该框架具有模块化和解耦的架构，确保了高度的灵活性和可扩展性。它涵盖了各种各样的现实场景，并支持主流的RL算法。此外，我们提出了ScalingInter-RL，这是一种专为探索-利用平衡和稳定RL优化而设计的训练方法。在早期阶段，它强调通过限制互动次数来开发，并逐渐转向更大视野的探索，以鼓励多样化的解决问题策略。通过这种方式，代理开发出更多样化的行为，并且在长期视野下不太容易崩溃。我们进行了大量的实验来验证AgentGym-RL框架和ScalingInter-RL方法的稳定性和有效性。我们的智能体在不同环境中的27项任务上与商业模型相匹配或超过商业模型。我们提供关键见解，并将开源完整的AgentGym-RL框架（包括代码和数据集），以帮助研究界开发下一代智能代理。
摘要：Developing autonomous LLM agents capable of making a series of intelligent decisions to solve complex, real-world tasks is a fast-evolving frontier. Like human cognitive development, agents are expected to acquire knowledge and skills through exploration and interaction with the environment. Despite advances, the community still lacks a unified, interactive reinforcement learning (RL) framework that can effectively train such agents from scratch -- without relying on supervised fine-tuning (SFT) -- across diverse and realistic environments. To bridge this gap, we introduce AgentGym-RL, a new framework to train LLM agents for multi-turn interactive decision-making through RL. The framework features a modular and decoupled architecture, ensuring high flexibility and extensibility. It encompasses a wide variety of real-world scenarios, and supports mainstream RL algorithms. Furthermore, we propose ScalingInter-RL, a training approach designed for exploration-exploitation balance and stable RL optimization. In early stages, it emphasizes exploitation by restricting the number of interactions, and gradually shifts towards exploration with larger horizons to encourage diverse problem-solving strategies. In this way, the agent develops more diverse behaviors and is less prone to collapse under long horizons. We perform extensive experiments to validate the stability and effectiveness of both the AgentGym-RL framework and the ScalingInter-RL approach. Our agents match or surpass commercial models on 27 tasks across diverse environments. We offer key insights and will open-source the complete AgentGym-RL framework -- including code and datasets -- to empower the research community in developing the next generation of intelligent agents.
【3】ChemBOMAS: Accelerated BO in Chemistry with LLM-Enhanced Multi-Agent System
标题：ChemBOMAS：化学中的加速BO与LLM增强的多智能体系统
链接：https://arxiv.org/abs/2509.08736
摘要 ：贝叶斯优化（BO）在化学中的效率往往受到稀疏的实验数据和复杂的反应机理。为了克服这些局限性，我们引入了ChemBOMAS，一个新的框架，名为LLM增强的多智能体系统，用于加速化学BO。ChemBOMAS的优化过程通过LLM增强，并协同采用两种策略：知识驱动的粗粒度优化和数据驱动的细粒度优化。首先，在知识驱动的粗粒度优化阶段，LLM通过对现有化学知识进行推理来智能地分解广阔的搜索空间，以识别有希望的候选区域。随后，在数据驱动的细粒度优化阶段，LLM通过生成伪数据点来增强这些候选区域内的BO过程，从而提高数据利用效率并加速收敛。基准评估 ** 进一步证实，与各种BO算法相比，ChemBOMAS显著提高了优化效果和效率。重要的是，ChemBOMAS的实用性是通过在制药行业协议下进行的湿实验室实验进行验证的，针对以前未报道和具有挑战性的化学反应进行条件优化。在湿实验中，ChemBOMAS达到了96%的最佳目标值。这大大高于领域专家所达到的15%。这一现实世界的成功，以及在基准评估方面的出色表现，突出了ChemBOMAS作为加速化学发现的强大工具。
摘要：The efficiency of Bayesian optimization (BO) in chemistry is often hindered by sparse experimental data and complex reaction mechanisms. To overcome these limitations, we introduce ChemBOMAS, a new framework named LLM-Enhanced Multi-Agent System for accelerating BO in chemistry. ChemBOMAS's optimization process is enhanced by LLMs and synergistically employs two strategies: knowledge-driven coarse-grained optimization and data-driven fine-grained optimization. First, in the knowledge-driven coarse-grained optimization stage, LLMs intelligently decompose the vast search space by reasoning over existing chemical knowledge to identify promising candidate regions. Subsequently, in the data-driven fine-grained optimization stage, LLMs enhance the BO process within these candidate regions by generating pseudo-data points, thereby improving data utilization efficiency and accelerating convergence. Benchmark evaluations** further confirm that ChemBOMAS significantly enhances optimization effectiveness and efficiency compared to various BO algorithms. Importantly, the practical utility of ChemBOMAS was validated through wet-lab experiments conducted under pharmaceutical industry protocols, targeting conditional optimization for a previously unreported and challenging chemical reaction. In the wet experiment, ChemBOMAS achieved an optimal objective value of 96%. This was substantially higher than the 15% achieved by domain experts. This real-world success, together with strong performance on benchmark evaluations, highlights ChemBOMAS as a powerful tool to accelerate chemical discovery.
【4】Adapting Vision-Language Models for Neutrino Event Classification in High-Energy Physics
标题：调整视觉语言模型用于高能物理中的中微子事件分类
链接：https://arxiv.org/abs/2509.08461
摘要：大型语言模型（LLM）的最新进展已经证明了它们在处理和推理自然语言之外的结构化和非结构化数据模式方面的卓越能力。在这项工作中，我们探索视觉语言模型（VLM）的应用，特别是LLaMa 3.2的微调变体，从高能物理（HEP）实验的像素化探测器数据中识别中微子相互作用的任务。我们将该模型与最先进的卷积神经网络（CNN）架构进行基准测试，该架构类似于NOvA和DUNE实验中使用的架构，这些实验在分类电子和μ子中微子事件方面实现了高效率和纯度。我们的评估同时考虑了模型预测的分类性能和可解释性。我们发现，VLM可以优于CNN，同时在整合辅助文本或语义信息方面提供更大的灵活性，并提供更多可解释的、基于推理的预测。这项工作突出了VLM作为物理事件分类的通用骨干的潜力，由于其高性能，可解释性和可推广性，这为在实验中微子物理学中集成多模态推理开辟了新的途径。
摘要：Recent advances in Large Language Models (LLMs) have demonstrated their remarkable capacity to process and reason over structured and unstructured data modalities beyond natural language. In this work, we explore the applications of Vision Language Models (VLMs), specifically a fine-tuned variant of LLaMa 3.2, to the task of identifying neutrino interactions in pixelated detector data from high-energy physics (HEP) experiments. We benchmark this model against a state-of-the-art convolutional neural network (CNN) architecture, similar to those used in the NOvA and DUNE experiments, which have achieved high efficiency and purity in classifying electron and muon neutrino events. Our evaluation considers both the classification performance and interpretability of the model predictions. We find that VLMs can outperform CNNs, while also providing greater flexibility in integrating auxiliary textual or semantic information and offering more interpretable, reasoning-based predictions. This work highlights the potential of VLMs as a general-purpose backbone for physics event classification, due to their high performance, interpretability, and generalizability, which opens new avenues for integrating multimodal reasoning in experimental neutrino physics.
【5】Efficient Decoding Methods for Language Models on Encrypted Data
标题：加密数据上语言模型的高效解码方法
链接：https://arxiv.org/abs/2509.08383
摘要：大型语言模型（LLM）为现代AI应用程序提供动力，但在不受信任的服务器上处理敏感数据会引发隐私问题。同态加密（HE）允许对加密数据进行计算以进行安全推断。然而，神经文本生成需要像argmax和采样这样的解码方法，这些方法是非多项式的，因此在加密下计算量很大，造成了显著的性能瓶颈。我们介绍cutmax，一个HE友好的argmax算法，减少了密文操作相比，以前的方法，使实际的贪婪解码加密。我们还提出了第一个HE兼容的核心（top-p）采样方法，利用cutmax进行有效的随机解码，并具有可证明的隐私保证。这两种技术都是多项式的，支持在隐私保护设置中进行有效的推理。此外，它们的可微性有利于基于梯度的序列级优化作为多项式替代直通估计。我们进一步为cutmax提供了强有力的理论保证，证明它全局收敛到一个唯一的两级不动点，独立于最大化器身份之外的输入值，这解释了它在几次迭代中的快速收敛。对现实LLM输出的评估显示，延迟比基线减少了24 - 35倍，从而推进了安全文本生成。
摘要：Large language models (LLMs) power modern AI applications, but processing sensitive data on untrusted servers raises privacy concerns. Homomorphic encryption (HE) enables computation on encrypted data for secure inference. However, neural text generation requires decoding methods like argmax and sampling, which are non-polynomial and thus computationally expensive under encryption, creating a significant performance bottleneck. We introduce cutmax, an HE-friendly argmax algorithm that reduces ciphertext operations compared to prior methods, enabling practical greedy decoding under encryption. We also propose the first HE-compatible nucleus (top-p) sampling method, leveraging cutmax for efficient stochastic decoding with provable privacy guarantees. Both techniques are polynomial, supporting efficient inference in privacy-preserving settings. Moreover, their differentiability facilitates gradient-based sequence-level optimization as a polynomial alternative to straight-through estimators. We further provide strong theoretical guarantees for cutmax, proving it converges globally to a unique two-level fixed point, independent of the input values beyond the identity of the maximizer, which explains its rapid convergence in just a few iterations. Evaluations on realistic LLM outputs show latency reductions of 24x-35x over baselines, advancing secure text generation.
【6】Accelerating Reinforcement Learning Algorithms Convergence using Pre-trained Large Language Models as Tutors With Advice Reusing
标题：使用预训练的大型语言模型作为导师并建议重用加速强化学习算法收敛
链接：https://arxiv.org/abs/2509.08329
摘要：强化学习（RL）算法通常需要长时间的训练才能变得有用，特别是在奖励稀疏的复杂环境中。虽然存在奖励塑造和课程学习等技术来加速培训，但这些技术通常非常具体，需要开发人员在问题领域的专业知识和专门知识。为了应对这一挑战，在这项研究中，我们探索了预先训练的大型语言模型（LLM）作为学生-教师架构中的教师与RL算法的有效性，假设LLM生成的指导可以更快地收敛。特别是，我们探讨了重用LLM的RL的收敛动态的意见的有效性。通过广泛的实证研究，其中包括54种配置，改变RL算法（DQN，PPO，A2 C），LLM导师（Llama，Vicuna，DeepSeek）和环境（Blackjack，Snake，Connect Four），我们的结果表明，LLM辅导显着加速RL收敛，同时保持相当的最佳性能。此外，建议重用机制在训练持续时间上显示出进一步的改进，但也导致不太稳定的收敛动态。我们的研究结果表明，LLM辅导一般提高收敛，其有效性是敏感的具体任务，RL算法，LLM模型组合。
摘要 ：Reinforcement Learning (RL) algorithms often require long training to become useful, especially in complex environments with sparse rewards. While techniques like reward shaping and curriculum learning exist to accelerate training, these are often extremely specific and require the developer's professionalism and dedicated expertise in the problem's domain. Tackling this challenge, in this study, we explore the effectiveness of pre-trained Large Language Models (LLMs) as tutors in a student-teacher architecture with RL algorithms, hypothesizing that LLM-generated guidance allows for faster convergence. In particular, we explore the effectiveness of reusing the LLM's advice on the RL's convergence dynamics. Through an extensive empirical examination, which included 54 configurations, varying the RL algorithm (DQN, PPO, A2C), LLM tutor (Llama, Vicuna, DeepSeek), and environment (Blackjack, Snake, Connect Four), our results demonstrate that LLM tutoring significantly accelerates RL convergence while maintaining comparable optimal performance. Furthermore, the advice reuse mechanism shows a further improvement in training duration but also results in less stable convergence dynamics. Our findings suggest that LLM tutoring generally improves convergence, and its effectiveness is sensitive to the specific task, RL algorithm, and LLM model combination.
【7】EvolKV: Evolutionary KV Cache Compression for LLM Inference
标题：EvolKV：用于LLM推理的进化性KV缓存压缩
链接：https://arxiv.org/abs/2509.08315
摘要：现有的键值（KV）缓存压缩方法通常依赖于算法，例如跨层的均匀缓存分配或静态驱逐策略，但是它们忽略了特定于层的特征模式和任务性能之间的关键相互作用，这可能导致泛化能力下降。在本文中，我们提出了EvolKV，一个自适应框架分层，任务驱动的KV缓存压缩，共同优化的内存效率和任务性能。通过将缓存分配重新定义为多目标优化问题，EvolKV利用进化搜索来动态配置层预算，同时直接最大化下游性能。对11个任务的广泛实验表明，我们的方法在长上下文任务的KV缓存预算范围内优于所有基线方法，并在GSM 8K上超过启发式基线高达7个百分点。值得注意的是，EvolKV在代码完成时实现了优于完整KV缓存设置的性能，同时仅利用了原始预算的1.5%，这表明KV缓存预算分配的学习压缩策略具有未开发的潜力。
摘要：Existing key-value (KV) cache compression methods typically rely on heuristics, such as uniform cache allocation across layers or static eviction policies, however, they ignore the critical interplays among layer-specific feature patterns and task performance, which can lead to degraded generalization. In this paper, we propose EvolKV, an adaptive framework for layer-wise, task-driven KV cache compression that jointly optimizes the memory efficiency and task performance. By reformulating cache allocation as a multi-objective optimization problem, EvolKV leverages evolutionary search to dynamically configure layer budgets while directly maximizing downstream performance. Extensive experiments on 11 tasks demonstrate that our approach outperforms all baseline methods across a wide range of KV cache budgets on long-context tasks and surpasses heuristic baselines by up to 7 percentage points on GSM8K. Notably, EvolKV achieves superior performance over the full KV cache setting on code completion while utilizing only 1.5% of the original budget, suggesting the untapped potential in learned compression strategies for KV cache budget allocation.
【8】Interpretable Physics Reasoning and Performance Taxonomy in Vision-Language Models
标题：视觉语言模型中的可解释物理推理和性能分类
链接：https://arxiv.org/abs/2509.08270
摘要：随着视觉语言模型（VLM）变得越来越复杂，它们执行推理的能力受到越来越多的监督。虽然他们擅长许多任务，但他们对物理学等基本科学原理的掌握仍然是一个未被探索的前沿。为了反映这些功能的进步，我们引入了一个新颖的和可访问的框架，旨在严格评估VLM对2D物理的理解。我们的框架具有一个务实的场景生成器，它创建了一个跨越四个核心领域的400多个问题的多样化测试平台：弹丸运动，碰撞动力学，力学和流体动力学。通过对四个最先进的VLM的综合评估，我们证明了模型规模和推理能力之间的强相关性，我们的表现最好的模型Qwen2.5-VL-7 B的总得分为0.815。我们发现，虽然模型擅长公式化的问题，他们的斗争显着领域需要抽象的空间推理。通过设计这个框架，我们的目标是民主化的研究科学推理的VLMs和促进更深入地了解他们的能力和局限性。
摘要：As Vision-Language Models (VLMs) grow in sophistication, their ability to perform reasoning is coming under increasing supervision. While they excel at many tasks, their grasp of fundamental scientific principles, such as physics, remains an underexplored frontier. To reflect the advancements in these capabilities, we introduce a novel and accessible framework designed to rigorously evaluate VLMs on their understanding of 2D physics. Our framework features a pragmatic scenario generator that creates a diverse testbed of over 400 problems across four core domains: Projectile Motion, Collision Dynamics, Mechanics, and Fluid Dynamics. Through comprehensive evaluation of four state-of-the-art VLMs, we demonstrate a strong correlation between model scale and reasoning ability, with our top-performing model, Qwen2.5-VL-7B, achieving an overall score of 0.815. We find that while models excel at formulaic problems, they struggle significantly with domains requiring abstract spatial reasoning. By designing this framework, we aim to democratize the study of scientific reasoning in VLMs and foster deeper insights into their capabilities and limitations.
【9】Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning
标题：使用遗忘感知修剪来缓解大型语言模型中的灾难性遗忘
链接：https://arxiv.org/abs/2509.08255
备注：Accepted by emnlp2025
摘要：大型语言模型（LLM）的最新进展在各种下游任务中显示出令人印象深刻的能力，但通常在微调期间面临灾难性遗忘（CF）。在本文中，我们提出了Forgetting-Aware剪枝度量（FAPM），一种新的基于剪枝的方法来平衡CF和下游任务的性能。我们的调查显示，任务向量（即，从在下游任务上微调的权重中减去预先训练的权重）与预先训练的模型参数重叠是CF的关键因素。基于这一发现，FAPM采用任务向量与预训练模型参数的比率作为量化CF的度量，将该度量集成到修剪标准中。重要的是，FAPM不需要修改训练过程或模型架构，也不需要任何辅助数据。我们在八个数据集上进行了广泛的实验，涵盖自然语言推理，一般问答，医学问答，数学问答，阅读理解和完形填空测试。结果表明，FAPM将CF限制为仅0.25%，同时在下游任务上保持99.67%的准确性。我们提供代码来重现我们的结果。
摘要：Recent advancements in large language models (LLMs) have shown impressive capabilities in various downstream tasks but typically face Catastrophic Forgetting (CF) during fine-tuning. In this paper, we propose the Forgetting-Aware Pruning Metric (FAPM), a novel pruning-based approach to balance CF and downstream task performance. Our investigation reveals that the degree to which task vectors (i.e., the subtraction of pre-trained weights from the weights fine-tuned on downstream tasks) overlap with pre-trained model parameters is a critical factor for CF. Based on this finding, FAPM employs the ratio of the task vector to pre-trained model parameters as a metric to quantify CF, integrating this measure into the pruning criteria. Importantly, FAPM does not necessitate modifications to the training process or model architecture, nor does it require any auxiliary data. We conducted extensive experiments across eight datasets, covering natural language inference, General Q&A, Medical Q&A, Math Q&A, reading comprehension, and cloze tests. The results demonstrate that FAPM limits CF to just 0.25\% while maintaining 99.67\% accuracy on downstream tasks. We provide the code to reproduce our results.
【10】Bias after Prompting: Persistent Discrimination in Large Language Models
标题：预算后的偏见：大型语言模型中的持续歧视
链接：https://arxiv.org/abs/2509.08146
摘要 ：从先前关于偏见转移假设（BTH）的工作中可以得出一个危险的假设，即偏见不会从预先训练的大型语言模型（LLM）转移到适应模型。我们通过研究因果模型中的BTH在即时适应下使这一假设无效，因为提示是一种非常流行且可访问的适应策略，用于现实世界的应用中。与以前的工作相比，我们发现，偏见可以通过提示和流行的基于情感的缓解方法不一致，防止偏见转移。具体来说，在人口统计学和任务中，内在偏见和迅速适应后的偏见之间的相关性仍然是中等到强的-例如，在共指解决中的性别（rho >= 0.94），以及在问题回答中的年龄（rho >= 0.98）和宗教（rho >= 0.69）。此外，我们发现，偏见仍然强烈相关时，不同的Few-Shot组成参数，如样本量，刻板印象的内容，职业分布和代表性的平衡（ρ>= 0.90）。我们评估了几种基于非线性的去偏策略，发现不同的方法具有不同的优势，但没有一种方法能持续减少模型、任务或人口统计数据之间的偏差转移。这些结果表明，纠正偏见，并可能提高推理能力，在内在模型可以防止传播偏见的下游任务。
摘要：A dangerous assumption that can be made from prior work on the bias transfer hypothesis (BTH) is that biases do not transfer from pre-trained large language models (LLMs) to adapted models. We invalidate this assumption by studying the BTH in causal models under prompt adaptations, as prompting is an extremely popular and accessible adaptation strategy used in real-world applications. In contrast to prior work, we find that biases can transfer through prompting and that popular prompt-based mitigation methods do not consistently prevent biases from transferring. Specifically, the correlation between intrinsic biases and those after prompt adaptation remain moderate to strong across demographics and tasks -- for example, gender (rho >= 0.94) in co-reference resolution, and age (rho >= 0.98) and religion (rho >= 0.69) in question answering. Further, we find that biases remain strongly correlated when varying few-shot composition parameters, such as sample size, stereotypical content, occupational distribution and representational balance (rho >= 0.90). We evaluate several prompt-based debiasing strategies and find that different approaches have distinct strengths, but none consistently reduce bias transfer across models, tasks or demographics. These results demonstrate that correcting bias, and potentially improving reasoning ability, in intrinsic models may prevent propagation of biases to downstream tasks.
【11】From Limited Data to Rare-event Prediction: LLM-powered Feature Engineering and Multi-model Learning in Venture Capital
标题：从有限数据到罕见事件预测：LLM支持的特征工程和风险投资中的多模型学习
链接：https://arxiv.org/abs/2509.08140
备注：6 pages, 3 figures
摘要：本文提出了一个框架，通过将大型语言模型（LLM）与多模型机器学习（ML）架构集成，预测罕见的高影响力结果。该方法将黑箱模型的预测能力与可靠决策所需的可解释性相结合。我们使用LLM支持的特征工程来从非结构化数据中提取和合成复杂信号，然后在包括XGBoost，随机森林和线性回归在内的分层集成模型中进行处理。该集成首先产生成功可能性的连续估计，然后将其阈值化以产生二进制罕见事件预测。我们将此框架应用于风险投资（VC）领域，投资者必须用有限且嘈杂的早期数据评估初创公司。实证结果显示了强大的性能：该模型在三个独立的测试子集中实现了9.8倍至11.1倍的随机分类器基线精度。特征敏感性分析进一步揭示了可解释的成功驱动因素：初创公司的类别列表占预测影响力的15.6%，其次是创始人数量，而教育水平和领域专业知识贡献较小但一致的影响。
摘要：This paper presents a framework for predicting rare, high-impact outcomes by integrating large language models (LLMs) with a multi-model machine learning (ML) architecture. The approach combines the predictive strength of black-box models with the interpretability required for reliable decision-making. We use LLM-powered feature engineering to extract and synthesize complex signals from unstructured data, which are then processed within a layered ensemble of models including XGBoost, Random Forest, and Linear Regression. The ensemble first produces a continuous estimate of success likelihood, which is then thresholded to produce a binary rare-event prediction. We apply this framework to the domain of Venture Capital (VC), where investors must evaluate startups with limited and noisy early-stage data. The empirical results show strong performance: the model achieves precision between 9.8X and 11.1X the random classifier baseline in three independent test subsets. Feature sensitivity analysis further reveals interpretable success drivers: the startup's category list accounts for 15.6% of predictive influence, followed by the number of founders, while education level and domain expertise contribute smaller yet consistent effects.
【12】SCA-LLM: Spectral-Attentive Channel Prediction with Large Language Models in MIMO-OFDM
标题：SCA-LLM：MMO-CDMA中使用大型语言模型的频谱关注频道预测
链接：https://arxiv.org/abs/2509.08139
摘要：近年来，大型语言模型（LLM）的成功激发了人们对探索其在无线通信中的潜在应用，特别是信道预测任务的兴趣。然而，直接将LLM应用于信道预测面临着源于其基于文本的预训练的域失配问题。为了缓解这一问题，出现了“适配器+ LLM”范例，其中适配器被设计为桥接信道状态信息（CSI）数据和LLM之间的域间隙。虽然显示出初步的成功，现有的适配器可能无法充分利用这种模式的潜力。为了解决这一限制，这项工作提供了一个关键的见解，即从CSI特征的频谱分量学习表示可以更有效地帮助弥合域间隙。因此，我们提出了一个频谱关注的框架，命名为SCA-LLM，在多输入多输出正交频分复用（MIMO-OFDM）系统的信道预测。具体来说，它的新型适配器可以捕获更精细的频谱细节，并更好地适应LLM信道预测比以前的方法。大量的仿真结果表明，SCA-LLM实现国家的最先进的预测性能和强大的推广，产生高达$-2.4~\text{dB}$归一化均方误差（NMSE）的优势，比以前的LLM为基础的方法。消融研究进一步证实了SCA-LLM在减轻结构域错配方面的优越性。
摘要：In recent years, the success of large language models (LLMs) has inspired growing interest in exploring their potential applications in wireless communications, especially for channel prediction tasks. However, directly applying LLMs to channel prediction faces a domain mismatch issue stemming from their text-based pre-training. To mitigate this, the ``adapter + LLM" paradigm has emerged, where an adapter is designed to bridge the domain gap between the channel state information (CSI) data and LLMs. While showing initial success, existing adapters may not fully exploit the potential of this paradigm. To address this limitation, this work provides a key insight that learning representations from the spectral components of CSI features can more effectively help bridge the domain gap. Accordingly, we propose a spectral-attentive framework, named SCA-LLM, for channel prediction in multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. Specifically, its novel adapter can capture finer spectral details and better adapt the LLM for channel prediction than previous methods. Extensive simulations show that SCA-LLM achieves state-of-the-art prediction performance and strong generalization, yielding up to $-2.4~\text{dB}$ normalized mean squared error (NMSE) advantage over the previous LLM based method. Ablation studies further confirm the superiority of SCA-LLM in mitigating domain mismatch.
【13】LALM-Eval: An Open-Source Toolkit for Holistic Evaluation of Large Audio Language Models
标题：LALM-Eval：一个用于大型音频语言模型整体评估的开源工具包
链接：https://arxiv.org/abs/2509.08031
摘要：大型音频语言模型（LALM）正在迅速发展，但由于效率低下的工具包限制了公平比较和系统评估，因此对其进行评估仍然具有挑战性。目前的框架存在三个关键问题：处理速度慢，阻碍了大规模研究，不一致的提示损害了可重复性，以及任务覆盖范围窄，错过了重要的音频推理能力。我们介绍了LALM评估，一个有效的和全面的评估框架LALM。我们的系统通过优化的批处理和并行执行实现了高达127%的速度比现有的工具包，使大规模的评估以前不切实际。我们提供标准化的提示协议和灵活的配置，在不同的场景中进行公平的模型比较。此外，我们还引入了两个新的评估类别：用于时间音频理解的LLM自适应Diarization和用于复杂的基于音频的认知任务的口语推理。通过对380多个任务的评估，我们揭示了当前LALM的显著差距，特别是在时间理解和复杂的口语推理任务方面。我们的研究结果还强调了音频基准中存在的教学模式缺乏标准化，这可能导致下游任务后具有挑战性的复杂教学的性能差异高达9.5个绝对点。LALM-Eval提供了实用的评估工具和对模型局限性的深入了解，推进了系统的LALM开发。
摘要 ：Large Audio Language Models (LALMs) are rapidly advancing, but evaluating them remains challenging due to inefficient toolkits that limit fair comparison and systematic assessment. Current frameworks suffer from three critical issues: slow processing that bottlenecks large-scale studies, inconsistent prompting that hurts reproducibility, and narrow task coverage that misses important audio reasoning capabilities. We introduce LALM-Eval, an efficient and comprehensive evaluation framework for LALMs. Our system achieves a speedup of up to 127% over existing toolkits through optimized batch processing and parallel execution, enabling large-scale evaluations previously impractical. We provide standardized prompting protocols and flexible configurations for fair model comparison across diverse scenarios. Additionally, we introduce two new evaluation categories: LLM-Adaptive Diarization for temporal audio understanding and Spoken Language Reasoning for complex audio-based cognitive tasks. Through evaluation across 380+ tasks, we reveal significant gaps in current LALMs, particularly in temporal understanding and complex spoken language reasoning tasks. Our findings also highlight a lack of standardization in instruction modality existent across audio benchmarks, which can lead up performance differences up to 9.5 absolute points on the challenging complex instruction following downstream tasks. LALM-Eval provides both practical evaluation tools and insights into model limitations, advancing systematic LALM development.
【14】LLM-Guided Ansätze Design for Quantum Circuit Born Machines in Financial Generative Modeling
标题：金融生成建模中量子电路诞生机的LLM引导Ansätze设计
链接：https://arxiv.org/abs/2509.08385
备注：Work presented at the 3rd International Workshop on Quantum Machine Learning: From Research to Practice (QML@QCE'25)
摘要：量子生成建模使用量子电路玻恩机（QCBMs）显示出有前途的潜力，实际的量子优势。然而，发现一个既有表现力又有硬件效率的方法仍然是一个关键的挑战，特别是在有噪声的中间尺度量子（NISQ）设备上。在这项工作中，我们引入了一个基于XML的框架，利用大型语言模型（LLM）来生成硬件感知的QCBM架构。量子数的条件是量子比特的连通性，门错误率和硬件拓扑结构，而迭代反馈，包括Kullback-Leibler（KL）发散，电路深度和有效性，是用来完善电路。我们评估我们的方法上的金融建模任务，涉及日本政府债券（JGB）利率的每日变化。我们的研究结果表明，与使用12个量子位在真正的IBM量子硬件上执行时的标准基线相比，LLM生成的ANZ显着更浅，并且实现了更好的生成性能。这些发现证明了LLM驱动的量子架构搜索的实际效用，并突出了一条通往近期量子设备的鲁棒，可部署的生成模型的有希望的道路。
摘要：Quantum generative modeling using quantum circuit Born machines (QCBMs) shows promising potential for practical quantum advantage. However, discovering ans\"atze that are both expressive and hardware-efficient remains a key challenge, particularly on noisy intermediate-scale quantum (NISQ) devices. In this work, we introduce a prompt-based framework that leverages large language models (LLMs) to generate hardware-aware QCBM architectures. Prompts are conditioned on qubit connectivity, gate error rates, and hardware topology, while iterative feedback, including Kullback-Leibler (KL) divergence, circuit depth, and validity, is used to refine the circuits. We evaluate our method on a financial modeling task involving daily changes in Japanese government bond (JGB) interest rates. Our results show that the LLM-generated ans\"atze are significantly shallower and achieve superior generative performance compared to the standard baseline when executed on real IBM quantum hardware using 12 qubits. These findings demonstrate the practical utility of LLM-driven quantum architecture search and highlight a promising path toward robust, deployable generative models for near-term quantum devices.
【15】Steering Protein Language Models
标题：引导蛋白质语言模型
链接：https://arxiv.org/abs/2509.07983
备注：Accepted to ICML 2025
摘要：蛋白质语言模型（PLMs），从天然蛋白质的广泛的进化数据预先训练，已成为蛋白质设计不可或缺的工具。虽然功能强大，但由于控制其输出的固有挑战，PLM通常难以生产具有精确指定功能或特性的蛋白质。在这项工作中，我们研究了激活转向的潜力，这是一种最初为控制大型语言模型（LLM）中的文本生成而开发的技术，可以指导PLM生成具有目标属性的蛋白质序列。我们提出了一种简单而有效的方法，采用激活编辑来引导PLM输出，并通过一种新的编辑位点识别模块将这种方法扩展到蛋白质优化。通过对溶菌酶样序列生成和优化的综合实验，我们证明了我们的方法可以无缝集成到自动编码和自回归PLM中，而无需额外的训练。这些结果突出了一个有前途的方向，精确的蛋白质工程使用的基础模型。
摘要：Protein Language Models (PLMs), pre-trained on extensive evolutionary data from natural proteins, have emerged as indispensable tools for protein design. While powerful, PLMs often struggle to produce proteins with precisely specified functionalities or properties due to inherent challenges in controlling their outputs. In this work, we investigate the potential of Activation Steering, a technique originally developed for controlling text generation in Large Language Models (LLMs), to direct PLMs toward generating protein sequences with targeted properties. We propose a simple yet effective method that employs activation editing to steer PLM outputs, and extend this approach to protein optimization through a novel editing site identification module. Through comprehensive experiments on lysozyme-like sequence generation and optimization, we demonstrate that our methods can be seamlessly integrated into both auto-encoding and autoregressive PLMs without requiring additional training. These results highlight a promising direction for precise protein engineering using foundation models.
Graph相关(图学习|图神经网络|图优化等)(3篇)
【1】Data Skeleton Learning: Scalable Active Clustering with Sparse Graph Structures
标题：数据骨架学习：具有稀疏图结构的可扩展主动集群
链接：https://arxiv.org/abs/2509.08530
摘要：在这项工作中，我们专注于基于成对约束的主动聚类的效率和可扩展性，这对于处理数据挖掘，知识注释和AI模型预训练等应用中的大规模数据至关重要。我们有三个目标：（1）减少迭代聚类更新的计算成本;（2）增强用户提供的约束的影响，以最小化精确聚类的注释要求;以及（3）减少实际部署中的内存使用。为了实现这些目标，我们提出了一个基于图的主动聚类算法，利用两个稀疏图：一个用于表示数据之间的关系（我们提出的数据骨架），另一个用于更新这个数据骨架。这两个图协同工作，使数据骨架中连接的子图能够细化，以创建嵌套的集群。我们的实证分析证实，所提出的算法始终有利于更准确的聚类与用户提供的约束输入显着减少，并优于其同行的计算性能和可扩展性，同时保持跨各种距离度量的鲁棒性。
摘要：In this work, we focus on the efficiency and scalability of pairwise constraint-based active clustering, crucial for processing large-scale data in applications such as data mining, knowledge annotation, and AI model pre-training. Our goals are threefold: (1) to reduce computational costs for iterative clustering updates; (2) to enhance the impact of user-provided constraints to minimize annotation requirements for precise clustering; and (3) to cut down memory usage in practical deployments. To achieve these aims, we propose a graph-based active clustering algorithm that utilizes two sparse graphs: one for representing relationships between data (our proposed data skeleton) and another for updating this data skeleton. These two graphs work in concert, enabling the refinement of connected subgraphs within the data skeleton to create nested clusters. Our empirical analysis confirms that the proposed algorithm consistently facilitates more accurate clustering with dramatically less input of user-provided constraints, and outperforms its counterparts in terms of computational performance and scalability, while maintaining robustness across various distance metrics.
【2】Two Sides of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models
标题：同一优化币的两面：图基础模型中的模型退化和表示崩溃
链接：https://arxiv.org/abs/2509.08401
摘要：受LLM成功的启发，图基础模型被设计为从多域TAG中学习最佳嵌入，以实现下游跨任务泛化能力。在我们的调查中，图VQ-MAE在GFM架构日益多样化的景观中脱颖而出。这是由于它能够将多个域的拓扑和文本属性联合编码到具有清晰语义边界的离散嵌入空间中。尽管有其潜力，但领域泛化冲突会导致难以察觉的陷阱。在本文中，我们实例化了其中的两个，它们就像同一个GFM优化硬币的两面-第一面模型退化：编码器和码本无法捕获输入的多样性;第二面表示崩溃：由于窄表示子空间的约束，隐藏的嵌入和码本向量无法保持语义可分性。这两个陷阱（侧面）共同损害解码器并生成低质量的重建监督，导致预训练期间的GFM优化困境（硬币）。通过实证研究，我们将上述挑战归结为信息瓶颈和规则化缺陷。为了解决这些问题，我们提出了MoT（Mixture-of-Tinkers）-（1）针对两个陷阱的信息修补程序，它利用边语义融合策略和具有域感知路由的混合码本来提高信息容量。(2)Regularization Tinker for Optimization Coin，它利用两个额外的正则化来进一步改进我们提出的Information Tinker中的梯度监督。值得注意的是，作为一个灵活的架构，MoT遵循GFM的缩放定律，提供了一个可控的模型比例。与SOTA基线相比，在6个领域的22个数据集上的实验表明，MoT在监督，Few-Shot和zero-shot场景中实现了显着的改进。
摘要：Graph foundation models, inspired by the success of LLMs, are designed to learn the optimal embedding from multi-domain TAGs for the downstream cross-task generalization capability. During our investigation, graph VQ-MAE stands out among the increasingly diverse landscape of GFM architectures. This is attributed to its ability to jointly encode topology and textual attributes from multiple domains into discrete embedding spaces with clear semantic boundaries. Despite its potential, domain generalization conflicts cause imperceptible pitfalls. In this paper, we instantiate two of them, and they are just like two sides of the same GFM optimization coin - Side 1 Model Degradation: The encoder and codebook fail to capture the diversity of inputs; Side 2 Representation Collapse: The hidden embedding and codebook vector fail to preserve semantic separability due to constraints from narrow representation subspaces. These two pitfalls (sides) collectively impair the decoder and generate the low-quality reconstructed supervision, causing the GFM optimization dilemma during pre-training (coin). Through empirical investigation, we attribute the above challenges to Information Bottleneck and Regularization Deficit. To address them, we propose MoT (Mixture-of-Tinkers) - (1) Information Tinker for Two Pitfalls, which utilizes an edge-wise semantic fusion strategy and a mixture-of-codebooks with domain-aware routing to improve information capacity. (2) Regularization Tinker for Optimization Coin, which utilizes two additional regularizations to further improve gradient supervision in our proposed Information Tinker. Notably, as a flexible architecture, MoT adheres to the scaling laws of GFM, offering a controllable model scale. Compared to SOTA baselines, experiments on 22 datasets across 6 domains demonstrate that MoT achieves significant improvements in supervised, few-shot, and zero-shot scenarios.
【3】JEL: A Novel Model Linking Knowledge Graph entities to News Mentions
标题：JEL：一种新的知识图实体与新闻提及链接模型
链接：https://arxiv.org/abs/2509.08086
摘要：我们提出了JEL，一种新的计算高效的端到端的多神经网络的实体链接模型，它击败了当前的最先进的模型。知识图已经成为一种引人注目的抽象，用于捕获感兴趣的实体之间的关键关系，并集成来自多个异构源的数据。利用知识图的核心问题是将其实体链接到提及（例如，人，公司名称），其在文本源中遇到（例如，新闻，博客。等）正确，因为每次提及都有数千个实体需要考虑。这种链接提及和实体的任务被称为实体链接（EL）。它是自然语言处理中的一项基本任务，在各种用例中都是有益的，例如构建新分析平台。在摩根大通，新闻分析是一项重要的任务，使公司的多个群体受益。根据Innovation Digital团队1进行的一项调查，公司约有25个团队正在积极寻找新闻分析解决方案，每年用于外部供应商的成本超过200万美元。实体链接对于将非结构化新闻文本与知识图连接起来至关重要，使用户能够访问知识图中的大量精选数据，并极大地促进他们的日常工作。
摘要：We present JEL, a novel computationally efficient end-to-end multi-neural network based entity linking model, which beats current state-of-art model. Knowledge Graphs have emerged as a compelling abstraction for capturing critical relationships among the entities of interest and integrating data from multiple heterogeneous sources. A core problem in leveraging a knowledge graph is linking its entities to the mentions (e.g., people, company names) that are encountered in textual sources (e.g., news, blogs., etc) correctly, since there are thousands of entities to consider for each mention. This task of linking mentions and entities is referred as Entity Linking (EL). It is a fundamental task in natural language processing and is beneficial in various uses cases, such as building a New Analytics platform. News Analytics, in JPMorgan, is an essential task that benefits multiple groups across the firm. According to a survey conducted by the Innovation Digital team 1 , around 25 teams across the firm are actively looking for news analytics solutions, and more than \$2 million is being spent annually on external vendor costs. Entity linking is critical for bridging unstructured news text with knowledge graphs, enabling users access to vast amounts of curated data in a knowledge graph and dramatically facilitating their daily work.
Transformer(3篇)
【1】RepViT-CXR: A Channel Replication Strategy for Vision Transformers in Chest X-ray Tuberculosis and Pneumonia Classification
标题：RepViT-CXR：胸部X射线结核和肺炎分类中视觉转换器的通道复制策略
链接：https://arxiv.org/abs/2509.08234
备注：10 pages, 5 figures
摘要：胸部X射线（CXR）成像仍然是用于检测肺结核（TB）和肺炎等肺部疾病的最广泛使用的诊断工具之一。深度学习的最新进展，特别是Vision Transformers（ViTs），已经显示出自动化医学图像分析的强大潜力。然而，大多数ViT架构都是在自然图像上进行预训练的，需要三通道输入，而CXR扫描本身就是灰度的。为了解决这一差距，我们提出了RepViT-CXR，一个通道复制策略，适应单通道CXR图像到ViT兼容的格式，而不会引入额外的信息丢失。我们在三个基准数据集上评估RepViT-CXR。在TB-CXR数据集上，我们的方法实现了99.9%的准确度和99.9%的AUC，超过了现有的最先进的方法，如Topo-CXR（99.3%的准确度，99.8%的AUC）。对于儿科肺炎数据集，RepViT-CXR获得了99.0%的准确率，99.2%的召回率，99.3%的精确度和99.0%的AUC，优于包括DCNN和VGG 16在内的强基线。在深圳结核病数据集上，我们的方法实现了91.1%的准确率和91.2%的AUC，比以前报道的基于CNN的方法性能有所提高。这些结果表明，一个简单而有效的通道复制策略，使ViTs充分利用其代表性的灰度医学成像任务的权力。RepViT-CXR建立了一个新的最先进的肺结核和肺炎检测从胸部X射线，显示出强大的潜力，部署在现实世界的临床筛查系统。
摘要：Chest X-ray (CXR) imaging remains one of the most widely used diagnostic tools for detecting pulmonary diseases such as tuberculosis (TB) and pneumonia. Recent advances in deep learning, particularly Vision Transformers (ViTs), have shown strong potential for automated medical image analysis. However, most ViT architectures are pretrained on natural images and require three-channel inputs, while CXR scans are inherently grayscale. To address this gap, we propose RepViT-CXR, a channel replication strategy that adapts single-channel CXR images into a ViT-compatible format without introducing additional information loss. We evaluate RepViT-CXR on three benchmark datasets. On the TB-CXR dataset,our method achieved an accuracy of 99.9% and an AUC of 99.9%, surpassing prior state-of-the-art methods such as Topo-CXR (99.3% accuracy, 99.8% AUC). For the Pediatric Pneumonia dataset, RepViT-CXR obtained 99.0% accuracy, with 99.2% recall, 99.3% precision, and an AUC of 99.0%, outperforming strong baselines including DCNN and VGG16. On the Shenzhen TB dataset, our approach achieved 91.1% accuracy and an AUC of 91.2%, marking a performance improvement over previously reported CNN-based methods. These results demonstrate that a simple yet effective channel replication strategy allows ViTs to fully leverage their representational power on grayscale medical imaging tasks. RepViT-CXR establishes a new state of the art for TB and pneumonia detection from chest X-rays, showing strong potential for deployment in real-world clinical screening systems.
【2】Selective Induction Heads: How Transformers Select Causal Structures In Context
标题：选择性诱导头：Transformer如何在背景下选择因果结构
链接：https://arxiv.org/abs/2509.08184
摘要：Transformers在序列建模任务中表现出了卓越的能力，利用了自我注意力和上下文学习。这一成功的关键是感应头，注意力回路，使复制令牌基于他们以前的出现。在这项工作中，我们介绍了一个新的框架，展示了Transformers的能力，动态处理因果结构。现有的作品依赖于马尔可夫链来研究感应头的形成，揭示了Transformers如何捕获因果依赖关系并在上下文中学习转移概率。然而，它们依赖于固定的因果结构，无法捕捉自然语言的复杂性，其中记号之间的关系随着上下文动态变化。为此，我们的框架通过具有不同滞后的交错马尔可夫链改变因果结构，同时保持转移概率固定。这种设置揭示了选择性感应头的形成，这是一种新的电路，赋予Transformers在上下文中选择正确因果结构的能力。我们的经验表明，Transformers学习这种机制，通过识别正确的滞后和复制相应的令牌从过去预测下一个令牌。我们提供了一个3层的Transformer实现选择性感应头的详细结构，并通过理论分析证明了该机制渐近收敛到最大似然解。我们的研究结果推进了对Transformers如何选择因果结构的理解，为它们的功能和可解释性提供了新的见解。
摘要：Transformers have exhibited exceptional capabilities in sequence modeling tasks, leveraging self-attention and in-context learning. Critical to this success are induction heads, attention circuits that enable copying tokens based on their previous occurrences. In this work, we introduce a novel framework that showcases transformers' ability to dynamically handle causal structures. Existing works rely on Markov Chains to study the formation of induction heads, revealing how transformers capture causal dependencies and learn transition probabilities in-context. However, they rely on a fixed causal structure that fails to capture the complexity of natural languages, where the relationship between tokens dynamically changes with context. To this end, our framework varies the causal structure through interleaved Markov chains with different lags while keeping the transition probabilities fixed. This setting unveils the formation of Selective Induction Heads, a new circuit that endows transformers with the ability to select the correct causal structure in-context. We empirically demonstrate that transformers learn this mechanism to predict the next token by identifying the correct lag and copying the corresponding token from the past. We provide a detailed construction of a 3-layer transformer to implement the selective induction head, and a theoretical analysis proving that this mechanism asymptotically converges to the maximum likelihood solution. Our findings advance the understanding of how transformers select causal structures, providing new insights into their functioning and interpretability.
【3】In-Context Learning Enhanced Credibility Transformer
标题：上下文学习增强的可信度Transformer
链接：https://arxiv.org/abs/2509.08122
摘要：我们的网络架构的起点是可信度Transformer，它通过可信度机制扩展了经典的Transformer架构，以提高模型学习和预测性能。该可信度Transformer学习可扩展的CLS令牌，这些令牌用作原始输入特征的学习表示。在本文中，我们提出了一个新的范例，增强了这种架构的上下文学习机制，即，我们通过由类似实例组成的上下文批来增加信息集。这允许模型通过额外的上下文信息和微调来增强实例的CLS令牌表示。我们经验性地验证了这种情境学习通过适应类似的风险模式来提高预测的准确性。此外，这种上下文学习还允许模型推广到新的实例，例如，在分类协变量中具有特征水平，这些特征水平在模型训练时不存在--举一个相关的例子，考虑一个汽车制造商刚刚开发的新车型。
摘要：The starting point of our network architecture is the Credibility Transformer which extends the classical Transformer architecture by a credibility mechanism to improve model learning and predictive performance. This Credibility Transformer learns credibilitized CLS tokens that serve as learned representations of the original input features. In this paper we present a new paradigm that augments this architecture by an in-context learning mechanism, i.e., we increase the information set by a context batch consisting of similar instances. This allows the model to enhance the CLS token representations of the instances by additional in-context information and fine-tuning. We empirically verify that this in-context learning enhances predictive accuracy by adapting to similar risk patterns. Moreover, this in-context learning also allows the model to generalize to new instances which, e.g., have feature levels in the categorical covariates that have not been present when the model was trained -- for a relevant example, think of a new vehicle model which has just been developed by a car manufacturer.
GAN|对抗|攻击|生成相关(2篇)
【1】MCTED: A Machine-Learning-Ready Dataset for Digital Elevation Model Generation From Mars Imagery
标题：MCTED：一个可机器学习的数据集，用于从火星图像生成数字海拔模型
链接：https://arxiv.org/abs/2509.08027
备注：22 pages, 21 figures
摘要：这项工作为火星数字高程模型预测任务提供了一个新的数据集，可用于机器学习应用程序MCTED。该数据集是使用综合管道生成的，该管道旨在处理Day等人的高分辨率火星正射影像和DEM对，产生由80，898个数据样本组成的数据集。源图像是由火星勘测轨道飞行器使用CTX仪器收集的数据，提供了火星表面非常多样化和全面的覆盖范围。考虑到大规模DEM中使用的处理管道的复杂性，原始数据中经常存在伪影和缺失数据点，我们开发了工具来解决或减轻其影响。我们将处理后的样本分为训练和验证部分，确保两个部分中的样本不覆盖共同的区域，以避免数据泄漏。数据集中的每个样本都由光学图像块、DEM块和两个掩模块表示，表示最初丢失或被我们更改的值。这使得数据集的未来用户可以随意处理更改的高程区域。我们提供生成的数据集的统计见解，包括样本的空间分布，高程值的分布，斜率等。最后，我们在MCTED数据集上训练了一个小型U-Net架构，并将其性能与单目深度估计基础模型DepthAnythingV 2在高程预测任务上进行了比较。我们发现，即使是在这个数据集上训练的非常小的架构，也能击败深度估计基础模型（如DepthAnythingV 2）的zero-shot性能。我们使数据集和用于生成它的代码在公共存储库中完全开源。
摘要：This work presents a new dataset for the Martian digital elevation model prediction task, ready for machine learning applications called MCTED. The dataset has been generated using a comprehensive pipeline designed to process high-resolution Mars orthoimage and DEM pairs from Day et al., yielding a dataset consisting of 80,898 data samples. The source images are data gathered by the Mars Reconnaissance Orbiter using the CTX instrument, providing a very diverse and comprehensive coverage of the Martian surface. Given the complexity of the processing pipelines used in large-scale DEMs, there are often artefacts and missing data points in the original data, for which we developed tools to solve or mitigate their impact. We divide the processed samples into training and validation splits, ensuring samples in both splits cover no mutual areas to avoid data leakage. Every sample in the dataset is represented by the optical image patch, DEM patch, and two mask patches, indicating values that were originally missing or were altered by us. This allows future users of the dataset to handle altered elevation regions as they please. We provide statistical insights of the generated dataset, including the spatial distribution of samples, the distributions of elevation values, slopes and more. Finally, we train a small U-Net architecture on the MCTED dataset and compare its performance to a monocular depth estimation foundation model, DepthAnythingV2, on the task of elevation prediction. We find that even a very small architecture trained on this dataset specifically, beats a zero-shot performance of a depth estimation foundation model like DepthAnythingV2. We make the dataset and code used for its generation completely open source in public repositories.
【2】CardioComposer: Flexible and Compositional Anatomical Structure Generation with Disentangled Geometric Guidance
标题：作曲家：具有解开的几何引导的灵活和组成的解剖结构生成
链接：https://arxiv.org/abs/2509.08015
备注：10 pages, 13 figures
摘要 ：当与生物物理模拟器集成时，3D解剖结构的生成模型能够为临床研究和医疗器械设计研究结构-功能关系。然而，目前的模型面临着可控性和解剖现实主义之间的权衡。我们提出了一个可编程的和组成的框架，用于指导人体解剖结构的无条件扩散模型，使用嵌入在3D空间中的可解释的椭球图元。我们的方法涉及选择多组织分割图中的某些组织，在此基础上，我们应用几何矩损失来指导反向扩散过程。该框架支持对尺寸、形状和位置的独立控制，以及推理过程中多组件约束的组合。
摘要：Generative models of 3D anatomy, when integrated with biophysical simulators, enable the study of structure-function relationships for clinical research and medical device design. However, current models face a trade-off between controllability and anatomical realism. We propose a programmable and compositional framework for guiding unconditional diffusion models of human anatomy using interpretable ellipsoidal primitives embedded in 3D space. Our method involves the selection of certain tissues within multi-tissue segmentation maps, upon which we apply geometric moment losses to guide the reverse diffusion process. This framework supports the independent control over size, shape, and position, as well as the composition of multi-component constraints during inference.
半/弱/无/有监督|不确定性|主动学习(2篇)
【1】Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition
标题：自我监督人类活动识别的集合分布蒸馏
链接：https://arxiv.org/abs/2509.08225
备注：37 pages, 10 figures
摘要：随着深度学习技术的采用，人类活动识别（HAR）取得了重大进展，但在数据要求、可靠性和鲁棒性方面仍然存在挑战。本文探讨了一种新的应用程序的包围分布蒸馏（EDD）在HAR的自我监督学习框架，旨在克服这些挑战。通过利用未标记的数据和部分监督的训练策略，我们的方法提高了预测准确性，对不确定性的鲁棒性估计，并大幅提高了对抗性扰动的鲁棒性;从而显着提高了真实世界场景中的可靠性，而不会增加推理的计算复杂性。我们证明了这一点与几个公开可用的数据集的评估。这项工作的贡献包括开发一个自我监督的EDD框架，一个创新的数据增强技术设计的HAR，和经验验证所提出的方法的有效性，提高鲁棒性和可靠性。
摘要：Human Activity Recognition (HAR) has seen significant advancements with the adoption of deep learning techniques, yet challenges remain in terms of data requirements, reliability and robustness. This paper explores a novel application of Ensemble Distribution Distillation (EDD) within a self-supervised learning framework for HAR aimed at overcoming these challenges. By leveraging unlabeled data and a partially supervised training strategy, our approach yields an increase in predictive accuracy, robust estimates of uncertainty, and substantial increases in robustness against adversarial perturbation; thereby significantly improving reliability in real-world scenarios without increasing computational complexity at inference. We demonstrate this with an evaluation on several publicly available datasets. The contributions of this work include the development of a self-supervised EDD framework, an innovative data augmentation technique designed for HAR, and empirical validation of the proposed method's effectiveness in increasing robustness and reliability.
【2】Domain Knowledge is Power: Leveraging Physiological Priors for Self Supervised Representation Learning in Electrocardiography
标题：领域知识就是力量：利用生理先验进行心电图中的自我监督表示学习
链接：https://arxiv.org/abs/2509.08116
摘要：目的：心电图（ECG）在诊断心脏病方面起着至关重要的作用;然而，基于人工智能（AI）的ECG分析的有效性往往受到标记数据有限的阻碍。自我监督学习（SSL）可以通过利用大规模未标记数据来解决这个问题。我们介绍了生理学感知的对比学习表示（ECG的生理感知对比学习表示），这是一个生理感知的对比学习框架，它结合了特定领域的先验知识，以增强基于ECG的心律失常分类的普遍性和临床相关性。研究方法：在预训练过程中，PhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPhysioPh与现有的方法不同，我们的方法将ECG生理相似性线索集成到对比学习中，促进了临床有意义的表示的学习。此外，我们引入了ECG特定的增强，保留增强后的ECG类别，并提出了一个混合损失函数，以进一步完善学习表示的质量。结果如下：我们在两个公共ECG数据集Chapman和Georgia上评估了Physiocomplete，用于多标签ECG诊断，以及标记为二进制分类的私人ICU数据集。在查普曼、乔治亚州和私人队列中，PhysioRisk将平均AUROC相对于最强基线提高了12%，强调了其强大的跨数据集泛化能力。结论：通过将生理知识嵌入到对比学习中，PhysioPhysiology使模型能够学习具有临床意义和可转移的ECG特征。重要性：生理学证明了生理学信息SSL的潜力，为更有效和标签效率更高的ECG诊断提供了一条有前途的道路。
摘要：Objective: Electrocardiograms (ECGs) play a crucial role in diagnosing heart conditions; however, the effectiveness of artificial intelligence (AI)-based ECG analysis is often hindered by the limited availability of labeled data. Self-supervised learning (SSL) can address this by leveraging large-scale unlabeled data. We introduce PhysioCLR (Physiology-aware Contrastive Learning Representation for ECG), a physiology-aware contrastive learning framework that incorporates domain-specific priors to enhance the generalizability and clinical relevance of ECG-based arrhythmia classification. Methods: During pretraining, PhysioCLR learns to bring together embeddings of samples that share similar clinically relevant features while pushing apart those that are dissimilar. Unlike existing methods, our method integrates ECG physiological similarity cues into contrastive learning, promoting the learning of clinically meaningful representations. Additionally, we introduce ECG- specific augmentations that preserve the ECG category post augmentation and propose a hybrid loss function to further refine the quality of learned representations. Results: We evaluate PhysioCLR on two public ECG datasets, Chapman and Georgia, for multilabel ECG diagnoses, as well as a private ICU dataset labeled for binary classification. Across the Chapman, Georgia, and private cohorts, PhysioCLR boosts the mean AUROC by 12% relative to the strongest baseline, underscoring its robust cross-dataset generalization. Conclusion: By embedding physiological knowledge into contrastive learning, PhysioCLR enables the model to learn clinically meaningful and transferable ECG eatures. Significance: PhysioCLR demonstrates the potential of physiology-informed SSL to offer a promising path toward more effective and label-efficient ECG diagnostics.
迁移|Zero/Few/One-Shot|自适应(12篇)
【1】ADHDeepNet From Raw EEG to Diagnosis: Improving ADHD Diagnosis through Temporal-Spatial Processing, Adaptive Attention Mechanisms, and Explainability in Raw EEG Signals
标题：ADHDepNet从原始EEG到诊断：通过时空处理，自适应注意力机制和原始EEG信号的可解释性来改善ADHD诊断
链接：https://arxiv.org/abs/2509.08779
备注：29 pages, 7 figures. Preprint. Correspondence: alijanpour@ucf.edu
摘要：注意力缺陷多动障碍（ADHD）是一种常见的儿童大脑疾病，可以持续到成年，影响社会，学术和职业生活。早期诊断对于管理这些对患者和医疗保健系统的影响至关重要，但通常是劳动密集型和耗时的。本文提出了一种新的方法，通过利用深度学习（DL）方法和脑电图（EEG）信号来提高ADHD诊断的准确性和及时性。我们介绍ADHDeepNet，这是一个DL模型，它利用了针对EEG信号优化的综合时空表征、注意力模块和可解释性技术。ADHDepNet集成了特征提取和细化过程，以增强ADHD诊断。该模型在121名参与者（61名ADHD，60名健康对照）的数据集上进行了训练和验证，采用嵌套交叉验证以获得稳健的性能。拟议的两阶段方法使用10倍的跨学科验证策略。最初，每次迭代都使用内部2重交叉验证优化模型的超参数。然后，加性高斯噪声（AGN）与不同的标准偏差和放大水平的数据增强。ADHDeepNet在分类ADHD/HC受试者方面实现了100%的灵敏度和99.17%的准确率。为了阐明模型的可解释性并识别ADHD诊断的关键大脑区域和频带，我们分析了模型主要层的学习权重和激活模式。此外，t分布随机邻居嵌入（t-SNE）可视化高维数据，帮助解释模型的决策。这项研究强调了DL和EEG在提高ADHD诊断准确性和效率方面的潜力。
摘要 ：Attention Deficit Hyperactivity Disorder (ADHD) is a common brain disorder in children that can persist into adulthood, affecting social, academic, and career life. Early diagnosis is crucial for managing these impacts on patients and the healthcare system but is often labor-intensive and time-consuming. This paper presents a novel method to improve ADHD diagnosis precision and timeliness by leveraging Deep Learning (DL) approaches and electroencephalogram (EEG) signals. We introduce ADHDeepNet, a DL model that utilizes comprehensive temporal-spatial characterization, attention modules, and explainability techniques optimized for EEG signals. ADHDeepNet integrates feature extraction and refinement processes to enhance ADHD diagnosis. The model was trained and validated on a dataset of 121 participants (61 ADHD, 60 Healthy Controls), employing nested cross-validation for robust performance. The proposed two-stage methodology uses a 10-fold cross-subject validation strategy. Initially, each iteration optimizes the model's hyper-parameters with inner 2-fold cross-validation. Then, Additive Gaussian Noise (AGN) with various standard deviations and magnification levels is applied for data augmentation. ADHDeepNet achieved 100% sensitivity and 99.17% accuracy in classifying ADHD/HC subjects. To clarify model explainability and identify key brain regions and frequency bands for ADHD diagnosis, we analyzed the learned weights and activation patterns of the model's primary layers. Additionally, t-distributed Stochastic Neighbor Embedding (t-SNE) visualized high-dimensional data, aiding in interpreting the model's decisions. This study highlights the potential of DL and EEG in enhancing ADHD diagnosis accuracy and efficiency.
【2】Implicit Shape-Prior for Few-Shot Assisted 3D Segmentation
标题：用于Few-Shot辅助3D分割的隐式形状优先
链接：https://arxiv.org/abs/2509.08580
备注：Both first Authors contributed equally to this work, lastnames in alphabetical order. This preprint has not undergone peer review or any post-submission improvements or corrections. The Version of Record of this contribution will be published in a Springer Nature Computer Science book series (CCIS, LNAI, LNBI, LNBIP, LNCS) and the doi will soon be released
摘要：本文的目的是显着减少医疗专业人员在复杂的3D分割任务，还不能完全自动化所需的手动工作量。例如，在放射治疗计划中，必须在计算机断层扫描（CT）或磁共振成像（MRI）扫描中准确识别有风险的器官，以确保它们免受有害辐射。类似地，诊断与年龄相关的退行性疾病，例如肌肉减少症，其涉及进行性肌肉体积损失和力量，通常基于通常从医疗体积的手动分割获得的肌肉质量测量。为了减轻手动分割的负担，本文介绍了一个隐式的形状之前，从稀疏切片手动注释推广到多器官的情况下，分割体积，以及一个简单的框架，自动选择信息量最大的切片，以指导和尽量减少下一个互动。实验验证显示了该方法在两个医疗用例上的有效性：在脑癌患者的风险器官的背景下进行辅助分割，以及加速创建具有肌肉减少症患者的不可见肌肉形状的新数据库。
摘要：The objective of this paper is to significantly reduce the manual workload required from medical professionals in complex 3D segmentation tasks that cannot be yet fully automated. For instance, in radiotherapy planning, organs at risk must be accurately identified in computed tomography (CT) or magnetic resonance imaging (MRI) scans to ensure they are spared from harmful radiation. Similarly, diagnosing age-related degenerative diseases such as sarcopenia, which involve progressive muscle volume loss and strength, is commonly based on muscular mass measurements often obtained from manual segmentation of medical volumes. To alleviate the manual-segmentation burden, this paper introduces an implicit shape prior to segment volumes from sparse slice manual annotations generalized to the multi-organ case, along with a simple framework for automatically selecting the most informative slices to guide and minimize the next interactions. The experimental validation shows the method's effectiveness on two medical use cases: assisted segmentation in the context of at risks organs for brain cancer patients, and acceleration of the creation of a new database with unseen muscle shapes for patients with sarcopenia.
【3】MAESTRO: Multi-modal Adaptive Ensemble for Spectro-Temporal Robust Optimization
标题：MAESTRO：光谱-时间鲁棒优化的多模式自适应集成
链接：https://arxiv.org/abs/2509.08578
摘要：及时和可靠的流感发病率预测对公共卫生决策至关重要。为了解决这个问题，我们提出了MAESTRO，一个多模态自适应Enarchy的频谱时间鲁棒优化。MAESTRO通过自适应融合多模态输入（包括监视、网络搜索趋势和气象数据）并利用全面的光谱-时间架构来实现鲁棒性。该模型首先将时间序列分解为季节和趋势分量。然后，通过混合特征增强流水线处理这些特征，该流水线结合了基于变换器的编码器、用于远程依赖性的Mamba状态空间模型、多尺度时间卷积和频域分析模块。跨渠道关注机制进一步整合了不同数据形态的信息。最后，时间投影头执行序列到序列预测，并使用可选的估计器来量化预测不确定性。根据超过11年的香港流感数据（不包括COVID-19期间）进行评估，MAESTRO显示出强大的竞争力，表现出卓越的模型拟合和相对准确性，达到最先进的R平方为0.956。广泛的消融证实了多模态融合和频谱-时间分量的重大贡献。我们的模块化和可复制的管道是公开的，以促进部署和扩展到其他地区和病原体。我们的公开管道提供了一个强大的，统一的框架，展示了先进的谱时建模和多模态数据融合的关键协同作用，以实现强大的流行病学预测。
摘要：Timely and robust influenza incidence forecasting is critical for public health decision-making. To address this, we present MAESTRO, a Multi-modal Adaptive Ensemble for Spectro-Temporal Robust Optimization. MAESTRO achieves robustness by adaptively fusing multi-modal inputs-including surveillance, web search trends, and meteorological data-and leveraging a comprehensive spectro-temporal architecture. The model first decomposes time series into seasonal and trend components. These are then processed through a hybrid feature enhancement pipeline combining Transformer-based encoders, a Mamba state-space model for long-range dependencies, multi-scale temporal convolutions, and a frequency-domain analysis module. A cross-channel attention mechanism further integrates information across the different data modalities. Finally, a temporal projection head performs sequence-to-sequence forecasting, with an optional estimator to quantify prediction uncertainty. Evaluated on over 11 years of Hong Kong influenza data (excluding the COVID-19 period), MAESTRO shows strong competitive performance, demonstrating a superior model fit and relative accuracy, achieving a state-of-the-art R-square of 0.956. Extensive ablations confirm the significant contributions of both multi-modal fusion and the spectro-temporal components. Our modular and reproducible pipeline is made publicly available to facilitate deployment and extension to other regions and pathogens.Our publicly available pipeline presents a powerful, unified framework, demonstrating the critical synergy of advanced spectro-temporal modeling and multi-modal data fusion for robust epidemiological forecasting.
【4】Behind the Scenes: Mechanistic Interpretability of LoRA-adapted Whisper for Speech Emotion Recognition
标题：幕后：用于语音情感识别的LoRA适应Whisper的机械解释性
链接：https://arxiv.org/abs/2509.08454
备注：Work in process
摘要：像Whisper这样的大型预训练语音模型提供了很强的泛化能力，但对资源有效的适应提出了重大挑战。低秩自适应（Low-Rank Adaptation，LoRA）已成为一种流行的参数有效的微调方法，但其在语音任务中的潜在机制仍然知之甚少。在这项工作中，我们进行了第一次系统的机械可解释性研究LoRA内的耳语编码器语音情感识别（SER）。使用一套分析工具，包括层贡献探测，logit镜头检查，并通过奇异值分解（SVD）和中心内核对齐（CKA）表示相似性，我们揭示了两个关键机制：延迟专业化过程，在巩固特定任务的信息之前保留早期层的一般特征，以及LoRA矩阵之间的前向对齐，后向差分动态。我们的研究结果阐明了LoRA如何重塑编码器层次结构，为在大型语音模型中设计高效和可解释的自适应策略提供了经验见解和更深层次的机械理解。
摘要 ：Large pre-trained speech models such as Whisper offer strong generalization but pose significant challenges for resource-efficient adaptation. Low-Rank Adaptation (LoRA) has become a popular parameter-efficient fine-tuning method, yet its underlying mechanisms in speech tasks remain poorly understood. In this work, we conduct the first systematic mechanistic interpretability study of LoRA within the Whisper encoder for speech emotion recognition (SER). Using a suite of analytical tools, including layer contribution probing, logit-lens inspection, and representational similarity via singular value decomposition (SVD) and centered kernel alignment (CKA), we reveal two key mechanisms: a delayed specialization process that preserves general features in early layers before consolidating task-specific information, and a forward alignment, backward differentiation dynamic between LoRA's matrices. Our findings clarify how LoRA reshapes encoder hierarchies, providing both empirical insights and a deeper mechanistic understanding for designing efficient and interpretable adaptation strategies in large speech models.
【5】Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: The Utility of Vision Foundation Models
标题：重新思考类不平衡联邦源自由域适应中的主干：Vision Foundation模型的实用性
链接：https://arxiv.org/abs/2509.08372
备注：Accepted by the IEEE ICIP 2025 Satellite Workshop 1: Edge Intelligence: Smart, Efficient, and Scalable Solutions for IoT, Wearables, and Embedded Devices (SEEDS)
摘要：联邦学习（FL）提供了一个框架，用于协作训练模型，同时保护每个客户端的数据隐私。最近，研究集中在联邦无源域自适应（FFREEDA），这是一种更现实的场景，其中客户端持有的目标域数据保持未标记，并且服务器只能在预训练期间访问源域数据。我们将此框架扩展到一个更复杂和现实的设置：类不平衡FFREEDA（CI-FFREEDA），它考虑到源和目标域中的类不平衡，以及源和目标之间以及目标客户端之间的标签转移。在我们的实验设置中复制现有的方法，使我们重新思考从增强聚合和域自适应方法到改进网络本身内的特征提取器的重点。我们建议用冻结的视觉基础模型（VFM）取代FFREEDA主干，从而提高整体准确性，而无需大量的参数调整，并降低联邦学习中的计算和通信成本。我们的实验结果表明，VFM有效地减轻了领域差距，类不平衡，甚至目标客户端之间的非IID的影响，这表明强大的特征提取器，而不是复杂的适应或FL方法，是在现实世界中FL成功的关键。
摘要：Federated Learning (FL) offers a framework for training models collaboratively while preserving data privacy of each client. Recently, research has focused on Federated Source-Free Domain Adaptation (FFREEDA), a more realistic scenario wherein client-held target domain data remains unlabeled, and the server can access source domain data only during pre-training. We extend this framework to a more complex and realistic setting: Class Imbalanced FFREEDA (CI-FFREEDA), which takes into account class imbalances in both the source and target domains, as well as label shifts between source and target and among target clients. The replication of existing methods in our experimental setup lead us to rethink the focus from enhancing aggregation and domain adaptation methods to improving the feature extractors within the network itself. We propose replacing the FFREEDA backbone with a frozen vision foundation model (VFM), thereby improving overall accuracy without extensive parameter tuning and reducing computational and communication costs in federated learning. Our experimental results demonstrate that VFMs effectively mitigate the effects of domain gaps, class imbalances, and even non-IID-ness among target clients, suggesting that strong feature extractors, not complex adaptation or FL methods, are key to success in the real-world FL.
【6】Accelerating Mixture-of-Expert Inference with Adaptive Expert Split Mechanism
标题：自适应专家分割机制加速混合专家推理
链接：https://arxiv.org/abs/2509.08342
摘要：混合专家模型（Mixture-of-Experts，MoE）已经成为现代大型语言模型（Large Language Model，LLM）的一种有前途的体系结构。然而，大量的参数会占用大量的GPU内存（即，VRAM）的需求，阻碍了MoE LLM的广泛采用。将专家参数卸载到CPU RAM提供了减轻MoE推断的VRAM要求的有效方法。现有的方法通常在VRAM中缓存专家的一个小子集，并在推理期间从RAM中动态预取专家，由于缓存命中率低和专家加载延迟大，导致推理速度显著下降。在这项工作中，我们提出了MoEpic，一个有效的MoE推理系统与一个新的专家分裂机制。具体来说，每个专家垂直分为两个部分：顶部和底部。MoEpic缓存热门专家的顶级片段，以便在有限的VRAM预算下存储更多的专家，从而提高缓存命中率。在每一层的推理过程中，MoEpic预测并预取下一层的激活专家。由于高速缓存的专家的顶部段免于获取，因此减少了加载时间，这允许有效的传输计算重叠。然而，MoEpic的性能主要取决于缓存配置（即，每层的VRAM预算和专家分流比）。为此，我们提出了一种基于定点迭代的分而治之的自适应缓存配置算法。在流行的MoE LLM上进行的大量实验表明，与基线相比，MoEpic可以节省大约一半的GPU成本，同时降低推理延迟约37.51%-65.73%。
摘要：Mixture-of-Experts (MoE) has emerged as a promising architecture for modern large language models (LLMs). However, massive parameters impose heavy GPU memory (i.e., VRAM) demands, hindering the widespread adoption of MoE LLMs. Offloading the expert parameters to CPU RAM offers an effective way to alleviate the VRAM requirements for MoE inference. Existing approaches typically cache a small subset of experts in VRAM and dynamically prefetch experts from RAM during inference, leading to significant degradation in inference speed due to the poor cache hit rate and substantial expert loading latency. In this work, we propose MoEpic, an efficient MoE inference system with a novel expert split mechanism. Specifically, each expert is vertically divided into two segments: top and bottom. MoEpic caches the top segment of hot experts, so that more experts will be stored under the limited VRAM budget, thereby improving the cache hit rate. During each layer's inference, MoEpic predicts and prefetches the activated experts for the next layer. Since the top segments of cached experts are exempt from fetching, the loading time is reduced, which allows efficient transfer-computation overlap. Nevertheless, the performance of MoEpic critically depends on the cache configuration (i.e., each layer's VRAM budget and expert split ratio). To this end, we propose a divide-and-conquer algorithm based on fixed-point iteration for adaptive cache configuration. Extensive experiments on popular MoE LLMs demonstrate that MoEpic can save about half of the GPU cost, while lowering the inference latency by about 37.51%-65.73% compared to the baselines.
【7】Adaptive Rainfall Forecasting from Multiple Geographical Models Using Matrix Profile and Ensemble Learning
标题：使用矩阵轮廓和集合学习从多个地理模型进行自适应降雨预测
链接：https://arxiv.org/abs/2509.08277
摘要：越南的降雨预测具有很大的挑战性，因为其气候条件多样，流域之间的地理变化很大，但准确可靠的预测对于洪水管理，水电运营和防灾至关重要。在这项工作中，我们提出了一个矩阵配置文件为基础的加权枚举（MPWE），政权切换框架，动态捕获多个地理模型预测之间的协变依赖关系，同时结合冗余意识的权重，以平衡跨模型的贡献。我们评估MPWE从越南8个主要流域的降雨预报，跨越5个预测范围（1小时和累计降雨量超过12，24，48，72和84小时）。实验结果表明，MPWE始终实现较低的平均值和标准差的预测误差相比，地理模型和合奏基线，证明了提高的准确性和稳定性跨流域和地平线。
摘要：Rainfall forecasting in Vietnam is highly challenging due to its diverse climatic conditions and strong geographical variability across river basins, yet accurate and reliable forecasts are vital for flood management, hydropower operation, and disaster preparedness. In this work, we propose a Matrix Profile-based Weighted Ensemble (MPWE), a regime-switching framework that dynamically captures covariant dependencies among multiple geographical model forecasts while incorporating redundancy-aware weighting to balance contributions across models. We evaluate MPWE using rainfall forecasts from eight major basins in Vietnam, spanning five forecast horizons (1 hour and accumulated rainfall over 12, 24, 48, 72, and 84 hours). Experimental results show that MPWE consistently achieves lower mean and standard deviation of prediction errors compared to geographical models and ensemble baselines, demonstrating both improved accuracy and stability across basins and horizons.
【8】Prescribe-then-Select: Adaptive Policy Selection for Contextual Stochastic Optimization
标题：先规定后选择：上下文随机优化的自适应策略选择
链接：https://arxiv.org/abs/2509.08194
摘要：我们解决上下文随机优化（CSO），协变量可作为上下文信息和决策必须满足硬可行性约束的政策选择的问题。在许多CSO设置中，多个候选策略-来自不同的建模范式-在协变量空间中表现出异构的性能，没有单一的策略均匀地占主导地位。我们提出了处方然后选择（PS），一个模块化的框架，首先构建一个库的可行的候选政策，然后学习一个元政策，以选择最好的政策，所观察到的协变量。我们使用通过训练集交叉验证训练的最优策略树集合来实现元策略，使策略选择完全由数据驱动。在两个基准的CSO问题-单阶段报童和两阶段的运输计划-PS始终优于最好的单一政策在异构制度的协变量空间和收敛到主导政策时，这种异质性是缺席的。可以在https://anonymous.4open.science/r/Prescribe-then-Select-TMLR上找到重现结果的所有代码。
摘要：We address the problem of policy selection in contextual stochastic optimization (CSO), where covariates are available as contextual information and decisions must satisfy hard feasibility constraints. In many CSO settings, multiple candidate policies--arising from different modeling paradigms--exhibit heterogeneous performance across the covariate space, with no single policy uniformly dominating. We propose Prescribe-then-Select (PS), a modular framework that first constructs a library of feasible candidate policies and then learns a meta-policy to select the best policy for the observed covariates. We implement the meta-policy using ensembles of Optimal Policy Trees trained via cross-validation on the training set, making policy choice entirely data-driven. Across two benchmark CSO problems--single-stage newsvendor and two-stage shipment planning--PS consistently outperforms the best single policy in heterogeneous regimes of the covariate space and converges to the dominant policy when such heterogeneity is absent. All the code to reproduce the results can be found at https://anonymous.4open.science/r/Prescribe-then-Select-TMLR.
【9】Multi-Label Transfer Learning in Non-Stationary Data Streams
标题：非平稳数据流中的多标签迁移学习
链接：https://arxiv.org/abs/2509.08181
备注：Accepted at IEEE International Conference on Data Mining (ICDM) 2025
摘要：多标签数据流中的标签概念通常在非平稳环境中独立地或与其他标签相关地经历漂移。在相关标签之间转移知识可以加速适应，但针对数据流的多标签转移学习的研究仍然有限。为了解决这个问题，我们提出了两种新的迁移学习方法：BR-MARLENE利用来自源和目标流中不同标签的知识进行多标签分类; BRPW-MARLENE通过显式建模和转移成对标签依赖关系来增强学习性能。综合实验表明，这两种方法在非平稳环境中的性能优于最先进的多标签流方法，证明了标签间知识转移对提高预测性能的有效性。
摘要：Label concepts in multi-label data streams often experience drift in non-stationary environments, either independently or in relation to other labels. Transferring knowledge between related labels can accelerate adaptation, yet research on multi-label transfer learning for data streams remains limited. To address this, we propose two novel transfer learning methods: BR-MARLENE leverages knowledge from different labels in both source and target streams for multi-label classification; BRPW-MARLENE builds on this by explicitly modelling and transferring pairwise label dependencies to enhance learning performance. Comprehensive experiments show that both methods outperform state-of-the-art multi-label stream approaches in non-stationary environments, demonstrating the effectiveness of inter-label knowledge transfer for improved predictive performance.
【10】MARLINE: Multi-Source Mapping Transfer Learning for Non-Stationary Environments
标题：MARLINE：非平稳环境下的多源映射迁移学习
链接：https://arxiv.org/abs/2509.08176
备注：Published in the 2020 IEEE International Conference on Data Mining (ICDM)
摘要：概念漂移是在线学习中的一个主要问题，因为它会影响数据流挖掘系统的预测性能。最近的研究已经开始探索来自不同来源的数据流，作为解决给定目标域中概念漂移的策略。这些方法假设至少有一个源模型表示与目标概念相似的概念，这在许多现实场景中可能不成立。在本文中，我们提出了一种新的方法，称为多源映射与tTransfer学习的非平稳环境（MARLINE）。MARLINE可以从非静态环境中的多个数据源的知识中受益，即使源和目标概念不匹配。这是通过将目标概念投影到每个源概念的空间来实现的，使得多个源子分类器能够作为整体的一部分对目标概念的预测做出贡献。在几个合成和真实世界数据集上的实验表明，MARLINE比几种最先进的数据流学习方法更准确。
摘要：Concept drift is a major problem in online learning due to its impact on the predictive performance of data stream mining systems. Recent studies have started exploring data streams from different sources as a strategy to tackle concept drift in a given target domain. These approaches make the assumption that at least one of the source models represents a concept similar to the target concept, which may not hold in many real-world scenarios. In this paper, we propose a novel approach called Multi-source mApping with tRansfer LearnIng for Non-stationary Environments (MARLINE). MARLINE can benefit from knowledge from multiple data sources in non-stationary environments even when source and target concepts do not match. This is achieved by projecting the target concept to the space of each source concept, enabling multiple source sub-classifiers to contribute towards the prediction of the target concept as part of an ensemble. Experiments on several synthetic and real-world datasets show that MARLINE was more accurate than several state-of-the-art data stream learning approaches.
【11】PCGBandit: One-shot acceleration of transient PDE solvers via online-learned preconditioners
标题：PCGBandit：通过在线学习预处理器一次性加速瞬时PCE解算器
链接：https://arxiv.org/abs/2509.08765
备注：25 pages, 11 figures
摘要：科学计算工作流的数据驱动加速一直是科学机器学习（ML）的一个高调目标，瞬态偏微分方程（PDE）的数值模拟是主要应用之一。到目前为止，重点一直是需要经典模拟来进行训练的方法，当与神经网络的数据饥饿和优化挑战相结合时，很难证明相对于强大的经典基线的令人信服的优势。我们考虑一种替代的范例，其中学习者使用经典求解器自己的数据来加速它，从而实现一次性的模拟加速。具体地，由于瞬态偏微分方程通常需要求解一系列相关的线性系统，因此来自对线性求解器（例如预处理共轭梯度（PCG））的重复调用的反馈可以由bandit算法用于在线学习求解器配置（例如预处理器）的自适应序列。我们开发的方法，PCGBandit，直接在流行的开源软件OpenFOAM上实现，我们用它来展示它对一组流体和磁流体力学（MHD）问题的有效性。
摘要 ：Data-driven acceleration of scientific computing workflows has been a high-profile aim of machine learning (ML) for science, with numerical simulation of transient partial differential equations (PDEs) being one of the main applications. The focus thus far has been on methods that require classical simulations to train, which when combined with the data-hungriness and optimization challenges of neural networks has caused difficulties in demonstrating a convincing advantage against strong classical baselines. We consider an alternative paradigm in which the learner uses a classical solver's own data to accelerate it, enabling a one-shot speedup of the simulation. Concretely, since transient PDEs often require solving a sequence of related linear systems, the feedback from repeated calls to a linear solver such as preconditioned conjugate gradient (PCG) can be used by a bandit algorithm to online-learn an adaptive sequence of solver configurations (e.g. preconditioners). The method we develop, PCGBandit, is implemented directly on top of the popular open source software OpenFOAM, which we use to show its effectiveness on a set of fluid and magnetohydrodynamics (MHD) problems.
【12】Enhancing Privacy Preservation and Reducing Analysis Time with Federated Transfer Learning in Digital Twins-based Computed Tomography Scan Analysis
标题：在基于数字孪生的计算机断层扫描分析中通过联邦转移学习增强隐私保护并减少分析时间
链接：https://arxiv.org/abs/2509.08018
备注：None
摘要：数字孪生（DT）技术和联邦学习（FL）的应用有很大的潜力改变生物医学图像分析领域，特别是计算机断层扫描（CT）扫描。本文提出了联邦迁移学习（FTL）作为一种新的基于数字孪生的CT扫描分析范式。FTL使用预先训练的模型和对等节点之间的知识转移来解决数据隐私，有限的计算资源和数据异构性等问题。拟议的框架允许云服务器和支持Digital Twin的CT扫描仪之间的实时协作，同时保护患者身份。我们将FTL方法应用于异构CT扫描数据集，并使用收敛时间，模型准确度，精度，召回率，F1评分和混淆矩阵评估模型性能。它已被证明比传统的FL和离散联合学习（CFL）方法更好地执行，具有更好的精确度，准确度，召回率和F1分数。该技术在数据不是独立和相同分布（非IID）的环境中是有益的，并且它为医疗诊断提供了可靠，高效和安全的解决方案。这些发现强调了使用FTL来改善基于数字孪生的CT扫描分析决策的可能性，安全有效的医学图像分析，促进隐私，并为应用精准医学和智能医疗系统开辟新的可能性。
摘要：The application of Digital Twin (DT) technology and Federated Learning (FL) has great potential to change the field of biomedical image analysis, particularly for Computed Tomography (CT) scans. This paper presents Federated Transfer Learning (FTL) as a new Digital Twin-based CT scan analysis paradigm. FTL uses pre-trained models and knowledge transfer between peer nodes to solve problems such as data privacy, limited computing resources, and data heterogeneity. The proposed framework allows real-time collaboration between cloud servers and Digital Twin-enabled CT scanners while protecting patient identity. We apply the FTL method to a heterogeneous CT scan dataset and assess model performance using convergence time, model accuracy, precision, recall, F1 score, and confusion matrix. It has been shown to perform better than conventional FL and Clustered Federated Learning (CFL) methods with better precision, accuracy, recall, and F1-score. The technique is beneficial in settings where the data is not independently and identically distributed (non-IID), and it offers reliable, efficient, and secure solutions for medical diagnosis. These findings highlight the possibility of using FTL to improve decision-making in digital twin-based CT scan analysis, secure and efficient medical image analysis, promote privacy, and open new possibilities for applying precision medicine and smart healthcare systems.
强化学习(2篇)
【1】A Survey of Reinforcement Learning for Large Reasoning Models
标题：大型推理模型的强化学习综述
链接：https://arxiv.org/abs/2509.08827
摘要：在本文中，我们综述了强化学习（RL）在大型语言模型（LLM）推理方面的最新进展。RL在推进LLM能力的前沿方面取得了显着的成功，特别是在解决数学和编码等复杂的逻辑任务方面。因此，RL已经成为将LLM转换为LRM的基础方法。随着该领域的快速发展，LRM的RL的进一步扩展现在不仅在计算资源方面面临基础挑战，而且在算法设计，训练数据和基础设施方面也面临挑战。为此，现在是时候重新审视这一领域的发展，重新评估其轨迹，并探索增强RL向人工超级智能（ASI）的可扩展性的策略。特别是，我们研究了将RL应用于LLM和LRM的推理能力的研究，特别是自DeepSeek-R1发布以来，包括基础组件，核心问题，培训资源和下游应用程序，以确定这个快速发展领域的未来机会和方向。我们希望这篇评论将促进更广泛的推理模型的强化学习的未来研究。Github网站：https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs
摘要：In this paper, we survey recent advances in Reinforcement Learning (RL) for reasoning with Large Language Models (LLMs). RL has achieved remarkable success in advancing the frontier of LLM capabilities, particularly in addressing complex logical tasks such as mathematics and coding. As a result, RL has emerged as a foundational methodology for transforming LLMs into LRMs. With the rapid progress of the field, further scaling of RL for LRMs now faces foundational challenges not only in computational resources but also in algorithm design, training data, and infrastructure. To this end, it is timely to revisit the development of this domain, reassess its trajectory, and explore strategies to enhance the scalability of RL toward Artificial SuperIntelligence (ASI). In particular, we examine research applying RL to LLMs and LRMs for reasoning abilities, especially since the release of DeepSeek-R1, including foundational components, core problems, training resources, and downstream applications, to identify future opportunities and directions for this rapidly evolving area. We hope this review will promote future research on RL for broader reasoning models. Github: https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs
【2】Replicable Reinforcement Learning with Linear Function Approximation
标题：具有线性函数逼近的可复制强化学习
链接：https://arxiv.org/abs/2509.08660
摘要：实验结果的复制一直是许多科学学科面临的挑战，包括机器学习领域。最近关于机器学习理论的工作已经将可复制性形式化为一种要求，即算法在来自同一分布的不同样本上执行两次时产生相同的结果。可证明的可复制算法对于强化学习（RL）特别有趣，其中已知算法在实践中是不稳定的。虽然可复制的算法存在于表格RL设置中，但将这些保证扩展到更实用的函数近似设置仍然是一个悬而未决的问题。在这项工作中，我们通过开发RL中线性函数逼近的可复制方法取得了进展。我们首先介绍两个有效的算法，可复制的随机设计回归和非中心协方差估计，每个独立的利益。然后，我们利用这些工具提供第一个可证明有效的可复制RL算法的线性马尔可夫决策过程中的生成模型和情节设置。最后，我们通过实验评估了我们的算法，并展示了它们如何激发更一致的神经策略。
摘要：Replication of experimental results has been a challenge faced by many scientific disciplines, including the field of machine learning. Recent work on the theory of machine learning has formalized replicability as the demand that an algorithm produce identical outcomes when executed twice on different samples from the same distribution. Provably replicable algorithms are especially interesting for reinforcement learning (RL), where algorithms are known to be unstable in practice. While replicable algorithms exist for tabular RL settings, extending these guarantees to more practical function approximation settings has remained an open problem. In this work, we make progress by developing replicable methods for linear function approximation in RL. We first introduce two efficient algorithms for replicable random design regression and uncentered covariance estimation, each of independent interest. We then leverage these tools to provide the first provably efficient replicable RL algorithms for linear Markov decision processes in both the generative model and episodic settings. Finally, we evaluate our algorithms experimentally and show how they can inspire more consistent neural policies.
医学相关(1篇)
【1】Heart Disease Prediction: A Comparative Study of Optimisers Performance in Deep Neural Networks
标题：心脏病预测：深度神经网络中优化器性能的比较研究
链接：https://arxiv.org/abs/2509.08499
备注：11 pages, 4 figures
摘要：优化一直是训练深度学习模型的一个重要因素和感兴趣的话题，但很少关注我们如何选择用于训练这些模型的优化器。因此，有必要深入研究我们如何选择用于训练的优化器以及决定这种选择的指标。在这项工作中，我们比较了10种不同的优化器在使用Kaggle的心脏病数据集训练一个简单的多层感知器模型时的性能。我们建立了一个一致的训练范式，并根据收敛速度和稳定性等指标评估优化器。我们还包括一些其他的机器学习评估指标，如AUC，精度和召回率，这些都是分类问题的核心指标。我们的研究结果表明，收敛速度和稳定性之间存在权衡，因为Adagrad和Adadelta等更稳定的优化器需要更长的时间才能收敛。在我们所有的指标中，我们选择RMSProp作为这个心脏病预测任务的最有效的优化器，因为它在关键指标上提供了平衡的性能。它实现了0.765的精确度，0.827的召回率和0.841的AUC，以及更快的训练时间。但它并不是最稳定的。我们建议，在计算受限较少的环境中，应采用这种通过全面评估选择优化器的方法，以提高训练深度学习模型的科学性和性能。
摘要：Optimization has been an important factor and topic of interest in training deep learning models, yet less attention has been given to how we select the optimizers we use to train these models. Hence, there is a need to dive deeper into how we select the optimizers we use for training and the metrics that determine this selection. In this work, we compare the performance of 10 different optimizers in training a simple Multi-layer Perceptron model using a heart disease dataset from Kaggle. We set up a consistent training paradigm and evaluate the optimizers based on metrics such as convergence speed and stability. We also include some other Machine Learning Evaluation metrics such as AUC, Precision, and Recall, which are central metrics to classification problems. Our results show that there are trade-offs between convergence speed and stability, as optimizers like Adagrad and Adadelta, which are more stable, took longer time to converge. Across all our metrics, we chose RMSProp to be the most effective optimizer for this heart disease prediction task because it offered a balanced performance across key metrics. It achieved a precision of 0.765, a recall of 0.827, and an AUC of 0.841, along with faster training time. However, it was not the most stable. We recommend that, in less compute-constrained environments, this method of choosing optimizers through a thorough evaluation should be adopted to increase the scientific nature and performance in training deep learning models.
蒸馏|知识提取(1篇)
【1】Merge-of-Thought Distillation
标题：思维融合蒸馏
链接：https://arxiv.org/abs/2509.08814
摘要：尽管有多个候选教师和不断增长的CoT语料库，但长思想链（CoT）模型的有效推理蒸馏越来越受到单个Oracle教师假设的限制。我们重新审视了教师的选择，并观察到不同的学生有不同的“最好的老师”，即使是同一个学生，最好的老师也会在不同的数据集上有所不同。因此，为了将多个教师的推理能力统一到学生中，同时克服各个教师的监督之间的冲突，我们提出了思想合并蒸馏（MoT），这是一个轻量级框架，可以在教师特定的监督微调分支和由此产生的学生变体的权重空间合并之间交替。在竞赛数学基准测试中，仅使用约200个高质量CoT样本，将MoT应用于Qwen 3 - 14 B学生超过了包括DEEPSEEK-R1，QWEN 3 - 30 B-A3 B，QWEN 3 - 32 B和OPENAI-O 1在内的强大模型，显示出显著的收益。此外，MoT始终优于最好的单教师蒸馏和天真的多教师工会，提高了性能上限，同时减轻过拟合，并显示出鲁棒性分布转移和同级教师。此外，MoT减少了灾难性的遗忘，提高了数学之外的一般推理，甚至培养了一个更好的老师，这表明共识过滤的推理特征广泛地转移。这些结果将MoT定位为一种简单，可扩展的途径，可以有效地将不同教师的长期CoT能力提取到紧凑的学生中。
摘要：Efficient reasoning distillation for long chain-of-thought (CoT) models is increasingly constrained by the assumption of a single oracle teacher, despite practical availability of multiple candidate teachers and growing CoT corpora. We revisit teacher selection and observe that different students have different "best teachers," and even for the same student the best teacher can vary across datasets. Therefore, to unify multiple teachers' reasoning abilities into student with overcoming conflicts among various teachers' supervision, we propose Merge-of-Thought Distillation (MoT), a lightweight framework that alternates between teacher-specific supervised fine-tuning branches and weight-space merging of the resulting student variants. On competition math benchmarks, using only about 200 high-quality CoT samples, applying MoT to a Qwen3-14B student surpasses strong models including DEEPSEEK-R1, QWEN3-30B-A3B, QWEN3-32B, and OPENAI-O1, demonstrating substantial gains. Besides, MoT consistently outperforms the best single-teacher distillation and the naive multi-teacher union, raises the performance ceiling while mitigating overfitting, and shows robustness to distribution-shifted and peer-level teachers. Moreover, MoT reduces catastrophic forgetting, improves general reasoning beyond mathematics and even cultivates a better teacher, indicating that consensus-filtered reasoning features transfer broadly. These results position MoT as a simple, scalable route to efficiently distilling long CoT capabilities from diverse teachers into compact students.
聚类(1篇)
【1】An upper bound of the silhouette validation metric for clustering
标题：用于集群的轮廓验证指标的上界
链接：https://arxiv.org/abs/2509.08625
摘要：侧影系数总结了每个观察结果的凝聚力与分离度[-1，1];平均侧影宽度（ASW）是聚类质量的常见内部度量，其中较高的值表示更令人垂涎的结果。然而，ASW的特定发动机最大值通常是未知的，并且标准上限1通常是无法达到的。在这项工作中，我们推导出一个给定的数据集中的每个数据点的轮廓宽度的一个尖锐的上限。通过聚合这些单独的界限，我们提出了一个规范的数据依赖的上限ASW，往往假设值远低于1。所呈现的边界可以指示单个数据点是否可以很好地放置，使基于轮廓的优化循环能够提前停止，并帮助回答一个关键问题：我的聚类结果与此特定数据的最佳可能结果有多接近？在合成数据集和真实数据集上，边界在许多情况下可以证明是接近紧的，并且提供了聚类质量评估的显着丰富。
摘要：The silhouette coefficient summarizes, per observation, cohesion versus separation in [-1, 1]; the average silhouette width (ASW) is a common internal measure of clustering quality where higher values indicate more coveted results. However, the dataset-specific maximum of ASW is typically unknown, and the standard upper limit 1 is often unattainable. In this work, we derive for each data point in a given dataset a sharp upper bound on its silhouette width. By aggregating these individual bounds, we present a canonical data-dependent upper bound on ASW that often assumes values well below 1. The presented bounds can indicate whether individual data points can ever be well placed, enable early stopping of silhouette-based optimization loops, and help answer a key question: How close is my clustering result to the best possible outcome on this specific data? Across synthetic and real datasets, the bounds are provably near-tight in many cases and offer significant enrichment of cluster quality evaluation.
超分辨率|去噪|去模糊|去雾(1篇)
【1】Learning Turbulent Flows with Generative Models: Super-resolution, Forecasting, and Sparse Flow Reconstruction
标题：用生成模型学习湍流：超分辨率、预测和稀疏流重建
链接：https://arxiv.org/abs/2509.08752
摘要 ：神经算子是动力系统的有前途的替代品，但当用标准L2损失训练时，它们往往会过度平滑精细尺度的湍流结构。在这里，我们证明了将算子学习与生成建模相结合可以克服这一限制。我们考虑三个实际的顺应流的挑战，传统的神经操作失败：时空超分辨率，预测和稀疏流重建。对于纹影射流超分辨率，一个逆向训练的神经算子（adv-NO）将能谱误差减少了15倍，同时以神经算子的推理代价保留了尖锐的梯度。对于3D均匀各向同性湍流，adv-NO仅在单个轨迹的160个时间步长上进行训练，准确地预测了五个涡流周转时间，并提供了比基线基于扩散的预报器快114倍的时钟速度，从而实现了近实时的推出。为了从高度稀疏的粒子跟踪测速输入重建圆柱尾流，条件生成模型推断出具有正确相位对准和统计的完整3D速度和压力场。这些进步使精确的重建和预测在低计算成本，使近实时的分析和控制在实验和计算流体力学触手可及。查看我们的项目页面：https://vivekoommen.github.io/Gen4Turb/
摘要：Neural operators are promising surrogates for dynamical systems but when trained with standard L2 losses they tend to oversmooth fine-scale turbulent structures. Here, we show that combining operator learning with generative modeling overcomes this limitation. We consider three practical turbulent-flow challenges where conventional neural operators fail: spatio-temporal super-resolution, forecasting, and sparse flow reconstruction. For Schlieren jet super-resolution, an adversarially trained neural operator (adv-NO) reduces the energy-spectrum error by 15x while preserving sharp gradients at neural operator-like inference cost. For 3D homogeneous isotropic turbulence, adv-NO trained on only 160 timesteps from a single trajectory forecasts accurately for five eddy-turnover times and offers 114x wall-clock speed-up at inference than the baseline diffusion-based forecasters, enabling near-real-time rollouts. For reconstructing cylinder wake flows from highly sparse Particle Tracking Velocimetry-like inputs, a conditional generative model infers full 3D velocity and pressure fields with correct phase alignment and statistics. These advances enable accurate reconstruction and forecasting at low compute cost, bringing near-real-time analysis and control within reach in experimental and computational fluid mechanics. See our project page: https://vivekoommen.github.io/Gen4Turb/
点云|SLAM|雷达|激光|深度RGBD相关(1篇)
【1】Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding
标题：用于3D点云属性编码的稀疏诱导RDO深度展开
链接：https://arxiv.org/abs/2509.08685
摘要：Given encoded 3D point cloud geometry available at the decoder, we study the problem of lossy attribute compression in a multi-resolution B-spline projection framework. A target continuous 3D attribute function is first projected onto a sequence of nested subspaces $\mathcal{F}^{(p)}_{l_0} \subseteq \cdots \subseteq \mathcal{F}^{(p)}_{L}$, where $\mathcal{F}^{(p)}_{l}$ is a family of functions spanned by a B-spline basis function of order $p$ at a chosen scale and its integer shifts. The projected low-pass coefficients $F_l^*$ are computed by variable-complexity unrolling of a rate-distortion (RD) optimization algorithm into a feed-forward network, where the rate term is the sparsity-promoting $\ell_1$-norm. Thus, the projection operation is end-to-end differentiable. For a chosen coarse-to-fine predictor, the coefficients are then adjusted to account for the prediction from a lower-resolution to a higher-resolution, which is also optimized in a data-driven manner.
摘要：Given encoded 3D point cloud geometry available at the decoder, we study the problem of lossy attribute compression in a multi-resolution B-spline projection framework. A target continuous 3D attribute function is first projected onto a sequence of nested subspaces $\mathcal{F}^{(p)}_{l_0} \subseteq \cdots \subseteq \mathcal{F}^{(p)}_{L}$, where $\mathcal{F}^{(p)}_{l}$ is a family of functions spanned by a B-spline basis function of order $p$ at a chosen scale and its integer shifts. The projected low-pass coefficients $F_l^*$ are computed by variable-complexity unrolling of a rate-distortion (RD) optimization algorithm into a feed-forward network, where the rate term is the sparsity-promoting $\ell_1$-norm. Thus, the projection operation is end-to-end differentiable. For a chosen coarse-to-fine predictor, the coefficients are then adjusted to account for the prediction from a lower-resolution to a higher-resolution, which is also optimized in a data-driven manner.
联邦学习|隐私保护|加密(7篇)
【1】PracMHBench: Re-evaluating Model-Heterogeneous Federated Learning Based on Practical Edge Device Constraints
标题：PractMHBench：基于实际边缘设备约束重新评估模型异类联邦学习
链接：https://arxiv.org/abs/2509.08750
备注：Accepted by DAC2025
摘要：在具有不同资源约束的边缘设备上联合异构模型是近年来的一个显著趋势。与传统的联邦学习（FL）假设一个相同的模型架构来协作相比，模型异构的联邦学习由于模型可以定制以满足部署需求而更加实用和灵活。不幸的是，以前的工作都没有深入到现有的模型异构FL算法下的实际边缘设备的约束，并提供各种数据场景和指标的定量分析，这促使我们重新思考和重新评估这种范式。在我们的工作中，我们构建了第一个系统平台\textbf{PracMHBench}来评估边缘设备实际约束下的模型异构FL，其中对多种模型异构算法进行了分类并在多个数据任务和指标上进行了测试。基于该平台，我们对这些算法在不同的边缘约束下进行了广泛的实验，以观察它们的适用性和相应的异构模式。
摘要：Federating heterogeneous models on edge devices with diverse resource constraints has been a notable trend in recent years. Compared to traditional federated learning (FL) that assumes an identical model architecture to cooperate, model-heterogeneous FL is more practical and flexible since the model can be customized to satisfy the deployment requirement. Unfortunately, no prior work ever dives into the existing model-heterogeneous FL algorithms under the practical edge device constraints and provides quantitative analysis on various data scenarios and metrics, which motivates us to rethink and re-evaluate this paradigm. In our work, we construct the first system platform \textbf{PracMHBench} to evaluate model-heterogeneous FL on practical constraints of edge devices, where diverse model heterogeneity algorithms are classified and tested on multiple data tasks and metrics. Based on the platform, we perform extensive experiments on these algorithms under the different edge constraints to observe their applicability and the corresponding heterogeneity pattern.
【2】Securing Private Federated Learning in a Malicious Setting: A Scalable TEE-Based Approach with Client Auditing
标题：在恶意环境中保护私人联邦学习：一种可扩展的基于EE的方法和客户审计
链接：https://arxiv.org/abs/2509.08709
备注：Accepted at PoPETs 2026
摘要：在跨设备私有联邦学习中，差分私有跟随正则化领导者（DP-FTRL）已成为一种有前途的隐私保护方法。然而，现有的方法假设一个半诚实的服务器，并没有解决安全地消除这一假设的挑战。这是由于它的状态性，这在客户端可能退出或被损坏的实际环境中变得特别有问题。虽然可信执行环境（TEE）似乎是一个显而易见的解决方案，但由于状态管理，直接的实现可能会引入分叉攻击或可用性问题。为了解决这个问题，我们介绍了一种新的服务器扩展，作为一个可信的计算基础（TCB）实现恶意安全DP-FTRL。TCB在服务器端使用临时TEE模块实现，以产生服务器动作的可验证证明。一些客户端，在被选中后，参与审核这些证明，并有少量额外的通信和计算需求。这种扩展解决方案减少了TCB的大小，同时保持了系统的可伸缩性和活性。我们提供了形式化的证明，基于交互式差分隐私，演示在恶意设置的隐私保证。最后，我们的实验表明，我们的框架在几个现实的设置中增加了小的恒定开销的客户端。
摘要 ：In cross-device private federated learning, differentially private follow-the-regularized-leader (DP-FTRL) has emerged as a promising privacy-preserving method. However, existing approaches assume a semi-honest server and have not addressed the challenge of securely removing this assumption. This is due to its statefulness, which becomes particularly problematic in practical settings where clients can drop out or be corrupted. While trusted execution environments (TEEs) might seem like an obvious solution, a straightforward implementation can introduce forking attacks or availability issues due to state management. To address this problem, our paper introduces a novel server extension that acts as a trusted computing base (TCB) to realize maliciously secure DP-FTRL. The TCB is implemented with an ephemeral TEE module on the server side to produce verifiable proofs of server actions. Some clients, upon being selected, participate in auditing these proofs with small additional communication and computational demands. This extension solution reduces the size of the TCB while maintaining the system's scalability and liveness. We provide formal proofs based on interactive differential privacy, demonstrating privacy guarantee in malicious settings. Finally, we experimentally show that our framework adds small constant overhead to clients in several realistic settings.
【3】Perfectly-Private Analog Secure Aggregation in Federated Learning
标题：联邦学习中完美私有的模拟安全聚合
链接：https://arxiv.org/abs/2509.08683
备注：Comments welcome
摘要：在联邦学习中，多方在本地训练模型，并与中央服务器共享其参数，中央服务器将其聚合以更新全局模型。为了解决通过本地模型暴露敏感数据的风险，提出了通过安全多方计算进行安全聚合以增强隐私。同时，完美的隐私只能通过均匀分布的被掩盖的局部模型来实现。这在处理实值数据时会产生一个问题，因为在掩码操作下不存在不变的实数度量，因此必然会发生信息泄漏。将数据转移到有限域可以避免这个问题，但缺点是由于定点模运算而不是浮点数可以同时处理不同大小的数字，因此会遇到固有的精度复杂度权衡问题。本文提出了一种新的安全的参数聚合方法，采用环面，而不是一个有限的字段。这种方法通过利用环面上的均匀分布来保证各方数据的完美隐私，同时避免准确性损失。实验结果表明，新协议在保持隐私性的同时，性能与无安全聚集的模型相似。与有限域安全聚合相比，基于环面的协议在某些情况下可以在模型精度和余弦相似性方面显着优于它，因此使其成为更安全的选择。
摘要：In federated learning, multiple parties train models locally and share their parameters with a central server, which aggregates them to update a global model. To address the risk of exposing sensitive data through local models, secure aggregation via secure multiparty computation has been proposed to enhance privacy. At the same time, perfect privacy can only be achieved by a uniform distribution of the masked local models to be aggregated. This raises a problem when working with real valued data, as there is no measure on the reals that is invariant under the masking operation, and hence information leakage is bound to occur. Shifting the data to a finite field circumvents this problem, but as a downside runs into an inherent accuracy complexity tradeoff issue due to fixed point modular arithmetic as opposed to floating point numbers that can simultaneously handle numbers of varying magnitudes. In this paper, a novel secure parameter aggregation method is proposed that employs the torus rather than a finite field. This approach guarantees perfect privacy for each party's data by utilizing the uniform distribution on the torus, while avoiding accuracy losses. Experimental results show that the new protocol performs similarly to the model without secure aggregation while maintaining perfect privacy. Compared to the finite field secure aggregation, the torus-based protocol can in some cases significantly outperform it in terms of model accuracy and cosine similarity, hence making it a safer choice.
【4】Strategies for Improving Communication Efficiency in Distributed and Federated Learning: Compression, Local Training, and Personalization
标题：提高分布式和联邦学习中通信效率的策略：压缩、本地训练和个性化
链接：https://arxiv.org/abs/2509.08233
备注：PhD Dissertation
摘要：分布式和联邦学习是跨分散数据源训练模型的基本范例，同时保护隐私，但通信开销仍然是一个主要瓶颈。本文从模型压缩、局部训练和个性化等方面探讨了提高通信效率的策略。我们建立了一个统一的框架有偏和无偏压缩算子的收敛保证，然后提出自适应本地训练策略，结合个性化，以加速收敛和减轻客户端漂移。特别是，Scafflix平衡了全局和个性化目标，在IID和非IID设置下都实现了卓越的性能。我们进一步引入隐私保护修剪框架，优化稀疏性，同时最大限度地减少通信成本，与队列挤压利用分层聚合，以减少跨设备开销。最后，对称后训练修剪方法SymWanda在高稀疏性下增强了鲁棒性，并且无需重新训练即可保持准确性。在基准测试和大规模语言模型上进行的大量实验表明，准确性、收敛性和通信之间存在有利的权衡，为可扩展、高效的分布式学习提供了理论和实践见解。
摘要：Distributed and federated learning are essential paradigms for training models across decentralized data sources while preserving privacy, yet communication overhead remains a major bottleneck. This dissertation explores strategies to improve communication efficiency, focusing on model compression, local training, and personalization. We establish a unified framework for biased and unbiased compression operators with convergence guarantees, then propose adaptive local training strategies that incorporate personalization to accelerate convergence and mitigate client drift. In particular, Scafflix balances global and personalized objectives, achieving superior performance under both IID and non-IID settings. We further introduce privacy-preserving pruning frameworks that optimize sparsity while minimizing communication costs, with Cohort-Squeeze leveraging hierarchical aggregation to reduce cross-device overhead. Finally, SymWanda, a symmetric post-training pruning method, enhances robustness under high sparsity and maintains accuracy without retraining. Extensive experiments on benchmarks and large-scale language models demonstrate favorable trade-offs among accuracy, convergence, and communication, offering theoretical and practical insights for scalable, efficient distributed learning.
【5】Sketched Gaussian Mechanism for Private Federated Learning
标题：私人联邦学习的草图高斯机制
链接：https://arxiv.org/abs/2509.08195
摘要：通信成本和隐私是联邦学习（FL）中的两个主要考虑因素。对于通信成本，通常使用通过绘制客户端传输的模型更新的梯度压缩来减少每轮通信。对于隐私，高斯机制（GM），它包括裁剪更新和添加高斯噪声，通常用于保证客户端级别的差分隐私。现有的私人FL的文献分析隐私的素描和GM在一个孤立的方式，说明素描提供的隐私由素描尺寸和GM必须提供任何额外的期望的隐私。 在本文中，我们介绍了素描高斯机制（SGM），它直接结合素描和高斯隐私机制。使用R\'enyi-DP工具，我们提出了一个联合分析SGM的整体隐私保证，这是显着更灵活，更尖锐的素描和GM隐私的孤立分析相比。特别是，我们证明了SGM的隐私水平为一个固定的噪声幅度是成比例的1/\sqrt{b}$，其中$b$是草图尺寸，表明（为温和的$b$）SGM可以提供更强的隐私保证比原来的GM在相同的噪声预算。我们演示了SGM的应用程序FL与梯度下降或自适应服务器优化，并建立优化收敛的理论结果，它只表现出对数依赖于参数的数量$d$。实验结果证实，在相同的隐私水平，SGM为基础的FL是至少有竞争力的非素描私人FL的变种，并优于他们在某些设置。此外，在服务器上使用自适应优化提高了经验性能，同时保持了隐私保证。
摘要：Communication cost and privacy are two major considerations in federated learning (FL). For communication cost, gradient compression by sketching the clients' transmitted model updates is often used for reducing per-round communication. For privacy, the Gaussian mechanism (GM), which consists of clipping updates and adding Gaussian noise, is commonly used to guarantee client-level differential privacy. Existing literature on private FL analyzes privacy of sketching and GM in an isolated manner, illustrating that sketching provides privacy determined by the sketching dimension and that GM has to supply any additional desired privacy. In this paper, we introduce the Sketched Gaussian Mechanism (SGM), which directly combines sketching and the Gaussian mechanism for privacy. Using R\'enyi-DP tools, we present a joint analysis of SGM's overall privacy guarantee, which is significantly more flexible and sharper compared to isolated analysis of sketching and GM privacy. In particular, we prove that the privacy level of SGM for a fixed noise magnitude is proportional to $1/\sqrt{b}$, where $b$ is the sketching dimension, indicating that (for moderate $b$) SGM can provide much stronger privacy guarantees than the original GM under the same noise budget. We demonstrate the application of SGM to FL with either gradient descent or adaptive server optimizers, and establish theoretical results on optimization convergence, which exhibits only a logarithmic dependence on the number of parameters $d$. Experimental results confirm that at the same privacy level, SGM based FL is at least competitive with non-sketching private FL variants and outperforms them in some settings. Moreover, using adaptive optimization at the server improves empirical performance while maintaining the privacy guarantees.
【6】Optimization Methods and Software for Federated Learning
标题：联邦学习的优化方法和软件
链接：https://arxiv.org/abs/2509.08120
备注：A dissertation by Konstantin Burlachenko submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy
摘要：联合学习（FL）是一种新颖的多学科机器学习范式，其中多个客户端（如移动设备）协作解决机器学习问题。FL最初由Kone et al.（2016 a，b）; McMahan et al.（2017）引入，通过将其纳入美国国家人工智能研究与发展战略计划（2023年更新）（科学与人工智能，2023年）而获得了进一步的关注。FL培训过程本质上是分散的，通常发生在与数据中心相比控制程度较低的环境中，这带来了与完全受控环境不同的独特挑战。在这篇论文中，我们确定了联邦学习中的五个关键挑战，并提出了新的方法来解决这些问题。这些挑战来自于数据和设备的异质性，沟通问题以及FL培训中客户的隐私问题。此外，即使是成熟的理论进步，在外语需要不同形式的实际实施，以提高其现实世界的适用性。我们的贡献推进FL算法和系统，弥合理论进步和实际实施。更广泛地说，我们的工作为研究人员提供了一个指南，帮助他们将理论方法转化为有效的现实世界实现和软件。此外，它提供了深入了解适应实际实现方面回到理论算法设计的反向过程。这种反向过程特别有趣，因为实践的视角迫使我们更深入地研究算法的底层机制和灵活性，经常发现所研究算法的新维度。
摘要：Federated Learning (FL) is a novel, multidisciplinary Machine Learning paradigm where multiple clients, such as mobile devices, collaborate to solve machine learning problems. Initially introduced in Kone{\v{c}}n{\'y} et al. (2016a,b); McMahan et al. (2017), FL has gained further attention through its inclusion in the National AI Research and Development Strategic Plan (2023 Update) of the United States (Science and on Artificial Intelligence, 2023). The FL training process is inherently decentralized and often takes place in less controlled settings compared to data centers, posing unique challenges distinct from those in fully controlled environments. In this thesis, we identify five key challenges in Federated Learning and propose novel approaches to address them. These challenges arise from the heterogeneity of data and devices, communication issues, and privacy concerns for clients in FL training. Moreover, even well-established theoretical advances in FL require diverse forms of practical implementation to enhance their real-world applicability. Our contributions advance FL algorithms and systems, bridging theoretical advancements and practical implementations. More broadly, our work serves as a guide for researchers navigating the complexities of translating theoretical methods into efficient real-world implementations and software. Additionally, it offers insights into the reverse process of adapting practical implementation aspects back into theoretical algorithm design. This reverse process is particularly intriguing, as the practical perspective compels us to examine the underlying mechanics and flexibilities of algorithms more deeply, often uncovering new dimensions of the algorithms under study.
【7】Hammer and Anvil: A Principled Defense Against Backdoors in Federated Learning
标题：锤子和铁锤：联邦学习中针对后门的原则性防御
链接：https://arxiv.org/abs/2509.08089
摘要：联合学习是一种分布式学习技术，其中多个客户端合作训练机器学习模型。分布式设置促进了恶意客户端的后门攻击，恶意客户端可以在参与训练过程期间将恶意行为嵌入到模型中。这些恶意行为在推理期间由特定触发器激活。没有任何防御后门攻击的方法经得起时间的考验，特别是针对自适应攻击者，这是一种强大但尚未完全开发的攻击者类别。在这项工作中，我们首先设计了一种新的自适应对手，它在能力上超过了现有的对手，产生的攻击只需要20个恶意客户端中的一个或两个就可以打破现有的最先进的防御。然后，我们提出了锤子和铁砧，一个原则性的防御方法，结合了两个防御正交的基本原则，以产生一个组合的防御，给定一组正确的参数，必须成功地抵御任何攻击。我们表明，我们最好的组合防御，克鲁姆+，是成功的对我们的新的自适应对手和国家的最先进的攻击。
摘要：Federated Learning is a distributed learning technique in which multiple clients cooperate to train a machine learning model. Distributed settings facilitate backdoor attacks by malicious clients, who can embed malicious behaviors into the model during their participation in the training process. These malicious behaviors are activated during inference by a specific trigger. No defense against backdoor attacks has stood the test of time, especially against adaptive attackers, a powerful but not fully explored category of attackers. In this work, we first devise a new adaptive adversary that surpasses existing adversaries in capabilities, yielding attacks that only require one or two malicious clients out of 20 to break existing state-of-the-art defenses. Then, we present Hammer and Anvil, a principled defense approach that combines two defenses orthogonal in their underlying principle to produce a combined defense that, given the right set of parameters, must succeed against any attack. We show that our best combined defense, Krum+, is successful against our new adaptive adversary and state-of-the-art attacks.
推理|分析|理解|解释(6篇)
【1】A layered architecture for log analysis in complex IT systems
标题：用于复杂IT系统中日志分析的分层架构
链接：https://arxiv.org/abs/2509.08698
备注：Dissertation
摘要：在不断发展的IT环境中，系统的稳定性和可靠性至关重要，但其日益增长的复杂性对DevOps团队的实施和维护提出了挑战。日志分析是AIOps的核心元素，它提供了对复杂行为和故障的重要见解。本文介绍了一种三层架构来支持DevOps的故障解决。第一层，日志调查，执行自主日志标记和异常分类。我们提出了一种无需人工标记日志数据的方法，从而实现了异常检测的监督训练和精确评估。此外，我们定义了一个分类法，将异常分为三类，以确保适当的方法选择。第二层，异常检测，检测偏离规范的行为。我们提出了一种灵活的异常检测方法，适用于无监督，弱监督和监督训练。对公共和行业数据集的评估显示F1分数在0.98和1.0之间，确保了可靠的异常检测。第三层，根本原因分析，确定最小的日志集描述故障，其起源和事件序列。通过平衡训练数据和识别关键服务，我们的根本原因分析方法始终在前10名候选人中检测到90-98%的根本原因日志行，为缓解提供可操作的见解。我们的研究涉及如何设计和优化日志分析方法，以帮助DevOps有效地解决故障。通过集成这三个层，该架构为团队提供了增强IT系统可靠性的强大方法。
摘要：In the evolving IT landscape, stability and reliability of systems are essential, yet their growing complexity challenges DevOps teams in implementation and maintenance. Log analysis, a core element of AIOps, provides critical insights into complex behaviors and failures. This dissertation introduces a three-layered architecture to support DevOps in failure resolution. The first layer, Log Investigation, performs autonomous log labeling and anomaly classification. We propose a method that labels log data without manual effort, enabling supervised training and precise evaluation of anomaly detection. Additionally, we define a taxonomy that groups anomalies into three categories, ensuring appropriate method selection. The second layer, Anomaly Detection, detects behaviors deviating from the norm. We propose a flexible Anomaly Detection method adaptable to unsupervised, weakly supervised, and supervised training. Evaluations on public and industry datasets show F1-scores between 0.98 and 1.0, ensuring reliable anomaly detection. The third layer, Root Cause Analysis, identifies minimal log sets describing failures, their origin, and event sequences. By balancing training data and identifying key services, our Root Cause Analysis method consistently detects 90-98% of root cause log lines within the top 10 candidates, providing actionable insights for mitigation. Our research addresses how log analysis methods can be designed and optimized to help DevOps resolve failures efficiently. By integrating these three layers, the architecture equips teams with robust methods to enhance IT system reliability.
【2】Interpretability as Alignment: Making Internal Understanding a Design Principle
标题：可解释性作为一致性：将内部理解作为设计原则
链接：https://arxiv.org/abs/2509.08592
备注：Pre-Print
摘要：大型神经模型越来越多地部署在高风险环境中，这引发了人们对它们的行为是否可靠地符合人类价值观的担忧。可解释性通过揭示驱动输出的计算提供了一条通往内部透明的途径。我们认为，可解释性，特别是机械的方法应被视为对齐的设计原则，而不是一个辅助诊断工具。LIME或SHAP等事后方法提供了直观但相关的解释，而电路跟踪或激活修补等机械技术可以对内部故障产生因果洞察，包括RLHF，红色团队或宪法AI等行为方法可能忽略的欺骗性或不一致的推理。尽管有这些优势，可解释性面临着可扩展性，认知不确定性和学习表征与人类概念之间的不匹配的挑战。我们的立场是，安全和值得信赖的人工智能的进展将取决于将可解释性作为人工智能研究和开发的首要目标，确保系统不仅有效，而且可审计，透明，并符合人类意图。
摘要：Large neural models are increasingly deployed in high-stakes settings, raising concerns about whether their behavior reliably aligns with human values. Interpretability provides a route to internal transparency by revealing the computations that drive outputs. We argue that interpretability especially mechanistic approaches should be treated as a design principle for alignment, not an auxiliary diagnostic tool. Post-hoc methods such as LIME or SHAP offer intuitive but correlational explanations, while mechanistic techniques like circuit tracing or activation patching yield causal insight into internal failures, including deceptive or misaligned reasoning that behavioral methods like RLHF, red teaming, or Constitutional AI may overlook. Despite these advantages, interpretability faces challenges of scalability, epistemic uncertainty, and mismatches between learned representations and human concepts. Our position is that progress on safe and trustworthy AI will depend on making interpretability a first-class objective of AI research and development, ensuring that systems are not only effective but also auditable, transparent, and aligned with human intent.
【3】Modified Loss of Momentum Gradient Descent: Fine-Grained Analysis
标题：改进的动量梯度下降损失：细粒度分析
链接：https://arxiv.org/abs/2509.08483
摘要：我们分析梯度下降与Polyak重球动量（HB），其固定的动量参数$\beta \in（0，1）$提供指数衰减的记忆。在Kovachki和Stuart（2021）的基础上，我们证明了在指数吸引不变流形上，只要步长h足够小，该算法就是具有修正损失的普通梯度下降算法。虽然修改后的损失不承认一个封闭形式的表达，我们描述它与任意精度和证明全球（有限的“时间”范围）的逼近界$O（h^{R}）$任何有限的顺序$R \geq 2$。然后，我们进行细粒度分析的组合数学基础的无记忆近似HB，特别是，找到一个丰富的家庭多项式在$\beta$隐藏在其中包含欧拉和纳拉亚纳多项式。我们推导出任意近似阶的连续修正方程（具有严格的边界）和近似HB动力学的主流，推广了Rosca等人（2023）。近似定理覆盖全批和小批HB。我们的理论研究结果揭示了重球动量梯度下降的主要特点，并概述了其他优化算法的类似分析的路线图。
摘要：We analyze gradient descent with Polyak heavy-ball momentum (HB) whose fixed momentum parameter $\beta \in (0, 1)$ provides exponential decay of memory. Building on Kovachki and Stuart (2021), we prove that on an exponentially attractive invariant manifold the algorithm is exactly plain gradient descent with a modified loss, provided that the step size $h$ is small enough. Although the modified loss does not admit a closed-form expression, we describe it with arbitrary precision and prove global (finite "time" horizon) approximation bounds $O(h^{R})$ for any finite order $R \geq 2$. We then conduct a fine-grained analysis of the combinatorics underlying the memoryless approximations of HB, in particular, finding a rich family of polynomials in $\beta$ hidden inside which contains Eulerian and Narayana polynomials. We derive continuous modified equations of arbitrary approximation order (with rigorous bounds) and the principal flow that approximates the HB dynamics, generalizing Rosca et al. (2023). Approximation theorems cover both full-batch and mini-batch HB. Our theoretical results shed new light on the main features of gradient descent with heavy-ball momentum, and outline a road-map for similar analysis of other optimization algorithms.
【4】LD-ViCE: Latent Diffusion Model for Video Counterfactual Explanations
标题：LD-ViCE：视频反事实解释的潜在扩散模型
链接：https://arxiv.org/abs/2509.08422
备注：30 pages
摘要：基于视频的人工智能系统越来越多地应用于自动驾驶和医疗保健等安全关键领域。然而，由于视频数据固有的时空复杂性和深度学习模型的不透明性，解释他们的决定仍然具有挑战性。现有的解释技术往往遭受有限的时间连贯性，鲁棒性不足，缺乏可操作的因果见解。当前的反事实解释方法通常不包含来自目标模型的指导，从而降低了语义保真度和实际效用。我们介绍了视频反事实解释的潜在扩散（LD-ViCE），这是一个旨在解释基于视频的AI模型行为的新框架。与以前的方法相比，LD-ViCE通过使用最先进的扩散模型在潜在空间中操作来降低生成解释的计算成本，同时通过额外的细化步骤来生成现实和可解释的反事实。我们的实验证明了LD-ViCE在三个不同的视频数据集上的有效性，包括EchoNet-Dynamic（心脏超声），FERV 39 k（面部表情）和Something-Something V2（动作识别）。LD-ViCE优于最新的最先进的方法，实现了R2分数高达68%的提高，同时将推理时间减少了一半。定性分析证实，LD-ViCE生成语义上有意义的和时间上连贯的解释，提供有价值的见解目标模型的行为。LD-ViCE代表了在安全关键领域中可靠部署AI的重要一步。
摘要：Video-based AI systems are increasingly adopted in safety-critical domains such as autonomous driving and healthcare. However, interpreting their decisions remains challenging due to the inherent spatiotemporal complexity of video data and the opacity of deep learning models. Existing explanation techniques often suffer from limited temporal coherence, insufficient robustness, and a lack of actionable causal insights. Current counterfactual explanation methods typically do not incorporate guidance from the target model, reducing semantic fidelity and practical utility. We introduce Latent Diffusion for Video Counterfactual Explanations (LD-ViCE), a novel framework designed to explain the behavior of video-based AI models. Compared to previous approaches, LD-ViCE reduces the computational costs of generating explanations by operating in latent space using a state-of-the-art diffusion model, while producing realistic and interpretable counterfactuals through an additional refinement step. Our experiments demonstrate the effectiveness of LD-ViCE across three diverse video datasets, including EchoNet-Dynamic (cardiac ultrasound), FERV39k (facial expression), and Something-Something V2 (action recognition). LD-ViCE outperforms a recent state-of-the-art method, achieving an increase in R2 score of up to 68% while reducing inference time by half. Qualitative analysis confirms that LD-ViCE generates semantically meaningful and temporally coherent explanations, offering valuable insights into the target model behavior. LD-ViCE represents a valuable step toward the trustworthy deployment of AI in safety-critical domains.
【5】Chordless cycle filtrations for dimensionality detection in complex networks via topological data analysis
标题：通过拓扑数据分析进行复杂网络维度检测的无弦循环过滤
链接：https://arxiv.org/abs/2509.08350
摘要：许多复杂的网络，从社会到生物系统，都表现出与潜在的双曲几何相一致的结构模式。揭示这个潜在空间的维度可以解开社区的结构复杂性，影响有效的网络导航，并从根本上塑造连通性和系统行为。我们介绍了一种新的拓扑数据分析加权计划的图形，基于无弦圈，旨在估计网络的维数在数据驱动的方式。我们进一步表明，由此产生的描述符可以有效地估计网络维数使用神经网络架构训练的合成图数据库构建为此目的，这不需要重新训练，有效地转移到现实世界的网络。因此，通过结合循环感知过滤，代数拓扑和机器学习，我们的方法提供了一个强大而有效的方法来揭示复杂网络的隐藏几何结构，并指导准确的建模和低维嵌入。
摘要 ：Many complex networks, ranging from social to biological systems, exhibit structural patterns consistent with an underlying hyperbolic geometry. Revealing the dimensionality of this latent space can disentangle the structural complexity of communities, impact efficient network navigation, and fundamentally shape connectivity and system behavior. We introduce a novel topological data analysis weighting scheme for graphs, based on chordless cycles, aimed at estimating the dimensionality of networks in a data-driven way. We further show that the resulting descriptors can effectively estimate network dimensionality using a neural network architecture trained in a synthetic graph database constructed for this purpose, which does not need retraining to transfer effectively to real-world networks. Thus, by combining cycle-aware filtrations, algebraic topology, and machine learning, our approach provides a robust and effective method for uncovering the hidden geometry of complex networks and guiding accurate modeling and low-dimensional embedding.
【6】Contributions to Robust and Efficient Methods for Analysis of High Dimensional Data
标题：对稳健有效的多维数据分析方法的贡献
链接：https://arxiv.org/abs/2509.08155
备注：PhD thesis . Available at this https URL
摘要：我们这个时代的数据的一个普遍特征是它们的超大尺寸和维度。分析这样的高维数据带来了巨大的挑战，因为特征维度通常比样本大小大得多。本文介绍了强大的和计算效率高的方法来解决与高维数据相关的几个常见的挑战。在我的第一份手稿中，我提出了一个连贯的方法来筛选变量，以适应非线性协会。我开发了一种新的变量筛选方法，超越了传统的线性假设，利用互信息，在神经影像数据的预期应用。这种方法允许通过捕获结果和协变量之间的非线性和线性关系来准确识别重要变量。在此基础上，我开发了新的优化方法稀疏估计使用非凸处罚在我的第二个手稿。这些方法解决了当前统计计算实践中的显著挑战，促进了复杂数据集的计算效率和鲁棒性分析。所提出的方法可以应用于一般类的优化问题。在我的第三篇手稿中，我通过开发一个基于Tsallis幂律熵最大化的混合效应模型，对高维相关观测的鲁棒建模做出了贡献，并讨论了这种分布的理论性质。该模型超越了传统的高斯模型的约束，通过适应更广泛的一类分布与增强的鲁棒性离群值。此外，我开发了一个近端非线性共轭梯度算法，加快收敛，同时保持数值稳定性，以及严格的统计特性的建议框架。
摘要：A ubiquitous feature of data of our era is their extra-large sizes and dimensions. Analyzing such high-dimensional data poses significant challenges, since the feature dimension is often much larger than the sample size. This thesis introduces robust and computationally efficient methods to address several common challenges associated with high-dimensional data. In my first manuscript, I propose a coherent approach to variable screening that accommodates nonlinear associations. I develop a novel variable screening method that transcends traditional linear assumptions by leveraging mutual information, with an intended application in neuroimaging data. This approach allows for accurate identification of important variables by capturing nonlinear as well as linear relationships between the outcome and covariates. Building on this foundation, I develop new optimization methods for sparse estimation using nonconvex penalties in my second manuscript. These methods address notable challenges in current statistical computing practices, facilitating computationally efficient and robust analyses of complex datasets. The proposed method can be applied to a general class of optimization problems. In my third manuscript, I contribute to robust modeling of high-dimensional correlated observations by developing a mixed-effects model based on Tsallis power-law entropy maximization and discussed the theoretical properties of such distribution. This model surpasses the constraints of conventional Gaussian models by accommodating a broader class of distributions with enhanced robustness to outliers. Additionally, I develop a proximal nonlinear conjugate gradient algorithm that accelerates convergence while maintaining numerical stability, along with rigorous statistical properties for the proposed framework.
检测相关(2篇)
【1】Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization
标题：重温Deepfake检测：按时间顺序连续学习和概括的局限性
链接：https://arxiv.org/abs/2509.07993
摘要：Deepfake生成技术的快速发展对检测系统提出了严峻的挑战，因为非持续学习方法需要频繁且昂贵的再培训。我们将deepfake检测（DFD）重新定义为一个持续学习（CL）问题，提出了一个有效的框架，该框架可以逐步适应新兴的视觉操作技术，同时保留过去生成器的知识。与依赖于不真实模拟序列的先前方法不同，我们的框架在7年的时间内模拟了deepfake技术在真实世界中的时间演变。同时，我们的框架建立在轻量级视觉主干之上，以实现DFD系统的实时性能。此外，我们贡献了两个新的指标：连续AUC（C-AUC）的历史性能和前向传递AUC（FWT-AUC）的未来推广。通过大量的实验（超过600次模拟），我们凭经验证明，虽然有效的适应（比完全再训练快155倍）和强大的历史知识保留是可能的，但由于每个现有发电机的独特印记，当前方法在没有额外训练的情况下对未来发电机的推广仍然是近随机的（FWT-AUC $\约0.5）。这些观察是我们新提出的非普适Deepfake分布假设的基础。 \textbf{代码将在验收后发布。}
摘要：The rapid evolution of deepfake generation technologies poses critical challenges for detection systems, as non-continual learning methods demand frequent and expensive retraining. We reframe deepfake detection (DFD) as a Continual Learning (CL) problem, proposing an efficient framework that incrementally adapts to emerging visual manipulation techniques while retaining knowledge of past generators. Our framework, unlike prior approaches that rely on unreal simulation sequences, simulates the real-world chronological evolution of deepfake technologies in extended periods across 7 years. Simultaneously, our framework builds upon lightweight visual backbones to allow for the real-time performance of DFD systems. Additionally, we contribute two novel metrics: Continual AUC (C-AUC) for historical performance and Forward Transfer AUC (FWT-AUC) for future generalization. Through extensive experimentation (over 600 simulations), we empirically demonstrate that while efficient adaptation (+155 times faster than full retraining) and robust retention of historical knowledge is possible, the generalization of current approaches to future generators without additional training remains near-random (FWT-AUC $\approx$ 0.5) due to the unique imprint characterizing each existing generator. Such observations are the foundation of our newly proposed Non-Universal Deepfake Distribution Hypothesis. \textbf{Code will be released upon acceptance.}
【2】RAPID Quantum Detection and Demodulation of Covert Communications: Breaking the Noise Limit with Solid-State Spin Sensors
标题：RAID秘密通信的量子检测和解调：利用固态旋转传感器打破噪音限制
链接：https://arxiv.org/abs/2509.08171
摘要：我们介绍了一个全面的框架，使用固态自旋传感器的检测和解调隐蔽的电磁信号。我们的方法，名为RAPID，是一个两阶段的混合策略，利用氮空位（NV）中心，通过模仿和蒸馏采用强大的自适应政策低于经典的噪声地板。我们首先制定联合检测和估计任务作为一个统一的随机最优控制问题，优化复合贝叶斯风险目标下现实的物理约束。RAPID算法通过首先计算基于量子Fisher信息矩阵（QRST）的鲁棒的非自适应基线协议来解决这个问题，然后使用这个基线来热启动通过深度强化学习（Soft Actor-Critic）学习的在线自适应策略。该方法动态优化控制脉冲，询问时间和测量基地，以最大限度地提高信息增益，同时积极抑制非马尔可夫噪声和退相干。数值模拟表明，该协议实现了一个显着的灵敏度增益静态方法，保持高的估计精度在相关噪声环境中，并且，当应用于传感器阵列，使相干量子波束形成，实现海森堡般的缩放精度。这项工作为在电子战和秘密监视等安全关键应用中部署量子传感器建立了理论上严格和实际可行的途径。
摘要 ：We introduce a comprehensive framework for the detection and demodulation of covert electromagnetic signals using solid-state spin sensors. Our approach, named RAPID, is a two-stage hybrid strategy that leverages nitrogen-vacancy (NV) centers to operate below the classical noise floor employing a robust adaptive policy via imitation and distillation. We first formulate the joint detection and estimation task as a unified stochastic optimal control problem, optimizing a composite Bayesian risk objective under realistic physical constraints. The RAPID algorithm solves this by first computing a robust, non-adaptive baseline protocol grounded in the quantum Fisher information matrix (QFIM), and then using this baseline to warm-start an online, adaptive policy learned via deep reinforcement learning (Soft Actor-Critic). This method dynamically optimizes control pulses, interrogation times, and measurement bases to maximize information gain while actively suppressing non-Markovian noise and decoherence. Numerical simulations demonstrate that the protocol achieves a significant sensitivity gain over static methods, maintains high estimation precision in correlated noise environments, and, when applied to sensor arrays, enables coherent quantum beamforming that achieves Heisenberg-like scaling in precision. This work establishes a theoretically rigorous and practically viable pathway for deploying quantum sensors in security-critical applications such as electronic warfare and covert surveillance.
分类|识别(5篇)
【1】Explainability of CNN Based Classification Models for Acoustic Signal
标题：基于CNN的声信号分类模型的可解释性
链接：https://arxiv.org/abs/2509.08717
备注：Accepted in IEEE ICTAI 2025
摘要：可解释人工智能（XAI）已经成为解释复杂深度学习模型预测的关键工具。虽然XAI已经越来越多地应用于声学的各个领域，但它在生物声学中的应用，包括分析来自生物体的音频信号，仍然相对不足。在本文中，我们调查了一种鸟类的发声，在北美的整个范围内具有很强的地理变异。音频记录被转换成声谱图图像，并用于训练深度卷积神经网络（CNN）进行分类，准确率达到94.8%。为了解释模型的预测，我们应用了模型不可知（LIME，SHAP）和模型特定（DeepLIFT，Grad-CAM）XAI技术。这些技术产生了不同但互补的解释，当它们的解释被考虑在一起时，它们为模型的决策提供了更完整和可解释的见解。这项工作强调了使用XAI技术组合来提高信任和互操作性的重要性，不仅在更广泛的声学信号分析中，而且还主张在不同领域的特定任务中具有更广泛的适用性。
摘要：Explainable Artificial Intelligence (XAI) has emerged as a critical tool for interpreting the predictions of complex deep learning models. While XAI has been increasingly applied in various domains within acoustics, its use in bioacoustics, which involves analyzing audio signals from living organisms, remains relatively underexplored. In this paper, we investigate the vocalizations of a bird species with strong geographic variation throughout its range in North America. Audio recordings were converted into spectrogram images and used to train a deep Convolutional Neural Network (CNN) for classification, achieving an accuracy of 94.8\%. To interpret the model's predictions, we applied both model-agnostic (LIME, SHAP) and model-specific (DeepLIFT, Grad-CAM) XAI techniques. These techniques produced different but complementary explanations, and when their explanations were considered together, they provided more complete and interpretable insights into the model's decision-making. This work highlights the importance of using a combination of XAI techniques to improve trust and interoperability, not only in broader acoustics signal analysis but also argues for broader applicability in different domain specific tasks.
【2】Classification of 24-hour movement behaviors from wrist-worn accelerometer data: from handcrafted features to deep learning techniques
标题：根据腕戴式加速度计数据对24小时运动行为进行分类：从手工制作的特征到深度学习技术
链接：https://arxiv.org/abs/2509.08606
摘要：目的：我们比较了深度学习（DL）和经典机器学习（ML）算法在将24小时运动行为分类为睡眠、久坐、轻度体力活动（LPA）和中度至剧烈体力活动（MVPA）方面的性能。方法：使用来自151名佩戴腕戴式加速度计（Axivity-AX 3）的成年人的开放访问数据。参与者被随机分为训练组、验证组和测试组（每组121人、15人和15人）。原始加速度信号被分割成不重叠的10秒窗口，然后总共提取了104个手工特征。四种DL算法-长短期记忆（LSTM），双向长短期记忆（BiLSTM），门控递归单元（GRU）和一维卷积神经网络（1D-CNN）-使用原始加速度信号和从这些信号中提取的手工特征进行训练，以预测24小时运动行为类别。手工制作的功能也被用于训练经典的ML算法，即随机森林（RF），支持向量机（SVM），极端梯度提升（XGBoost），逻辑回归（LR），人工神经网络（ANN）和决策树（DT），用于对24小时运动行为强度进行分类。结果如下：LSTM、BiLSTM和GRU在使用原始加速度信号进行训练时，总体准确率约为85%，而1D-CNN的总体准确率约为80%。当在手工特征上进行训练时，DL和经典ML算法的总体准确率在70%到81%之间。总体而言，与睡眠和久坐类别相比，MVPA和LPA的分类更容易混淆。结论：与使用手工特征训练DL和经典ML相比，使用原始加速度信号的DL方法在预测24小时运动行为强度方面仅略好。
摘要：Purpose: We compared the performance of deep learning (DL) and classical machine learning (ML) algorithms for the classification of 24-hour movement behavior into sleep, sedentary, light intensity physical activity (LPA), and moderate-to-vigorous intensity physical activity (MVPA). Methods: Open-access data from 151 adults wearing a wrist-worn accelerometer (Axivity-AX3) was used. Participants were randomly divided into training, validation, and test sets (121, 15, and 15 participants each). Raw acceleration signals were segmented into non-overlapping 10-second windows, and then a total of 104 handcrafted features were extracted. Four DL algorithms-Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BiLSTM), Gated Recurrent Units (GRU), and One-Dimensional Convolutional Neural Network (1D-CNN)-were trained using raw acceleration signals and with handcrafted features extracted from these signals to predict 24-hour movement behavior categories. The handcrafted features were also used to train classical ML algorithms, namely Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Logistic Regression (LR), Artificial Neural Network (ANN), and Decision Tree (DT) for classifying 24-hour movement behavior intensities. Results: LSTM, BiLSTM, and GRU showed an overall accuracy of approximately 85% when trained with raw acceleration signals, and 1D-CNN an overall accuracy of approximately 80%. When trained on handcrafted features, the overall accuracy for both DL and classical ML algorithms ranged from 70% to 81%. Overall, there was a higher confusion in classification of MVPA and LPA, compared to sleep and sedentary categories. Conclusion: DL methods with raw acceleration signals had only slightly better performance in predicting 24-hour movement behavior intensities, compared to when DL and classical ML were trained with handcrafted features.
【3】Motion-Based User Identification across XR and Metaverse Applications by Deep Classification and Similarity Learning
标题：通过深度分类和相似性学习跨XR和Metaverse应用程序进行基于运动的用户识别
链接：https://arxiv.org/abs/2509.08539
摘要：本文研究了两个国家的最先进的分类和相似性学习模型的泛化能力，在可靠地识别用户的基础上，他们的运动在各种延展实境（XR）的应用。我们开发了一个新的数据集，其中包含来自五个不同XR应用程序中49个用户的各种运动数据：四个具有不同任务和动作模式的XR游戏，以及一个没有预定义任务集的社交XR应用程序。该数据集用于评估性能，特别是跨应用程序的两个模型的泛化能力。我们的研究结果表明，虽然这些模型可以准确地识别同一应用程序中的个人，但它们识别不同XR应用程序中用户的能力仍然有限。总的来说，我们的研究结果提供了深入了解当前模型的泛化能力和适用性，作为用户验证和识别的生物特征识别方法。这些结果还可以作为XR和Metaverse应用程序中危险和不需要的用户识别的迫切需要的风险评估。我们的跨应用XR运动数据集和代码向公众开放，以鼓励在典型的Metaverse应用用例中对基于运动的用户识别进行类似的研究。
摘要 ：This paper examines the generalization capacity of two state-of-the-art classification and similarity learning models in reliably identifying users based on their motions in various Extended Reality (XR) applications. We developed a novel dataset containing a wide range of motion data from 49 users in five different XR applications: four XR games with distinct tasks and action patterns, and an additional social XR application with no predefined task sets. The dataset is used to evaluate the performance and, in particular, the generalization capacity of the two models across applications. Our results indicate that while the models can accurately identify individuals within the same application, their ability to identify users across different XR applications remains limited. Overall, our results provide insight into current models generalization capabilities and suitability as biometric methods for user verification and identification. The results also serve as a much-needed risk assessment of hazardous and unwanted user identification in XR and Metaverse applications. Our cross-application XR motion dataset and code are made available to the public to encourage similar research on the generalization of motion-based user identification in typical Metaverse application use cases.
【4】\emph{FoQuS}: A Forgetting-Quality Coreset Selection Framework for Automatic Modulation Recognition
链接：https://arxiv.org/abs/2509.08300
摘要：基于深度学习的自动调制识别（AMR）模型在大规模标记数据的支持下取得了重大进展。然而，在开发新模型或进行超参数调整时，使用大量数据进行重复训练所带来的时间和能量消耗往往是难以承受的。为了解决上述挑战，我们提出了\foQuS}，它通过从原始数据集中选择一个核心集来近似完整训练的效果，从而显着降低训练开销。具体来说，\foQuS}记录了全数据集训练过程中每个样本的预测轨迹，并基于训练动态构建了三个重要性度量。实验结果表明，FoQuS在多个AMR数据集上仅使用1%~ 30%的原始数据就能保持较高的识别精度和良好的跨体系结构泛化能力.
摘要：Deep learning-based Automatic Modulation Recognition (AMR) model has made significant progress with the support of large-scale labeled data. However, when developing new models or performing hyperparameter tuning, the time and energy consumption associated with repeated training using massive amounts of data are often unbearable. To address the above challenges, we propose \emph{FoQuS}, which approximates the effect of full training by selecting a coreset from the original dataset, thereby significantly reducing training overhead. Specifically, \emph{FoQuS} records the prediction trajectory of each sample during full-dataset training and constructs three importance metrics based on training dynamics. Experiments show that \emph{FoQuS} can maintain high recognition accuracy and good cross-architecture generalization on multiple AMR datasets using only 1\%-30\% of the original data.
【5】Signals vs. Videos: Advancing Motion Intention Recognition for Human-Robot Collaboration in Construction
标题：信号与视频：推进建筑中人机协作的运动意图识别
链接：https://arxiv.org/abs/2509.07990
摘要：建筑行业中的人机协作（HRC）依赖于机器人对人类运动意图和动作的精确和及时识别，以最大限度地提高安全性和工作流程效率。在比较数据形式，特别是信号和视频，用于运动意图识别方面存在研究空白。为了解决这个问题，该研究利用深度学习来评估两种不同的模式，以在干墙安装任务的早期运动阶段识别工人的运动意图。卷积神经网络-长短期记忆（CNN-LSTM）模型利用表面肌电图（sEMG）数据实现了约87%的准确度，对样本输入执行预测的平均时间为0.04秒。与此同时，预先训练的Video Swin Transformer结合迁移学习，利用视频序列作为输入来识别运动意图，准确率达到94%，但类似预测的平均时间较长，为0.15秒。这项研究强调了这两种数据格式的独特优势和权衡，指导其系统部署，以提高HRC在现实世界的建设项目。
摘要：Human-robot collaboration (HRC) in the construction industry depends on precise and prompt recognition of human motion intentions and actions by robots to maximize safety and workflow efficiency. There is a research gap in comparing data modalities, specifically signals and videos, for motion intention recognition. To address this, the study leverages deep learning to assess two different modalities in recognizing workers' motion intention at the early stage of movement in drywall installation tasks. The Convolutional Neural Network - Long Short-Term Memory (CNN-LSTM) model utilizing surface electromyography (sEMG) data achieved an accuracy of around 87% with an average time of 0.04 seconds to perform prediction on a sample input. Meanwhile, the pre-trained Video Swin Transformer combined with transfer learning harnessed video sequences as input to recognize motion intention and attained an accuracy of 94% but with a longer average time of 0.15 seconds for a similar prediction. This study emphasizes the unique strengths and trade-offs of both data formats, directing their systematic deployments to enhance HRC in real-world construction projects.
表征(1篇)
【1】MasconCube: Fast and Accurate Gravity Modeling with an Explicit Representation
标题：MasconCube：具有显式表示的快速准确的重力建模
链接：https://arxiv.org/abs/2509.08607
摘要：不规则形状的小天体的大地测量对引力场建模提出了根本性的挑战，特别是随着深空探测任务越来越多地以小行星和彗星为目标。传统的方法受到严重的限制：球面谐波在航天器通常运行的布里渊球内发散，多面体模型假设不切实际的均匀密度分布，现有的机器学习方法，如GeodesyNets和物理信息神经网络（PINN-GM）需要大量的计算资源和训练时间。这项工作介绍了MasconCubes，一种新的自监督学习方法，将重力反演作为一个直接优化问题，在一个规则的3D网格的点质量（mascons）。与隐式神经表示不同，MasconCubes显式地对质量分布进行建模，同时利用已知的小行星形状信息来约束解决方案空间。对包括Bennu、Eros、Itokawa和合成小行星在内的各种小行星模型的综合评估表明，MasconCubes在多个指标上实现了卓越的性能。最值得注意的是，MasconCubes展示了计算效率的优势，其训练时间比GeodesyNets快约40倍，同时通过显式质量分布保持物理可解释性。这些结果建立MasconCubes作为一个有前途的方法，任务关键的重力建模应用程序，需要高精度，计算效率和物理洞察不规则天体的内部质量分布。
摘要：The geodesy of irregularly shaped small bodies presents fundamental challenges for gravitational field modeling, particularly as deep space exploration missions increasingly target asteroids and comets. Traditional approaches suffer from critical limitations: spherical harmonics diverge within the Brillouin sphere where spacecraft typically operate, polyhedral models assume unrealistic homogeneous density distributions, and existing machine learning methods like GeodesyNets and Physics-Informed Neural Networks (PINN-GM) require extensive computational resources and training time. This work introduces MasconCubes, a novel self-supervised learning approach that formulates gravity inversion as a direct optimization problem over a regular 3D grid of point masses (mascons). Unlike implicit neural representations, MasconCubes explicitly model mass distributions while leveraging known asteroid shape information to constrain the solution space. Comprehensive evaluation on diverse asteroid models including Bennu, Eros, Itokawa, and synthetic planetesimals demonstrates that MasconCubes achieve superior performance across multiple metrics. Most notably, MasconCubes demonstrate computational efficiency advantages with training times approximately 40 times faster than GeodesyNets while maintaining physical interpretability through explicit mass distributions. These results establish MasconCubes as a promising approach for mission-critical gravitational modeling applications requiring high accuracy, computational efficiency, and physical insight into internal mass distributions of irregular celestial bodies.
编码器(2篇)
【1】OCTANE -- Optimal Control for Tensor-based Autoencoder Network Emergence: Explicit Case
标题：OCTANE --基于张量的自动编码器网络涌现的最优控制：显式情况
链接：https://arxiv.org/abs/2509.08169
摘要：本文提出了一种新的、数学上严格的自动编码器型深度神经网络框架，该框架结合了最优控制理论和低秩张量方法，以实现内存高效的训练和自动架构发现。的学习任务制定为由微分方程表示的编码器和解码器组件的网络和相应的最优性条件通过拉格朗日方法推导出的约束的优化问题。有效的内存压缩，使低秩张量流形上使用自适应显式积分方案近似微分方程的解决方案。这些概念结合在一起形成了OCTANE（基于张量的自动编码器网络涌现的最优控制）-一个统一的训练框架，可以产生紧凑的自动编码器架构，减少内存使用，并实现有效的学习，即使训练数据有限。该框架的实用程序说明了与应用程序的图像去噪和去模糊任务，并提供有关管理超参数的建议。
摘要 ：This paper presents a novel, mathematically rigorous framework for autoencoder-type deep neural networks that combines optimal control theory and low-rank tensor methods to yield memory-efficient training and automated architecture discovery. The learning task is formulated as an optimization problem constrained by differential equations representing the encoder and decoder components of the network and the corresponding optimality conditions are derived via a Lagrangian approach. Efficient memory compression is enabled by approximating differential equation solutions on low-rank tensor manifolds using an adaptive explicit integration scheme. These concepts are combined to form OCTANE (Optimal Control for Tensor-based Autoencoder Network Emergence) -- a unified training framework that yields compact autoencoder architectures, reduces memory usage, and enables effective learning, even with limited training data. The framework's utility is illustrated with application to image denoising and deblurring tasks and recommendations regarding governing hyperparameters are provided.
【2】DLGE: Dual Local-Global Encoding for Generalizable Cross-BCI-Paradigm
标题：DLGE：可推广跨BCI范式的双本地-全局编码
链接：https://arxiv.org/abs/2509.07991
摘要：深度学习模型经常用于解码基于脑电图（EEG）的单个脑机接口（BCI）范例。由于不同的障碍，如不同的通道配置和不同的任务相关表示，使用一个模型解码多个BCI范例是具有挑战性的。在这项研究中，我们提出了双局部全局编码器（DLGE），使不同的BCI范式的分类。为了解决不同范式的EEG通道配置的异质性，我们采用了解剖学启发的脑区域划分和填充策略来标准化EEG通道配置。在所提出的模型中，本地编码器被设计为基于时间-频率信息在每个脑区域内学习跨BCI范例的共享特征，其将单个通道上的时间注意力与每个脑区域的通道之间的空间注意力相结合。这些共享特征随后在全局编码器中聚合以形成各自的特定于范例的特征表示。三个BCI范式（运动想象，休息状态，驾驶疲劳）被用来评估所提出的模型。结果表明，我们的模型能够处理不同的BCI范式，无需重新训练和重新调整，平均宏观准确率、召回率和F1得分分别为60.16%、59.88%和59.56%。我们初步尝试开发一个通用的跨BCI范式分类模型，避免重新训练或重新开发每个范式。本研究为开发一种有效而简单的跨BCI范式解码模型铺平了道路，这可能有利于通用BCI解码的便携式设备的设计。
摘要：Deep learning models have been frequently used to decode a single brain-computer interface (BCI) paradigm based on electroencephalography (EEG). It is challenging to decode multiple BCI paradigms using one model due to diverse barriers, such as different channel configurations and disparate task-related representations. In this study, we propose Dual Local-Global Encoder (DLGE), enabling the classification across different BCI paradigms. To address the heterogeneity in EEG channel configurations across paradigms, we employ an anatomically inspired brain-region partitioning and padding strategy to standardize EEG channel configuration. In the proposed model, the local encoder is designed to learn shared features across BCI paradigms within each brain region based on time-frequency information, which integrates temporal attention on individual channels with spatial attention among channels for each brain region. These shared features are subsequently aggregated in the global encoder to form respective paradigm-specific feature representations. Three BCI paradigms (motor imagery, resting state, and driving fatigue) were used to evaluate the proposed model. The results demonstrate that our model is capable of processing diverse BCI paradigms without retraining and retuning, achieving average macro precision, recall, and F1-score of 60.16\%, 59.88\%, and 59.56\%, respectively. We made an initial attempt to develop a general model for cross-BCI-paradigm classification, avoiding retraining or redevelopment for each paradigm. This study paves the way for the development of an effective but simple model for cross-BCI-paradigm decoding, which might benefit the design of portable devices for universal BCI decoding.
优化|敛散性(2篇)
【1】Decentralized Stochastic Nonconvex Optimization under the Relaxed Smoothness
标题：松弛光滑性下的分散随机非凸优化
链接：https://arxiv.org/abs/2509.08726
摘要：This paper studies decentralized optimization problem $f(\mathbf{x})=\frac{1}{m}\sum_{i=1}^m f_i(\mathbf{x})$, where each local function has the form of $f_i(\mathbf{x}) = {\mathbb E}\left[F(\mathbf{x};{\xi}_i)\right]$ which is $(L_0,L_1)$-smooth but possibly nonconvex and the random variable ${\xi}_i$ follows distribution ${\mathcal D}_i$. We propose a novel algorithm called decentralized normalized stochastic gradient descent (DNSGD), which can achieve the $\epsilon$-stationary point on each local agent. We present a new framework for analyzing decentralized first-order methods in the relaxed smooth setting, based on the Lyapunov function related to the product of the gradient norm and the consensus error. The analysis shows upper bounds on sample complexity of ${\mathcal O}(m^{-1}(L_f\sigma^2\Delta_f\epsilon^{-4} + \sigma^2\epsilon^{-2} + L_f^{-2}L_1^3\sigma^2\Delta_f\epsilon^{-1} + L_f^{-2}L_1^2\sigma^2))$ per agent and communication complexity of $\tilde{\mathcal O}((L_f\epsilon^{-2} + L_1\epsilon^{-1})\gamma^{-1/2}\Delta_f)$, where $L_f=L_0 +L_1\zeta$, $\sigma^2$ is the variance of the stochastic gradient, $\Delta_f$ is the initial optimal function value gap, $\gamma$ is the spectral gap of the network, and $\zeta$ is the degree of the gradient dissimilarity. In the special case of $L_1=0$, the above results (nearly) match the lower bounds on decentralized nonconvex optimization in the standard smooth setting. We also conduct numerical experiments to show the empirical superiority of our method.
摘要：This paper studies decentralized optimization problem $f(\mathbf{x})=\frac{1}{m}\sum_{i=1}^m f_i(\mathbf{x})$, where each local function has the form of $f_i(\mathbf{x}) = {\mathbb E}\left[F(\mathbf{x};{\xi}_i)\right]$ which is $(L_0,L_1)$-smooth but possibly nonconvex and the random variable ${\xi}_i$ follows distribution ${\mathcal D}_i$. We propose a novel algorithm called decentralized normalized stochastic gradient descent (DNSGD), which can achieve the $\epsilon$-stationary point on each local agent. We present a new framework for analyzing decentralized first-order methods in the relaxed smooth setting, based on the Lyapunov function related to the product of the gradient norm and the consensus error. The analysis shows upper bounds on sample complexity of ${\mathcal O}(m^{-1}(L_f\sigma^2\Delta_f\epsilon^{-4} + \sigma^2\epsilon^{-2} + L_f^{-2}L_1^3\sigma^2\Delta_f\epsilon^{-1} + L_f^{-2}L_1^2\sigma^2))$ per agent and communication complexity of $\tilde{\mathcal O}((L_f\epsilon^{-2} + L_1\epsilon^{-1})\gamma^{-1/2}\Delta_f)$, where $L_f=L_0 +L_1\zeta$, $\sigma^2$ is the variance of the stochastic gradient, $\Delta_f$ is the initial optimal function value gap, $\gamma$ is the spectral gap of the network, and $\zeta$ is the degree of the gradient dissimilarity. In the special case of $L_1=0$, the above results (nearly) match the lower bounds on decentralized nonconvex optimization in the standard smooth setting. We also conduct numerical experiments to show the empirical superiority of our method.
【2】Gaussian Process Regression -- Neural Network Hybrid with Optimized Redundant Coordinates
标题：高斯过程回归--优化冗余坐标的神经网络混合
链接：https://arxiv.org/abs/2509.08457
摘要：最近，提出了一种高斯过程回归-神经网络（GPRNN）混合机器学习方法，其基于由规则构造的冗余坐标中的加性核GPR [J. Phys. Chem. A 127（2023）7823]。该方法将神经网络的表达能力与线性回归的鲁棒性相结合，特别是当神经元数量增加到超过最佳值时，相对于过拟合。我们引入opt-GPRNN，其中GPRNN的冗余坐标用蒙特卡洛算法进行优化，并表明当与冗余坐标的优化相结合时，GPRNN以更少的术语/神经元达到最低的测试集误差，并保留了避免过拟合的优点，当神经元的数量增加超过最佳值时。该方法，opt-GPRNN具有更接近的多层神经网络的表达能力，并可以满足某些应用中对深层神经网络的需求。利用优化的冗余坐标，降维机制也是可能的。给出了在机器学习、原子间相互作用势和材料信息学中的应用实例.
摘要：Recently, a Gaussian Process Regression - neural network (GPRNN) hybrid machine learning method was proposed, which is based on additive-kernel GPR in redundant coordinates constructed by rules [J. Phys. Chem. A 127 (2023) 7823]. The method combined the expressive power of an NN with the robustness of linear regression, in particular, with respect to overfitting when the number of neurons is increased beyond optimal. We introduce opt-GPRNN, in which the redundant coordinates of GPRNN are optimized with a Monte Carlo algorithm and show that when combined with optimization of redundant coordinates, GPRNN attains the lowest test set error with much fewer terms / neurons and retains the advantage of avoiding overfitting when the number of neurons is increased beyond optimal value. The method, opt-GPRNN possesses an expressive power closer to that of a multilayer NN and could obviate the need for deep NNs in some applications. With optimized redundant coordinates, a dimensionality reduction regime is also possible. Examples of application to machine learning an interatomic potential and materials informatics are given.
预测|估计(6篇)
【1】Machine Learning-Based Prediction of Speech Arrest During Direct Cortical Stimulation Mapping
标题：直接皮质刺激映射期间基于机器学习的言语停止预测
链接：https://arxiv.org/abs/2509.08703
备注：Accepted at IEEE International Conference on Neural Engineering (NER), 2025. This is the author's accepted manuscript
摘要：识别对语言至关重要的皮层区域对于在语言区域或附近进行安全的脑外科手术至关重要。虽然电刺激标测（ESM）仍然是临床的金标准，但它是侵入性的和耗时的。为了解决这个问题，我们分析了16名参与者执行语音任务的颅内皮层脑电图（ECoG）数据，并开发了机器学习模型来直接预测每个ECoG电极下方的大脑区域是否至关重要。从电刺激映射（ESM）独立地导出指示言语停滞的地面实况标签，并用于训练分类模型。我们的框架集成了神经活动信号，解剖区域标签和功能连接功能，以捕获局部活动和网络级动态。我们发现，结合区域和连通性特征的模型与完整特征集的性能相匹配，并且优于单独使用任一类型的模型。为了对每个电极进行分类，使用应用于直方图编码评分的MLP对试验级预测进行汇总。我们表现最好的模型，一个试验级的RBF核支持向量机与基于MLP的聚合，实现了很强的准确性，对坚持的参与者（ROC-AUC：0.87，PR-AUC：0.57）。这些发现突出了空间和网络信息与非线性建模相结合的价值，以提高功能映射在术前评估。
摘要：Identifying cortical regions critical for speech is essential for safe brain surgery in or near language areas. While Electrical Stimulation Mapping (ESM) remains the clinical gold standard, it is invasive and time-consuming. To address this, we analyzed intracranial electrocorticographic (ECoG) data from 16 participants performing speech tasks and developed machine learning models to directly predict if the brain region underneath each ECoG electrode is critical. Ground truth labels indicating speech arrest were derived independently from Electrical Stimulation Mapping (ESM) and used to train classification models. Our framework integrates neural activity signals, anatomical region labels, and functional connectivity features to capture both local activity and network-level dynamics. We found that models combining region and connectivity features matched the performance of the full feature set, and outperformed models using either type alone. To classify each electrode, trial-level predictions were aggregated using an MLP applied to histogram-encoded scores. Our best-performing model, a trial-level RBF-kernel Support Vector Machine together with MLP-based aggregation, achieved strong accuracy on held-out participants (ROC-AUC: 0.87, PR-AUC: 0.57). These findings highlight the value of combining spatial and network information with non-linear modeling to improve functional mapping in presurgical evaluation.
【2】Spherical Brownian Bridge Diffusion Models for Conditional Cortical Thickness Forecasting
标题：用于条件皮质厚度预测的球形布朗桥扩散模型
链接：https://arxiv.org/abs/2509.08442
摘要：准确预测个性化的高分辨率皮质厚度（CTh）轨迹对于检测细微的皮质变化，提供对神经退行性过程的宝贵见解以及促进更早和更精确的干预策略至关重要。然而，CTh预测是一项具有挑战性的任务，由于复杂的非欧几里德几何的大脑皮层和需要整合多模态数据的特定主题的预测。为了解决这些问题，我们引入了球面布朗桥扩散模型（SBDM）。具体来说，我们提出了一个双向条件布朗桥扩散过程来预测CTh轨迹在顶点水平的注册皮质表面。我们的技术贡献包括一个新的去噪模型，条件球面U-网（CoS-UNet），它结合了球面卷积和密集交叉注意，无缝集成皮层表面和表格条件。与以前的方法相比，SBDM实现了显着降低的预测误差，正如我们的实验所证明的纵向数据集从ADNI和OASIS。此外，我们证明SBDM的能力，以产生个人的事实和反事实CTh轨迹，探索假设的情况下，皮层发育提供了一个新的框架。
摘要：Accurate forecasting of individualized, high-resolution cortical thickness (CTh) trajectories is essential for detecting subtle cortical changes, providing invaluable insights into neurodegenerative processes and facilitating earlier and more precise intervention strategies. However, CTh forecasting is a challenging task due to the intricate non-Euclidean geometry of the cerebral cortex and the need to integrate multi-modal data for subject-specific predictions. To address these challenges, we introduce the Spherical Brownian Bridge Diffusion Model (SBDM). Specifically, we propose a bidirectional conditional Brownian bridge diffusion process to forecast CTh trajectories at the vertex level of registered cortical surfaces. Our technical contribution includes a new denoising model, the conditional spherical U-Net (CoS-UNet), which combines spherical convolutions and dense cross-attention to integrate cortical surfaces and tabular conditions seamlessly. Compared to previous approaches, SBDM achieves significantly reduced prediction errors, as demonstrated by our experiments based on longitudinal datasets from the ADNI and OASIS. Additionally, we demonstrate SBDM's ability to generate individual factual and counterfactual CTh trajectories, offering a novel framework for exploring hypothetical scenarios of cortical development.
【3】Prediction Loss Guided Decision-Focused Learning
标题：预测损失引导的以决策为中心的学习
链接：https://arxiv.org/abs/2509.08359
摘要：不确定性下的决策通常分为两个阶段：预测未知参数，然后根据预测优化决策。传统的预测聚焦学习（PFL）将这两个阶段分开处理，而决策聚焦学习（DFL）通过端到端的方式直接优化决策质量来训练预测模型。然而，尽管使用精确或近似的梯度，vanilla DFL由于其平坦和尖锐的损失景观而经常遭受不稳定的收敛。相比之下，PFL产生更稳定的优化，但忽略了下游的决策质量。为了解决这个问题，我们提出了一种简单而有效的方法：使用预测损失梯度来扰动决策损失梯度以构建更新方向。我们的方法不需要额外的训练，可以与任何DFL求解器集成。利用S型衰减参数，通过预测损失梯度引导决策损失梯度来训练优化决策质量的预测模型。在较弱的假设条件下，给出了Pareto稳定点的理论收敛性保证.从经验上讲，我们在三个随机优化问题中展示了我们的方法，与其他基线相比，显示出有希望的结果。我们验证了我们的方法可以通过更稳定的训练实现更低的遗憾，即使在PFL或DFL挣扎的情况下。
摘要 ：Decision-making under uncertainty is often considered in two stages: predicting the unknown parameters, and then optimizing decisions based on predictions. While traditional prediction-focused learning (PFL) treats these two stages separately, decision-focused learning (DFL) trains the predictive model by directly optimizing the decision quality in an end-to-end manner. However, despite using exact or well-approximated gradients, vanilla DFL often suffers from unstable convergence due to its flat-and-sharp loss landscapes. In contrast, PFL yields more stable optimization, but overlooks the downstream decision quality. To address this, we propose a simple yet effective approach: perturbing the decision loss gradient using the prediction loss gradient to construct an update direction. Our method requires no additional training and can be integrated with any DFL solvers. Using the sigmoid-like decaying parameter, we let the prediction loss gradient guide the decision loss gradient to train a predictive model that optimizes decision quality. Also, we provide a theoretical convergence guarantee to Pareto stationary point under mild assumptions. Empirically, we demonstrate our method across three stochastic optimization problems, showing promising results compared to other baselines. We validate that our approach achieves lower regret with more stable training, even in situations where either PFL or DFL struggles.
【4】Network Contagion in Financial Labor Markets: Predicting Turnover in Hong Kong
标题：金融劳动力市场的网络传染：预测香港的流动性
链接：https://arxiv.org/abs/2509.08001
摘要：员工流动是金融市场的一个关键挑战，但人们对职业网络在塑造职业流动方面的作用知之甚少。我们使用香港证券及期货事务监察委员会（SFC）的公开登记册（2007-2024），构建了121，883名专业人士和4，979家公司的时间网络，以分析和预测员工离职。我们引入了一个基于图的功能传播框架，捕捉同行的影响力和组织的稳定性。我们的分析显示了一种传染效应：当超过30%的同行在六个月内离开时，专业人士离开的可能性增加了23%。将这些网络信号嵌入到机器学习模型中，可以将营业额预测提高30%。这些结果突出了时间网络效应在劳动力动态中的预测能力，并展示了基于网络的分析如何为监管监控、人才管理和系统性风险评估提供信息。
摘要：Employee turnover is a critical challenge in financial markets, yet little is known about the role of professional networks in shaping career moves. Using the Hong Kong Securities and Futures Commission (SFC) public register (2007-2024), we construct temporal networks of 121,883 professionals and 4,979 firms to analyze and predict employee departures. We introduce a graph-based feature propagation framework that captures peer influence and organizational stability. Our analysis shows a contagion effect: professionals are 23% more likely to leave when over 30% of their peers depart within six months. Embedding these network signals into machine learning models improves turnover prediction by 30% over baselines. These results highlight the predictive power of temporal network effects in workforce dynamics, and demonstrate how network-based analytics can inform regulatory monitoring, talent management, and systemic risk assessment.
【5】QCardEst/QCardCorr: Quantum Cardinality Estimation and Correction
标题：QCardEst/QCardCorr：量子基数估计和修正
链接：https://arxiv.org/abs/2509.08817
备注：7 pages
摘要：基数估计是数据库管理系统查询优化的重要组成部分。我们开发了一种量子基数估计（QCardEst）方法，使用量子机器学习和混合量子经典网络。我们定义了一个紧凑的编码，用于将SQL查询转换为量子状态，这只需要与查询中的表数量相等的量子位。这允许在当前硬件上用单个变分量子电路（VQC）处理完整查询。此外，我们比较了多个经典的后处理层，以将VQC的概率向量输出转换为基数值。我们引入了量子基数校正QCardCorr，它通过将输出与VQC生成的因子相乘来改进经典的基数估计，以提高基数估计。使用QCardCorr，我们对标准PostgreSQL优化器的改进为JOB-light的6.37倍和STATS的8.66倍。对于JOB-light，我们的表现甚至超过MSCN 3.47倍。
摘要：Cardinality estimation is an important part of query optimization in DBMS. We develop a Quantum Cardinality Estimation (QCardEst) approach using Quantum Machine Learning with a Hybrid Quantum-Classical Network. We define a compact encoding for turning SQL queries into a quantum state, which requires only qubits equal to the number of tables in the query. This allows the processing of a complete query with a single variational quantum circuit (VQC) on current hardware. In addition, we compare multiple classical post-processing layers to turn the probability vector output of VQC into a cardinality value. We introduce Quantum Cardinality Correction QCardCorr, which improves classical cardinality estimators by multiplying the output with a factor generated by a VQC to improve the cardinality estimation. With QCardCorr, we have an improvement over the standard PostgreSQL optimizer of 6.37 times for JOB-light and 8.66 times for STATS. For JOB-light we even outperform MSCN by a factor of 3.47.
【6】Forecasting Generative Amplification
标题：预测生成放大
链接：https://arxiv.org/abs/2509.08048
备注：23 pages, 15 figures
摘要：生成网络是提高LHC模拟速度和精度的完美工具。理解它们的统计精度很重要，特别是当生成的事件超过训练数据集的大小时。我们提出了两种互补的方法来估计放大因子没有大的holdout数据集。平均放大使用贝叶斯网络或集合来从给定相空间体积上的积分的精度估计放大。差异扩增使用假设检验来量化扩增而没有任何分辨率损失。应用于最先进的事件发生器，这两种方法表明，放大是可能的，在相空间的特定区域，但尚未跨越整个分布。
摘要：Generative networks are perfect tools to enhance the speed and precision of LHC simulations. It is important to understand their statistical precision, especially when generating events beyond the size of the training dataset. We present two complementary methods to estimate the amplification factor without large holdout datasets. Averaging amplification uses Bayesian networks or ensembling to estimate amplification from the precision of integrals over given phase-space volumes. Differential amplification uses hypothesis testing to quantify amplification without any resolution loss. Applied to state-of-the-art event generators, both methods indicate that amplification is possible in specific regions of phase space, but not yet across the entire distribution.
其他神经网络|深度学习|模型|建模(12篇)
【1】Fourier Learning Machines: Nonharmonic Fourier-Based Neural Networks for Scientific Machine Learning
标题：傅里叶学习机：用于科学机器学习的非调和傅里叶神经网络
链接：https://arxiv.org/abs/2509.08759
摘要：我们介绍了傅立叶学习机（FLM），神经网络（NN）的架构，旨在代表一个多维非谐波傅立叶级数。FLM使用具有余弦激活函数的简单前馈结构来学习序列的频率、振幅和相移作为可训练参数。这种设计允许该模型创建一个特定于问题的频谱基础，适用于周期性和非周期性函数。与以前的傅立叶启发的NN模型不同，FLM是第一个能够使用标准的多层感知器架构在多个维度上表示完整的、可分离的傅立叶基的架构。一对一的对应关系之间的傅立叶系数和振幅和相移的证明，允许之间的翻译一个完整的，可分离的基础形式和余弦相移。此外，我们评估了几个科学计算问题，包括基准偏微分方程（PDE）和一个家庭的最优控制问题（OCP）的FLM的性能。计算实验表明，FLM的性能是可比的，往往优于，建立的架构，如SIREN和香草前馈神经网络。
摘要 ：We introduce the Fourier Learning Machine (FLM), a neural network (NN) architecture designed to represent a multidimensional nonharmonic Fourier series. The FLM uses a simple feedforward structure with cosine activation functions to learn the frequencies, amplitudes, and phase shifts of the series as trainable parameters. This design allows the model to create a problem-specific spectral basis adaptable to both periodic and nonperiodic functions. Unlike previous Fourier-inspired NN models, the FLM is the first architecture able to represent a complete, separable Fourier basis in multiple dimensions using a standard Multilayer Perceptron-like architecture. A one-to-one correspondence between the Fourier coefficients and amplitudes and phase-shifts is demonstrated, allowing for the translation between a full, separable basis form and the cosine phase--shifted one. Additionally, we evaluate the performance of FLMs on several scientific computing problems, including benchmark Partial Differential Equations (PDEs) and a family of Optimal Control Problems (OCPs). Computational experiments show that the performance of FLMs is comparable, and often superior, to that of established architectures like SIREN and vanilla feedforward NNs.
【2】DEQuify your force field: More efficient simulations using deep equilibrium models
标题：解除你的磁场：使用深度平衡模型进行更有效的模拟
链接：https://arxiv.org/abs/2509.08734
备注：AI4MAT-ICLR-2025 Spotlight this https URL
摘要：与手动导出的力场相比，机器学习力场在实现更准确的分子动力学模拟方面显示出巨大的潜力。近年来的大部分进展都是通过利用有关物理系统的先验知识来推动的，特别是旋转，平移和反射下的对称性。在本文中，我们认为还有另一个重要的先验信息，因此fa，r还没有被探索：模拟分子系统必须是连续的，因此连续的状态非常相似。我们的贡献是表明，我们可以利用这些信息，通过重铸一个国家的最先进的同变基础模型作为一个深均衡模型。这使我们能够从以前的时间步中回收中间神经网络特征，使我们能够在MD 17，MD 22和OC 20 200 k数据集上将准确性和速度提高10 -20。训练也更节省内存，允许我们在更大的系统上训练更具表现力的模型。
摘要：Machine learning force fields show great promise in enabling more accurate molecular dynamics simulations compared to manually derived ones. Much of the progress in recent years was driven by exploiting prior knowledge about physical systems, in particular symmetries under rotation, translation, and reflections. In this paper, we argue that there is another important piece of prior information that, thus fa,r hasn't been explored: Simulating a molecular system is necessarily continuous, and successive states are therefore extremely similar. Our contribution is to show that we can exploit this information by recasting a state-of-the-art equivariant base model as a deep equilibrium model. This allows us to recycle intermediate neural network features from previous time steps, enabling us to improve both accuracy and speed by $10\%-20\%$ on the MD17, MD22, and OC20 200k datasets, compared to the non-DEQ base model. The training is also much more memory efficient, allowing us to train more expressive models on larger systems.
【3】Data-driven generative simulation of SDEs using diffusion models
标题：使用扩散模型对SDP进行数据驱动生成式模拟
链接：https://arxiv.org/abs/2509.08731
摘要：本文介绍了一种新的方法来生成未知的随机微分方程（SDEs）的样本路径使用扩散模型，一类生成AI模型通常用于图像和视频应用。与传统的Monte Carlo方法模拟的SDES，这需要明确的规格的漂移和扩散系数不同，我们的方法采用无模型，数据驱动的方法。给定一组有限的样本路径，我们利用条件扩散模型来生成新的，合成路径相同的样本路径。为了证明我们的方法的有效性，我们进行了模拟实验，比较我们的方法与其他基准，包括神经SDES。此外，在一项实证研究中，我们利用这些合成生成的样本路径来提高强化学习算法在连续时间均值-方差投资组合选择中的性能，暗示扩散模型在金融分析和决策中的应用前景。
摘要：This paper introduces a new approach to generating sample paths of unknown stochastic differential equations (SDEs) using diffusion models, a class of generative AI models commonly employed in image and video applications. Unlike the traditional Monte Carlo methods for simulating SDEs, which require explicit specifications of the drift and diffusion coefficients, our method takes a model-free, data-driven approach. Given a finite set of sample paths from an SDE, we utilize conditional diffusion models to generate new, synthetic paths of the same SDE. To demonstrate the effectiveness of our approach, we conduct a simulation experiment to compare our method with alternative benchmark ones including neural SDEs. Furthermore, in an empirical study we leverage these synthetically generated sample paths to enhance the performance of reinforcement learning algorithms for continuous-time mean-variance portfolio selection, hinting promising applications of diffusion models in financial analysis and decision-making.
【4】Compressing CNN models for resource-constrained systems by channel and layer pruning
标题：通过通道和层修剪压缩资源受限系统的CNN模型
链接：https://arxiv.org/abs/2509.08714
备注：16 pages, 4 figures, the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
摘要：卷积神经网络（CNN）在各个领域都取得了重大突破。然而，这些进步导致这些网络的复杂性和规模大幅增加。这在边缘设备上部署大型复杂网络时构成了挑战。因此，模型压缩已经成为一个旨在减少CNN的大小和复杂性的研究领域。模型压缩中的一个突出技术是模型修剪。本文将提出一种新的修剪技术，结合了通道和层修剪在所谓的“混合修剪框架”。受EfficientNet的启发，EfficientNet是一种著名的CNN架构，以从通道和层的角度扩展网络而闻名，这种混合方法应用了相同的原理，但相反，它通过修剪来缩小网络。对混合方法的实验表明，该模型的整体复杂性显着降低，与基线模型相比，准确性仅略有降低。在NVIDIA JETSON TX2嵌入式AI设备上部署精简模型时，这种复杂性的降低可转化为更低的延迟。
摘要：Convolutional Neural Networks (CNNs) have achieved significant breakthroughs in various fields. However, these advancements have led to a substantial increase in the complexity and size of these networks. This poses a challenge when deploying large and complex networks on edge devices. Consequently, model compression has emerged as a research field aimed at reducing the size and complexity of CNNs. One prominent technique in model compression is model pruning. This paper will present a new technique of pruning that combines both channel and layer pruning in what is called a "hybrid pruning framework". Inspired by EfficientNet, a renowned CNN architecture known for scaling up networks from both channel and layer perspectives, this hybrid approach applies the same principles but in reverse, where it scales down the network through pruning. Experiments on the hybrid approach demonstrated a notable decrease in the overall complexity of the model, with only a minimal reduction in accuracy compared to the baseline model. This complexity reduction translates into reduced latency when deploying the pruned models on an NVIDIA JETSON TX2 embedded AI device.
【5】Towards Interpretable Deep Neural Networks for Tabular Data
标题：面向表格数据的可解释深度神经网络
链接：https://arxiv.org/abs/2509.08617
摘要：表格数据是金融和医疗保健等领域许多应用程序的基础。尽管为表格数据量身定制的DNN实现了具有竞争力的预测性能，但它们是几乎没有可解释性的黑盒。我们介绍了XNNTab，这是一种神经架构，它使用稀疏自动编码器（SAE）来学习用于预测的潜在空间内的单语义特征字典。使用自动化的方法，我们分配人类可解释的语义这些功能。这使我们能够将预测表示为语义上有意义的成分的线性组合。经验评估表明，XNNTab的性能与最先进的黑盒神经模型和经典机器学习方法相当或超过它们，同时具有完全的可解释性。
摘要 ：Tabular data is the foundation of many applications in fields such as finance and healthcare. Although DNNs tailored for tabular data achieve competitive predictive performance, they are blackboxes with little interpretability. We introduce XNNTab, a neural architecture that uses a sparse autoencoder (SAE) to learn a dictionary of monosemantic features within the latent space used for prediction. Using an automated method, we assign human-interpretable semantics to these features. This allows us to represent predictions as linear combinations of semantically meaningful components. Empirical evaluations demonstrate that XNNTab attains performance on par with or exceeding that of state-of-the-art, black-box neural models and classical machine learning approaches while being fully interpretable.
【6】An Interpretable Deep Learning Model for General Insurance Pricing
标题：通用保险定价的可解释深度学习模型
链接：https://arxiv.org/abs/2509.08467
摘要：本文介绍了精算神经加法模型，这是一种用于一般保险定价的内在可解释的深度学习模型，可提供完全透明和可解释的结果，同时保留神经网络的强大预测能力。该模型为每个单独的协变量和成对交互项分配专用的神经网络（或子网络），以独立地学习其对建模输出的影响，同时实现各种架构约束，以允许保险应用中的基本可解释性（例如稀疏性）和实际要求（例如平滑性，单调性）。我们的模型的发展是建立在一个坚实的基础上，在保险的背景下，我们建立了一个具体的可解释性的定义，辅以严格的数学框架。使用合成和真实保险数据集，与传统的精算和最先进的机器学习方法在预测准确性方面进行了比较。结果表明，该模型在大多数情况下优于其他方法，同时在其内部逻辑中提供完全透明，强调了强大的可解释性和预测能力。
摘要：This paper introduces the Actuarial Neural Additive Model, an inherently interpretable deep learning model for general insurance pricing that offers fully transparent and interpretable results while retaining the strong predictive power of neural networks. This model assigns a dedicated neural network (or subnetwork) to each individual covariate and pairwise interaction term to independently learn its impact on the modeled output while implementing various architectural constraints to allow for essential interpretability (e.g. sparsity) and practical requirements (e.g. smoothness, monotonicity) in insurance applications. The development of our model is grounded in a solid foundation, where we establish a concrete definition of interpretability within the insurance context, complemented by a rigorous mathematical framework. Comparisons in terms of prediction accuracy are made with traditional actuarial and state-of-the-art machine learning methods using both synthetic and real insurance datasets. The results show that the proposed model outperforms other methods in most cases while offering complete transparency in its internal logic, underscoring the strong interpretability and predictive capability.
【7】Machine Learning with Multitype Protected Attributes: Intersectional Fairness through Regularisation
标题：具有多类型保护属性的机器学习：通过正规化实现交叉公平
链接：https://arxiv.org/abs/2509.08163
摘要：确保受保护属性（如性别或种族）的公平待遇（公平性）是机器学习中的一个关键问题。大多数现有的文献集中在二进制分类，但实现公平的回归任务，如保险定价或招聘分数评估同样重要。此外，反歧视法也适用于连续属性，如年龄，许多现有的方法不适用。在实践中，多个受保护的属性可以同时存在;然而，以跨若干属性的公平性为目标的方法通常忽略所谓的“公平选区划分”，从而忽略交叉子组之间的差异（例如，非裔美国女性或西班牙裔男性）。在本文中，我们提出了一个距离协方差正则化框架，该框架减轻了模型预测和受保护属性之间的关联，符合人口统计学平价的公平性定义，并捕获线性和非线性依赖关系。为了增强多个受保护属性存在下的适用性，我们扩展了我们的框架，将两个基于距离协方差的多变量依赖度量：先前提出的联合距离协方差（JdCov）和我们新的级联距离协方差（CCdCov），有效地解决了涉及各种类型受保护属性的回归和分类任务中的公平性。我们讨论并说明了如何校准正则化强度，包括基于詹森-香农发散的方法，该方法量化了各组预测分布的差异。我们将我们的框架应用于COMPAS累犯数据集和大型汽车保险索赔数据集。
摘要：Ensuring equitable treatment (fairness) across protected attributes (such as gender or ethnicity) is a critical issue in machine learning. Most existing literature focuses on binary classification, but achieving fairness in regression tasks-such as insurance pricing or hiring score assessments-is equally important. Moreover, anti-discrimination laws also apply to continuous attributes, such as age, for which many existing methods are not applicable. In practice, multiple protected attributes can exist simultaneously; however, methods targeting fairness across several attributes often overlook so-called "fairness gerrymandering", thereby ignoring disparities among intersectional subgroups (e.g., African-American women or Hispanic men). In this paper, we propose a distance covariance regularisation framework that mitigates the association between model predictions and protected attributes, in line with the fairness definition of demographic parity, and that captures both linear and nonlinear dependencies. To enhance applicability in the presence of multiple protected attributes, we extend our framework by incorporating two multivariate dependence measures based on distance covariance: the previously proposed joint distance covariance (JdCov) and our novel concatenated distance covariance (CCdCov), which effectively address fairness gerrymandering in both regression and classification tasks involving protected attributes of various types. We discuss and illustrate how to calibrate regularisation strength, including a method based on Jensen-Shannon divergence, which quantifies dissimilarities in prediction distributions across groups. We apply our framework to the COMPAS recidivism dataset and a large motor insurance claims dataset.
【8】torchmil: A PyTorch-based library for deep Multiple Instance Learning
标题：Torchmil：一个基于PyTorch的库，用于深度多实例学习
链接：https://arxiv.org/abs/2509.08129
摘要：多实例学习（MIL）是弱监督学习的强大框架，在细粒度注释不可用时特别有用。尽管对深度MIL方法的兴趣越来越大，但该领域缺乏用于模型开发、评估和比较的标准化工具，这阻碍了可重复性和可访问性。为了解决这个问题，我们提出了torchmil，这是一个基于PyTorch构建的开源Python库。torchmil提供了一个统一的、模块化的、可扩展的框架，具有用于MIL模型的基本构建块、标准化的数据格式以及基准数据集和模型的精选集合。该图书馆包括全面的文档和教程，以支持从业人员和研究人员。torchmil旨在加速MIL的进展并降低新用户的进入门槛。可在https://torchmil.readthedocs.io上获得。
摘要：Multiple Instance Learning (MIL) is a powerful framework for weakly supervised learning, particularly useful when fine-grained annotations are unavailable. Despite growing interest in deep MIL methods, the field lacks standardized tools for model development, evaluation, and comparison, which hinders reproducibility and accessibility. To address this, we present torchmil, an open-source Python library built on PyTorch. torchmil offers a unified, modular, and extensible framework, featuring basic building blocks for MIL models, a standardized data format, and a curated collection of benchmark datasets and models. The library includes comprehensive documentation and tutorials to support both practitioners and researchers. torchmil aims to accelerate progress in MIL and lower the entry barrier for new users. Available at https://torchmil.readthedocs.io.
【9】ToDMA: Large Model-Driven Token-Domain Multiple Access for Semantic Communications
标题：ToDMA：用于语义通信的大型模型驱动的令牌域多路访问
链接：https://arxiv.org/abs/2505.10946
备注：Submitted to IEEE journals
摘要 ：令牌通信（TokCom）是一种新兴的生成语义通信概念，其通过使用基于上下文和多模态大语言模型（MLLM）的令牌处理来降低传输速率，其中令牌充当跨模态的通用语义单元。在本文中，我们提出了一种语义多址接入方案在令牌域，称为令牌域多址接入（ToDMA），其中大量的设备共享一个令牌码本和调制码本的源和信道编码，分别。具体地，每个发射机首先将其源信号令牌化，并将每个令牌调制为码字。在接收端，首先采用压缩感知从叠加信号中检测出有效令牌和相应的信道状态信息（CSI）。然后，通过在多个时隙上聚类与令牌相关联的CSI来重构源令牌序列。在令牌冲突的情况下，一些活动令牌不能被分配，并且重构的令牌序列中的一些位置是空的。我们建议使用预先训练的MLLM来利用上下文，预测掩码令牌，从而减轻令牌冲突。仿真结果表明，所提出的ToDMA框架的文本和图像传输任务的有效性，实现显着较低的延迟相比，上下文不知道的正交通信方案，同时还提供卓越的失真和感知质量相比，国家的最先进的上下文不知道的非正交通信方法。
摘要：Token communications (TokCom) is an emerging generative semantic communication concept that reduces transmission rates by using context and multimodal large language model (MLLM)-based token processing, with tokens serving as universal semantic units across modalities. In this paper, we propose a semantic multiple access scheme in the token domain, referred to as token domain multiple access (ToDMA), where a large number of devices share a token codebook and a modulation codebook for source and channel coding, respectively. Specifically, each transmitter first tokenizes its source signal and modulate each token to a codeword. At the receiver, compressed sensing is employed first to detect active tokens and the corresponding channel state information (CSI) from the superposed signals. Then, the source token sequences are reconstructed by clustering the token-associated CSI across multiple time slots. In case of token collisions, some active tokens cannot be assigned and some positions in the reconstructed token sequences are empty. We propose to use pre-trained MLLMs to leverage the context, predict masked tokens, and thus mitigate token collisions. Simulation results demonstrate the effectiveness of the proposed ToDMA framework for both text and image transmission tasks, achieving significantly lower latency compared to context-unaware orthogonal communication schemes, while also delivering superior distortion and perceptual quality compared to state-of-the-art context-unaware non-orthogonal communication methods.
【10】Robust Belief-State Policy Learning for Quantum Network Routing Under Decoherence and Time-Varying Conditions
标题：去相关和时变条件下量子网络路由的鲁棒信念-状态策略学习
链接：https://arxiv.org/abs/2509.08654
摘要：本文提出了一种基于特征的量子网络路由部分可观测马尔可夫决策过程（POMDP）框架，将置信状态规划与图神经网络（GNNs）相结合，以解决动态量子系统中的部分可观测性，退相干和可扩展性挑战。我们的方法将复杂的量子网络动力学（包括纠缠退化和时变信道噪声）编码到低维特征空间中，从而实现有效的信念更新和可扩展的策略学习。我们的框架的核心是一个混合GNN-POMDP架构，处理纠缠链路的图形结构表示来学习路由策略，再加上一个噪声自适应机制，将POMDP信念更新与GNN输出融合，以实现稳健的决策。我们提供了一个理论分析，建立保证信念收敛，政策改进，和鲁棒性噪声。在多达100个节点的模拟量子网络上进行的实验表明，与最先进的基线相比，路由保真度和纠缠传输率有了显着改善，特别是在高退相干和非平稳条件下。
摘要：This paper presents a feature-based Partially Observable Markov Decision Process (POMDP) framework for quantum network routing, combining belief-state planning with Graph Neural Networks (GNNs) to address partial observability, decoherence, and scalability challenges in dynamic quantum systems. Our approach encodes complex quantum network dynamics, including entanglement degradation and time-varying channel noise, into a low-dimensional feature space, enabling efficient belief updates and scalable policy learning. The core of our framework is a hybrid GNN-POMDP architecture that processes graph-structured representations of entangled links to learn routing policies, coupled with a noise-adaptive mechanism that fuses POMDP belief updates with GNN outputs for robust decision making. We provide a theoretical analysis establishing guarantees for belief convergence, policy improvement, and robustness to noise. Experiments on simulated quantum networks with up to 100 nodes demonstrate significant improvements in routing fidelity and entanglement delivery rates compared to state-of-the-art baselines, particularly under high decoherence and nonstationary conditions.
【11】Facet: highly efficient E(3)-equivariant networks for interatomic potentials
标题：面：原子间势的高效E（3）-等变网络
链接：https://arxiv.org/abs/2509.08418
摘要：计算材料的发现受到第一性原理计算的高成本的限制。从晶体结构预测能量的机器学习（ML）潜力很有前途，但现有方法面临计算瓶颈。可控图神经网络（GNN）用球谐函数编码几何形状，尊重原子对称性-排列，旋转和平移-用于物理上现实的预测。然而，保持等方差是困难的：激活函数必须修改，每一层必须处理不同谐波阶数的多种数据类型。我们提出了Facet，这是一种高效ML潜力的GNN架构，通过对可操纵GNN的系统分析而开发。我们的创新包括用样条取代昂贵的多层感知器（MLP），以实现原子间距离，从而在降低计算和内存需求的同时匹配性能。我们还引入了一个通用的等变层，它通过球面网格投影混合节点信息，然后是标准的MLP-比张量积更快，比线性或门层更有表现力。在MPTrj数据集上，Facet匹配的主要模型参数少得多，训练计算量不到10%。在晶体弛豫任务中，它的运行速度是MACE模型的两倍。我们进一步表明，SevenNet-0的参数可以减少25%以上，而不会损失准确性。这些技术使ML潜力的大规模基础模型的训练速度提高了10倍以上，有可能重塑计算材料的发现。
摘要：Computational materials discovery is limited by the high cost of first-principles calculations. Machine learning (ML) potentials that predict energies from crystal structures are promising, but existing methods face computational bottlenecks. Steerable graph neural networks (GNNs) encode geometry with spherical harmonics, respecting atomic symmetries -- permutation, rotation, and translation -- for physically realistic predictions. Yet maintaining equivariance is difficult: activation functions must be modified, and each layer must handle multiple data types for different harmonic orders. We present Facet, a GNN architecture for efficient ML potentials, developed through systematic analysis of steerable GNNs. Our innovations include replacing expensive multi-layer perceptrons (MLPs) for interatomic distances with splines, which match performance while cutting computational and memory demands. We also introduce a general-purpose equivariant layer that mixes node information via spherical grid projection followed by standard MLPs -- faster than tensor products and more expressive than linear or gate layers. On the MPTrj dataset, Facet matches leading models with far fewer parameters and under 10% of their training compute. On a crystal relaxation task, it runs twice as fast as MACE models. We further show SevenNet-0's parameters can be reduced by over 25% with no accuracy loss. These techniques enable more than 10x faster training of large-scale foundation models for ML potentials, potentially reshaping computational materials discovery.
【12】Generative Quasi-Continuum Modeling of Confined Fluids at the Nanoscale
标题：纳米尺度约束流体的生成准连续体建模
链接：https://arxiv.org/abs/2509.08223
摘要：我们提出了一个数据高效，多尺度的框架，用于预测在纳米级的封闭流体的密度分布。虽然精确的密度估计需要非常长的时间尺度，这是从头算分子动力学（AIMD）模拟无法实现的，但机器学习分子动力学（MLMD）提供了一种可扩展的替代方案，能够以降低的计算成本生成从头算精度的力预测。然而，尽管它们的效率，MLMD模拟仍然受到飞秒时间步长的限制，这限制了它们用于计算精确密度估计所需的长时间平均值的实用性。为了解决这一问题，我们提出了一种基于条件去噪扩散概率模型（DDPM）的准连续方法，该方法以从有限AIMD数据集中提取的噪声力为条件，预测沿限制方向的力分布的长期行为。预测的光滑力，然后连接到连续介质理论通过能斯特-普朗克方程，以揭示潜在的密度行为。我们测试了两个石墨烯纳米级狭缝之间的水限制的框架，并证明了训练域之外的通道宽度的密度分布可以从头计算的准确性恢复。与AIMD和MLMD仿真相比，我们的方法在运行时实现了数量级的加速，并且需要的训练数据比以前的作品少得多。
摘要 ：We present a data-efficient, multiscale framework for predicting the density profiles of confined fluids at the nanoscale. While accurate density estimates require prohibitively long timescales that are inaccessible by ab initio molecular dynamics (AIMD) simulations, machine-learned molecular dynamics (MLMD) offers a scalable alternative, enabling the generation of force predictions at ab initio accuracy with reduced computational cost. However, despite their efficiency, MLMD simulations remain constrained by femtosecond timesteps, which limit their practicality for computing long-time averages needed for accurate density estimation. To address this, we propose a conditional denoising diffusion probabilistic model (DDPM) based quasi-continuum approach that predicts the long-time behavior of force profiles along the confinement direction, conditioned on noisy forces extracted from a limited AIMD dataset. The predicted smooth forces are then linked to continuum theory via the Nernst-Planck equation to reveal the underlying density behavior. We test the framework on water confined between two graphene nanoscale slits and demonstrate that density profiles for channel widths outside of the training domain can be recovered with ab initio accuracy. Compared to AIMD and MLMD simulations, our method achieves orders-of-magnitude speed-up in runtime and requires significantly less training data than prior works.
其他(27篇)
【1】A Survey of TinyML Applications in Beekeeping for Hive Monitoring and Management
标题：TinyML在蜂巢监测和管理养蜂中的应用调查
链接：https://arxiv.org/abs/2509.08822
备注：30 pages, 8 figures, 3 tables. Survey of TinyML and IoT applications in beekeeping (datasets, benchmarking, deployment). Submitted to ACM Computing Surveys (under review)
摘要：蜂群对全球粮食安全和生态系统稳定至关重要，但它们面临着来自害虫、疾病和环境压力的不断升级的威胁。传统的蜂箱检查是劳动密集型和破坏性的，而基于云的监控解决方案对于远程或资源有限的养蜂场仍然不切实际。物联网（IoT）和微型机器学习（TinyML）的最新进展可以直接在边缘设备上进行低功耗实时监控，提供可扩展的非侵入性替代方案。该调查综合了TinyML和养蜂业交叉点的当前创新，围绕四个关键功能领域组织：监测蜂箱条件，识别蜜蜂行为，检测害虫和疾病以及预测蜂群事件。我们进一步研究支持资源，包括公开可用的数据集，轻量级模型架构优化嵌入式部署，和基准测试策略量身定制的领域的限制。突出了数据稀缺、泛化挑战和离网环境中的部署障碍等关键限制，以及超高效推理管道、自适应边缘学习和数据集标准化方面的新兴机会。通过整合研究和工程实践，这项工作为可扩展的、人工智能驱动的和生态信息化的监测系统提供了基础，以支持可持续的传粉者管理。
摘要：Honey bee colonies are essential for global food security and ecosystem stability, yet they face escalating threats from pests, diseases, and environmental stressors. Traditional hive inspections are labor-intensive and disruptive, while cloud-based monitoring solutions remain impractical for remote or resource-limited apiaries. Recent advances in Internet of Things (IoT) and Tiny Machine Learning (TinyML) enable low-power, real-time monitoring directly on edge devices, offering scalable and non-invasive alternatives. This survey synthesizes current innovations at the intersection of TinyML and apiculture, organized around four key functional areas: monitoring hive conditions, recognizing bee behaviors, detecting pests and diseases, and forecasting swarming events. We further examine supporting resources, including publicly available datasets, lightweight model architectures optimized for embedded deployment, and benchmarking strategies tailored to field constraints. Critical limitations such as data scarcity, generalization challenges, and deployment barriers in off-grid environments are highlighted, alongside emerging opportunities in ultra-efficient inference pipelines, adaptive edge learning, and dataset standardization. By consolidating research and engineering practices, this work provides a foundation for scalable, AI-driven, and ecologically informed monitoring systems to support sustainable pollinator management.
【2】Using AI to Optimize Patient Transfer and Resource Utilization During Mass-Casualty Incidents: A Simulation Platform
标题：使用人工智能优化大规模伤亡事件期间的患者转移和资源利用：模拟平台
链接：https://arxiv.org/abs/2509.08756
摘要：大规模伤亡事件（MCI）使医疗系统不堪重负，需要在极端压力下做出快速、准确的患者-医院分配决策。在这里，我们开发并验证了一种基于深度强化学习的决策支持AI代理，通过平衡患者的紧急程度、专业护理要求、医院容量和运输物流，优化模拟MCI期间的患者转移决策。为了集成这个AI代理，我们开发了Master，这是一个用于MCI管理模拟的Web访问命令仪表板。通过一项有30名参与者（6名创伤专家和24名非专家）的对照用户研究，我们在大多伦多地区20名和60名患者的MCI场景中评估了与AI代理的三种交互方法（仅人类，人类-AI协作和仅AI）。结果表明，增加人工智能的参与可以显着提高决策质量和一致性。AI代理优于创伤外科医生（p < 0.001），并使非专家能够在辅助时达到专家水平的性能，与他们明显较差的无辅助性能形成鲜明对比（p < 0.001）。这些发现为我们的人工智能驱动的决策支持建立了潜力，以加强MCI准备培训和现实世界的应急响应管理。
摘要：Mass casualty incidents (MCIs) overwhelm healthcare systems and demand rapid, accurate patient-hospital allocation decisions under extreme pressure. Here, we developed and validated a deep reinforcement learning-based decision-support AI agent to optimize patient transfer decisions during simulated MCIs by balancing patient acuity levels, specialized care requirements, hospital capacities, and transport logistics. To integrate this AI agent, we developed MasTER, a web-accessible command dashboard for MCI management simulations. Through a controlled user study with 30 participants (6 trauma experts and 24 non-experts), we evaluated three interaction approaches with the AI agent (human-only, human-AI collaboration, and AI-only) across 20- and 60-patient MCI scenarios in the Greater Toronto Area. Results demonstrate that increasing AI involvement significantly improves decision quality and consistency. The AI agent outperforms trauma surgeons (p < 0.001) and enables non-experts to achieve expert-level performance when assisted, contrasting sharply with their significantly inferior unassisted performance (p < 0.001). These findings establish the potential for our AI-driven decision support to enhance both MCI preparedness training and real-world emergency response management.
【3】Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
标题：分享就是关怀：高效的LM后训练与集体RL经验分享
链接：https://arxiv.org/abs/2509.08721
备注：14 pages, 6 figures
摘要：具有强化学习（RL）的后训练语言模型（LM）可以在没有监督微调的情况下增强其复杂的推理能力，正如DeepSeek-R1-Zero所证明的那样。然而，有效地将RL用于LM需要显著的并行化来扩展推理，这引入了重要的技术挑战（例如延迟，内存和可靠性）以及不断增长的财务成本。我们提出了Swarm sAmpling Policy Optimization（SAPO），一种完全分散和异步的RL后训练算法。SAPO是为异构计算节点的分散网络而设计的，其中每个节点管理自己的策略模型，同时与网络中的其他节点“共享”部署;不需要对延迟，模型同质性或硬件进行明确的假设，如果需要，节点可以在筒仓中运行。因此，该算法避免了扩展RL后训练的常见瓶颈，同时还允许（甚至鼓励）新的可能性。通过在整个网络中对“共享”的展开进行采样，它使“啊哈时刻”能够传播，从而引导学习过程。在本文中，我们表明，SAPO实现了累积奖励收益高达94%的控制实验。我们还分享了在网络上进行测试的见解，该网络有数千个节点，由Gensyn社区成员在开源演示期间在不同的硬件和模型上运行该算法。
摘要 ：Post-training language models (LMs) with reinforcement learning (RL) can enhance their complex reasoning capabilities without supervised fine-tuning, as demonstrated by DeepSeek-R1-Zero. However, effectively utilizing RL for LMs requires significant parallelization to scale-up inference, which introduces non-trivial technical challenges (e.g. latency, memory, and reliability) alongside ever-growing financial costs. We present Swarm sAmpling Policy Optimization (SAPO), a fully decentralized and asynchronous RL post-training algorithm. SAPO is designed for decentralized networks of heterogenous compute nodes, where each node manages its own policy model(s) while "sharing" rollouts with others in the network; no explicit assumptions about latency, model homogeneity, or hardware are required and nodes can operate in silo if desired. As a result, the algorithm avoids common bottlenecks in scaling RL post-training while also allowing (and even encouraging) new possibilities. By sampling rollouts "shared" across the network, it enables "Aha moments" to propagate, thereby bootstrapping the learning process. In this paper we show SAPO achieved cumulative reward gains of up to 94% in controlled experiments. We also share insights from tests on a network with thousands of nodes contributed by Gensyn community members running the algorithm on diverse hardware and models during an open-source demo.
【4】TANGO: Traversability-Aware Navigation with Local Metric Control for Topological Goals
标题：TANGO：具有局部度量控制的可穿越性导航以实现布局目标
链接：https://arxiv.org/abs/2509.08699
备注：9 pages, 5 figures, ICRA 2025
摘要：机器人中的视觉导航传统上依赖于全局一致的3D地图或学习的控制器，这可能是计算昂贵的，并且难以在不同的环境中推广。在这项工作中，我们提出了一种新的RGB，对象级拓扑导航管道，使zero-shot，长视野的机器人导航，而不需要3D地图或预先训练的控制器。我们的方法将全局拓扑路径规划与局部度量轨迹控制相结合，使机器人能够在避开障碍物的同时导航到对象级子目标。我们解决了以前的方法的关键限制，通过使用单眼深度和遍历性估计连续预测局部轨迹，并结合自动切换机制，必要时回落到基线控制器。该系统使用基础模型运行，确保开放集的适用性，而无需特定于域的微调。我们证明了我们的方法在模拟环境和现实世界的测试中的有效性，突出其鲁棒性和可部署性。我们的方法优于现有的最先进的方法，提供了一个更适应和有效的解决方案，在开放的环境中的视觉导航。源代码是公开的：https://github.com/podgorki/TANGO。
摘要：Visual navigation in robotics traditionally relies on globally-consistent 3D maps or learned controllers, which can be computationally expensive and difficult to generalize across diverse environments. In this work, we present a novel RGB-only, object-level topometric navigation pipeline that enables zero-shot, long-horizon robot navigation without requiring 3D maps or pre-trained controllers. Our approach integrates global topological path planning with local metric trajectory control, allowing the robot to navigate towards object-level sub-goals while avoiding obstacles. We address key limitations of previous methods by continuously predicting local trajectory using monocular depth and traversability estimation, and incorporating an auto-switching mechanism that falls back to a baseline controller when necessary. The system operates using foundational models, ensuring open-set applicability without the need for domain-specific fine-tuning. We demonstrate the effectiveness of our method in both simulated environments and real-world tests, highlighting its robustness and deployability. Our approach outperforms existing state-of-the-art methods, offering a more adaptable and effective solution for visual navigation in open-set environments. The source code is made publicly available: https://github.com/podgorki/TANGO.
【5】Reshaping the Forward-Forward Algorithm with a Similarity-Based Objective
标题：以基于相似性的目标重塑前向-前向算法
链接：https://arxiv.org/abs/2509.08697
备注：6 pages
摘要：反向传播算法是人工神经网络成功的关键算法，但它也存在着生物学上不合理的反向锁定和全局错误传播等严重缺陷。为了规避这些限制，提出了Forward-Forward算法，作为一种生物学上更合理的方法，用额外的前向传递代替后向传递。尽管有这个优点，Forward-Forward算法在准确性上明显落后于反向传播，并且由于需要多次向前传递，其最佳形式表现出较低的推理效率。在这项工作中，Forward-Forward算法通过与相似性学习框架的集成进行了重塑，消除了推理过程中多次向前传递的需要。该算法被命名为基于相似性的元组丢失统一的前向-前向算法（FAUST）。对MNIST、Fashion-MNIST和CIFAR-10数据集的实证评估表明，FAUST大大提高了准确性，缩小了与反向传播的差距。在CIFAR-10上，FAUST采用简单的多层感知器结构，达到了56.22%的准确率，接近反向传播基准的57.63%的准确率。
摘要：Backpropagation is the pivotal algorithm underpinning the success of artificial neural networks, yet it has critical limitations such as biologically implausible backward locking and global error propagation. To circumvent these constraints, the Forward-Forward algorithm was proposed as a more biologically plausible method that replaces the backward pass with an additional forward pass. Despite this advantage, the Forward-Forward algorithm significantly trails backpropagation in accuracy, and its optimal form exhibits low inference efficiency due to multiple forward passes required. In this work, the Forward-Forward algorithm is reshaped through its integration with similarity learning frameworks, eliminating the need for multiple forward passes during inference. This proposed algorithm is named Forward-Forward Algorithm Unified with Similarity-based Tuplet loss (FAUST). Empirical evaluations on MNIST, Fashion-MNIST, and CIFAR-10 datasets indicate that FAUST substantially improves accuracy, narrowing the gap with backpropagation. On CIFAR-10, FAUST achieves 56.22\% accuracy with a simple multi-layer perceptron architecture, approaching the backpropagation benchmark of 57.63\% accuracy.
【6】Signal Fidelity Index-Aware Calibration for Dementia Predictions Across Heterogeneous Real-World Data
标题：跨异类现实世界数据的痴呆症预测的信号保真度指数感知校准
链接：https://arxiv.org/abs/2509.08679
摘要：\textbf{背景：}在电子健康记录（EHR）上训练的机器学习模型通常会由于分布转移而在医疗保健系统中降级。一个基本但未充分研究的因素是诊断信号衰减：诊断质量的变化和机构间的一致性，这会影响用于训练和预测的代码的可靠性。 \textbf{目的：}开发一种信号保真度指数（SFI），量化痴呆患者水平的诊断数据质量，并测试SFI感知校准，以提高无结果标签的异构数据集的模型性能。 \textbf{方法：}我们建立了一个模拟框架，生成2，500个合成数据集，每个数据集包含1，000名患者和基于痴呆风险因素的现实人口统计学，遭遇和编码模式。SFI来自六个可解释的组成部分：诊断特异性，时间一致性，熵，上下文一致性，药物对齐和轨迹稳定性。SFI感知校准应用了乘法调整，在50个模拟批次中进行了优化。 在最佳参数（$\alpha$ = 2.0）下，SFI感知校准显著改善了所有指标（p $
摘要：\textbf{Background:} Machine learning models trained on electronic health records (EHRs) often degrade across healthcare systems due to distributional shift. A fundamental but underexplored factor is diagnostic signal decay: variability in diagnostic quality and consistency across institutions, which affects the reliability of codes used for training and prediction. \textbf{Objective:} To develop a Signal Fidelity Index (SFI) quantifying diagnostic data quality at the patient level in dementia, and to test SFI-aware calibration for improving model performance across heterogeneous datasets without outcome labels. \textbf{Methods:} We built a simulation framework generating 2,500 synthetic datasets, each with 1,000 patients and realistic demographics, encounters, and coding patterns based on dementia risk factors. The SFI was derived from six interpretable components: diagnostic specificity, temporal consistency, entropy, contextual concordance, medication alignment, and trajectory stability. SFI-aware calibration applied a multiplicative adjustment, optimized across 50 simulation batches. \textbf{Results:} At the optimal parameter ($\alpha$ = 2.0), SFI-aware calibration significantly improved all metrics (p $
【7】Generative Data Refinement: Just Ask for Better Data
标题：生成式数据细化：只需要求更好的数据
链接：https://arxiv.org/abs/2509.08653
摘要 ：对于固定的参数大小，大型模型的能力主要取决于其训练数据的质量和数量。因此，训练数据集现在的增长速度快于新数据在网络上被索引的速度，导致预计未来十年数据耗尽。更多的数据以用户生成的内容的形式存在，这些内容没有公开索引，但合并这些数据会带来相当大的风险，例如泄露私人信息和其他不受欢迎的内容。我们引入了一个框架，生成数据细化（GDR），用于使用预训练的生成模型将具有不期望内容的数据集转换为更适合训练的细化数据集。我们的实验表明，GDR在数据集匿名化方面的性能优于行业级解决方案，并且能够直接对高度不安全的数据集进行解毒。此外，我们表明，通过生成以真实数据集中的每个示例为条件的合成数据，GDR的精炼输出自然匹配网络规模数据集的多样性，从而避免了通过模型提示生成多样化合成数据的挑战性任务。GDR的简单性和有效性使其成为扩展前沿模型训练数据总量的强大工具。
摘要：For a fixed parameter size, the capabilities of large models are primarily determined by the quality and quantity of its training data. Consequently, training datasets now grow faster than the rate at which new data is indexed on the web, leading to projected data exhaustion over the next decade. Much more data exists as user-generated content that is not publicly indexed, but incorporating such data comes with considerable risks, such as leaking private information and other undesirable content. We introduce a framework, Generative Data Refinement (GDR), for using pretrained generative models to transform a dataset with undesirable content into a refined dataset that is more suitable for training. Our experiments show that GDR can outperform industry-grade solutions for dataset anonymization, as well as enable direct detoxification of highly unsafe datasets. Moreover, we show that by generating synthetic data that is conditioned on each example in the real dataset, GDR's refined outputs naturally match the diversity of web scale datasets, and thereby avoid the often challenging task of generating diverse synthetic data via model prompting. The simplicity and effectiveness of GDR make it a powerful tool for scaling up the total stock of training data for frontier models.
【8】Variational Rank Reduction Autoencoders for Generative
标题：生成式的变分等级缩减自动编码器
链接：https://arxiv.org/abs/2509.08515
摘要：复杂几何形状的生成式热设计是许多工程领域的基础，但它面临着两个主要挑战：高保真仿真的高计算成本和传统生成模型的局限性。自编码器（AE）和变分自编码器（VAE）等方法通常会产生具有不连续性的非结构化潜在空间，这限制了它们探索设计和生成物理上一致的解决方案的能力。 为了解决这些限制，我们提出了一个混合框架，将变分降秩自编码器（VRRAE）与深度运营商网络（DeepONets）相结合。VRRAE在潜在空间内引入了截断的SVD，从而产生了连续的、可解释的和结构良好的表示，从而减轻了后崩溃并改善了几何重建。然后，DeepONet在其分支网络中利用这种紧凑的潜在编码，以及主干网络中的空间坐标，有效准确地预测温度梯度。 这种混合方法不仅提高了生成的几何图形的质量和梯度预测的准确性，而且与传统的数值求解器相比，在推理效率方面也具有很大的优势。总的来说，该研究强调了结构化潜在表示对操作员学习的重要性，并强调了在热设计和更广泛的工程应用中结合生成模型和操作员网络的潜力。
摘要：Generative thermal design for complex geometries is fundamental in many areas of engineering, yet it faces two main challenges: the high computational cost of high-fidelity simulations and the limitations of conventional generative models. Approaches such as autoencoders (AEs) and variational autoencoders (VAEs) often produce unstructured latent spaces with discontinuities, which restricts their capacity to explore designs and generate physically consistent solutions. To address these limitations, we propose a hybrid framework that combines Variational Rank-Reduction Autoencoders (VRRAEs) with Deep Operator Networks (DeepONets). The VRRAE introduces a truncated SVD within the latent space, leading to continuous, interpretable, and well-structured representations that mitigate posterior collapse and improve geometric reconstruction. The DeepONet then exploits this compact latent encoding in its branch network, together with spatial coordinates in the trunk network, to predict temperature gradients efficiently and accurately. This hybrid approach not only enhances the quality of generated geometries and the accuracy of gradient prediction, but also provides a substantial advantage in inference efficiency compared to traditional numerical solvers. Overall, the study underscores the importance of structured latent representations for operator learning and highlights the potential of combining generative models and operator networks in thermal design and broader engineering applications.
【9】HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants
标题：HumanJournalcyBench：人工智能助理人力机构支持的可扩展评估
链接：https://arxiv.org/abs/2509.08494
摘要：随着人类将更多的任务和决策委托给人工智能（AI），我们有可能失去对个人和集体未来的控制。相对简单的算法系统已经引导了人类的决策，例如社交媒体馈送算法，它会导致人们无意中和心不在焉地滚动浏览优化的内容。在本文中，我们通过将代理的哲学和科学理论与人工智能辅助评估方法相结合来发展人类代理的想法：使用大型语言模型（LLM）来模拟和验证用户查询并评估AI响应。我们开发了HumanarcityBench（HAB），这是一个可扩展和自适应的基准测试，基于典型的AI用例，具有六个人类代理维度。HAB衡量人工智能助理或代理提出澄清问题、避免价值操纵、纠正错误信息、推迟重要决策、鼓励学习和保持社交边界的倾向。我们发现低到中等的代理支持当代法学硕士为基础的助理和系统开发人员和尺寸的实质性变化。例如，虽然人择法学硕士最支持人类机构的整体，他们是最不支持的法学硕士在避免价值操纵方面。机构支持似乎并不总是源于法学硕士能力的提高或遵守指示的行为（例如，RLHF），我们鼓励转向更强大的安全和对齐目标。
摘要：As humans delegate more tasks and decisions to artificial intelligence (AI), we risk losing control of our individual and collective futures. Relatively simple algorithmic systems already steer human decision-making, such as social media feed algorithms that lead people to unintentionally and absent-mindedly scroll through engagement-optimized content. In this paper, we develop the idea of human agency by integrating philosophical and scientific theories of agency with AI-assisted evaluation methods: using large language models (LLMs) to simulate and validate user queries and to evaluate AI responses. We develop HumanAgencyBench (HAB), a scalable and adaptive benchmark with six dimensions of human agency based on typical AI use cases. HAB measures the tendency of an AI assistant or agent to Ask Clarifying Questions, Avoid Value Manipulation, Correct Misinformation, Defer Important Decisions, Encourage Learning, and Maintain Social Boundaries. We find low-to-moderate agency support in contemporary LLM-based assistants and substantial variation across system developers and dimensions. For example, while Anthropic LLMs most support human agency overall, they are the least supportive LLMs in terms of Avoid Value Manipulation. Agency support does not appear to consistently result from increasing LLM capabilities or instruction-following behavior (e.g., RLHF), and we encourage a shift towards more robust safety and alignment targets.
【10】SHAining on Process Mining: Explaining Event Log Characteristics Impact on Algorithms
标题：SHAining on Process Mining：解释事件日志特征对算法的影响
链接：https://arxiv.org/abs/2509.08482
摘要：流程挖掘的目的是从事件日志中提取和分析洞察力，然而算法度量结果根据结构化事件日志特征而变化很大。现有的工作往往评估算法上的一组固定的真实世界的事件日志，但缺乏一个系统的分析，如何事件日志特性的影响算法单独。此外，由于事件日志是从过程中产生的，其中特征共同发生，我们专注于关联而不是因果效应，以评估重叠的个体特征对评估指标的影响有多强，而不假设孤立的因果效应，这是一个经常被先前工作忽略的因素。我们介绍SHAining，第一种量化不同事件日志特征对流程挖掘算法度量的边际贡献的方法。使用流程发现作为下游任务，我们分析了超过22，000个事件日志，涵盖了广泛的特征，以揭示哪些影响指标之间的算法（例如，适应性、精确性、复杂性）最多。此外，我们提供了新的见解如何事件日志特性的值与其贡献的影响，评估算法的鲁棒性。
摘要 ：Process mining aims to extract and analyze insights from event logs, yet algorithm metric results vary widely depending on structural event log characteristics. Existing work often evaluates algorithms on a fixed set of real-world event logs but lacks a systematic analysis of how event log characteristics impact algorithms individually. Moreover, since event logs are generated from processes, where characteristics co-occur, we focus on associational rather than causal effects to assess how strong the overlapping individual characteristic affects evaluation metrics without assuming isolated causal effects, a factor often neglected by prior work. We introduce SHAining, the first approach to quantify the marginal contribution of varying event log characteristics to process mining algorithms' metrics. Using process discovery as a downstream task, we analyze over 22,000 event logs covering a wide span of characteristics to uncover which affect algorithms across metrics (e.g., fitness, precision, complexity) the most. Furthermore, we offer novel insights about how the value of event log characteristics correlates with their contributed impact, assessing the algorithm's robustness.
【11】Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narratives
标题：联合调查员人工智能：大型人工智能的崛起，以实现更智能、更值得信赖的反洗钱合规叙述
链接：https://arxiv.org/abs/2509.08380
摘要：生成合规的可疑活动报告（SAR）仍然是反洗钱（AML）工作流程中的高成本、低可扩展性瓶颈。虽然大型语言模型（LLM）提供了有希望的流畅性，但它们存在事实幻觉，有限的犯罪类型对齐和可解释性差-在合规性关键领域中构成了不可接受的风险。本文介绍了Co-Investigator AI，这是一个经过优化的代理框架，可以比传统方法更快、更准确地生成可疑活动报告（SAR）。从自主代理架构的最新进展（如AI Co-Scientist）中汲取灵感，我们的方法集成了专门的代理，用于规划，犯罪类型检测，外部情报收集和合规性验证。该系统具有动态内存管理，用于敏感数据处理的AI隐私保护层，以及采用代理作为法官范式的实时验证代理，以确保持续的叙事质量保证。人类调查人员仍然牢牢地处于循环中，有权在将人工智能效率与领域专业知识相结合的协作工作流程中审查和完善草案。我们展示了Co-Investigator AI在一系列复杂金融犯罪场景中的多功能性，突出了其简化SAR起草，使叙述与监管期望保持一致，并使合规团队能够专注于高阶分析工作的能力。这种方法标志着合规报告新时代的开始--将人工智能代理的变革性优势带入监管流程的核心，并为可扩展、可靠和透明的SAR生成铺平道路。
摘要：Generating regulatorily compliant Suspicious Activity Report (SAR) remains a high-cost, low-scalability bottleneck in Anti-Money Laundering (AML) workflows. While large language models (LLMs) offer promising fluency, they suffer from factual hallucination, limited crime typology alignment, and poor explainability -- posing unacceptable risks in compliance-critical domains. This paper introduces Co-Investigator AI, an agentic framework optimized to produce Suspicious Activity Reports (SARs) significantly faster and with greater accuracy than traditional methods. Drawing inspiration from recent advances in autonomous agent architectures, such as the AI Co-Scientist, our approach integrates specialized agents for planning, crime type detection, external intelligence gathering, and compliance validation. The system features dynamic memory management, an AI-Privacy Guard layer for sensitive data handling, and a real-time validation agent employing the Agent-as-a-Judge paradigm to ensure continuous narrative quality assurance. Human investigators remain firmly in the loop, empowered to review and refine drafts in a collaborative workflow that blends AI efficiency with domain expertise. We demonstrate the versatility of Co-Investigator AI across a range of complex financial crime scenarios, highlighting its ability to streamline SAR drafting, align narratives with regulatory expectations, and enable compliance teams to focus on higher-order analytical work. This approach marks the beginning of a new era in compliance reporting -- bringing the transformative benefits of AI agents to the core of regulatory processes and paving the way for scalable, reliable, and transparent SAR generation.
【12】Retrieval-Augmented VLMs for Multimodal Melanoma Diagnosis
标题：用于多模式黑色素瘤诊断的检索增强VLM
链接：https://arxiv.org/abs/2509.08338
备注：Medical Image Computing and Computer-Assisted Intervention (MICCAI) ISIC Skin Image Analysis Workshop (MICCAI ISIC) 2025; 10 pages
摘要：恶性黑色素瘤的准确和早期诊断对于改善患者预后至关重要。虽然卷积神经网络（CNN）在皮肤镜图像分析中表现出了希望，但它们往往忽略了临床元数据，需要大量的预处理。视觉语言模型（VLM）提供了一种多模态的替代方案，但在一般领域数据上训练时，很难捕捉临床特异性。为了解决这个问题，我们提出了一个检索增强的VLM框架，将语义相似的病人的情况下，诊断提示。我们的方法无需微调即可实现明智的预测，并显着提高了传统基线的分类准确性和纠错能力。这些结果表明，检索增强提示提供了一个强大的战略，临床决策支持。
摘要：Accurate and early diagnosis of malignant melanoma is critical for improving patient outcomes. While convolutional neural networks (CNNs) have shown promise in dermoscopic image analysis, they often neglect clinical metadata and require extensive preprocessing. Vision-language models (VLMs) offer a multimodal alternative but struggle to capture clinical specificity when trained on general-domain data. To address this, we propose a retrieval-augmented VLM framework that incorporates semantically similar patient cases into the diagnostic prompt. Our method enables informed predictions without fine-tuning and significantly improves classification accuracy and error correction over conventional baselines. These results demonstrate that retrieval-augmented prompting provides a robust strategy for clinical decision support.
【13】The CRITICAL Records Integrated Standardization Pipeline (CRISP): End-to-End Processing of Large-scale Multi-institutional OMOP CDM Data
标题：CRITIRAL Records集成标准化管道（CRISP）：大规模多机构OMOP CDM数据的端到端处理
链接：https://arxiv.org/abs/2509.08247
备注：15 pages, 9 figures
摘要：虽然MIMIC和eICU等现有重症监护EHR数据集已经在临床人工智能研究方面取得了重大进展，但CRITICAL数据集通过提供广泛的规模和多样性开辟了新的领域-包含来自四个地理位置不同的CTSA机构的371，365名患者的19.5亿条记录。CRITICAL的独特优势在于捕捉全方位的患者旅程，包括ICU前、ICU和ICU后在住院和门诊环境中的遭遇。这种多机构的纵向视角为开发可推广的预测模型和推进健康公平研究创造了变革性的机会。然而，这种多站点资源的丰富性在数据协调方面引入了相当大的复杂性，异构的收集实践和不同的词汇使用模式需要复杂的预处理方法。 我们提出CRISP来释放这一宝贵资源的全部潜力。CRISP通过以下方式将原始观察性医学成果伙伴关系通用数据模型数据系统地转换为ML就绪数据集：（1）具有全面审计跟踪的透明数据质量管理，（2）异构医学术语到统一的SNOMED-CT标准的跨词汇映射，具有去重和单元标准化，（3）具有并行优化的模块化架构，即使在标准计算硬件上也能够在$
摘要：While existing critical care EHR datasets such as MIMIC and eICU have enabled significant advances in clinical AI research, the CRITICAL dataset opens new frontiers by providing extensive scale and diversity -- containing 1.95 billion records from 371,365 patients across four geographically diverse CTSA institutions. CRITICAL's unique strength lies in capturing full-spectrum patient journeys, including pre-ICU, ICU, and post-ICU encounters across both inpatient and outpatient settings. This multi-institutional, longitudinal perspective creates transformative opportunities for developing generalizable predictive models and advancing health equity research. However, the richness of this multi-site resource introduces substantial complexity in data harmonization, with heterogeneous collection practices and diverse vocabulary usage patterns requiring sophisticated preprocessing approaches. We present CRISP to unlock the full potential of this valuable resource. CRISP systematically transforms raw Observational Medical Outcomes Partnership Common Data Model data into ML-ready datasets through: (1) transparent data quality management with comprehensive audit trails, (2) cross-vocabulary mapping of heterogeneous medical terminologies to unified SNOMED-CT standards, with deduplication and unit standardization, (3) modular architecture with parallel optimization enabling complete dataset processing in $
【14】Rollout-LaSDI: Enhancing the long-term accuracy of Latent Space Dynamics
标题：推出LaEDI：提高潜在空间动力的长期准确性
链接：https://arxiv.org/abs/2509.08191
备注：6 pages, 2 figures
摘要：求解复杂的偏微分方程在物理科学中至关重要，但通常需要计算昂贵的数值方法。降阶模型（ROM）通过利用降维来创建快速近似来解决这个问题。虽然现代ROM可以解决参数化的PDE族，但它们的预测能力会随着时间的推移而下降。我们通过（1）引入一个灵活的，高阶的，但廉价的有限差分格式和（2）提出一个滚动损失，训练ROM在任意时间范围内做出准确的预测。我们证明了我们的方法上的二维Burgers方程。
摘要：Solving complex partial differential equations is vital in the physical sciences, but often requires computationally expensive numerical methods. Reduced-order models (ROMs) address this by exploiting dimensionality reduction to create fast approximations. While modern ROMs can solve parameterized families of PDEs, their predictive power degrades over long time horizons. We address this by (1) introducing a flexible, high-order, yet inexpensive finite-difference scheme and (2) proposing a Rollout loss that trains ROMs to make accurate predictions over arbitrary time horizons. We demonstrate our approach on the 2D Burgers equation.
【15】ArtifactGen: Benchmarking WGAN-GP vs Diffusion for Label-Aware EEG Artifact Synthesis
标题：ArtifactGen：对WGAN-GP与扩散进行标签感知的脑电合成的基准测试
链接：https://arxiv.org/abs/2509.08188
备注：16 Pages, 6 figures
摘要：脑电图（EEG）中的伪影--肌肉、眼球运动、电极、咀嚼和颤抖--使自动化分析变得混乱，但大规模标记的成本很高。我们研究现代生成模型是否可以合成现实的，标签感知的工件段适合增强和压力测试。使用TUH EEG（TUAR）语料库，我们策划了主题分割和固定长度的多通道窗口（例如，250个样本），并为每个模型定制预处理（针对对抗训练的每窗口最小值-最大值;针对扩散的每记录/通道$z$-得分）。我们比较了一个有条件的WGAN-GP与一个具有无分类器指导的一维去噪扩散模型，并沿着三个轴进行评估：（i）通过Welch带功率增量的保真度（$\Delta\delta，\ \Delta\theta，\ \Delta\alpha，\ \Delta\beta$）、通道协方差Frobenius距离、自相关L_2和分布度量（MMD/PRD）;（ii）通过轻量级$k$NN/分类器的类条件恢复的特异性;以及（iii）通过对伪影识别的增强效应的实用性。在我们的设置中，WGAN-GP实现了更接近真实数据的光谱对齐和更低的MMD，而两个模型都表现出较弱的类条件恢复，限制了即时增强增益，并揭示了更强的条件反射和覆盖的机会。我们发布了一个可复制的管道-数据清单，训练配置和评估脚本-为EEG伪影合成建立基线，并为未来的工作提供可操作的故障模式。
摘要：Artifacts in electroencephalography (EEG) -- muscle, eye movement, electrode, chewing, and shiver -- confound automated analysis yet are costly to label at scale. We study whether modern generative models can synthesize realistic, label-aware artifact segments suitable for augmentation and stress-testing. Using the TUH EEG Artifact (TUAR) corpus, we curate subject-wise splits and fixed-length multi-channel windows (e.g., 250 samples) with preprocessing tailored to each model (per-window min--max for adversarial training; per-recording/channel $z$-score for diffusion). We compare a conditional WGAN-GP with a projection discriminator to a 1D denoising diffusion model with classifier-free guidance, and evaluate along three axes: (i) fidelity via Welch band-power deltas ($\Delta\delta,\ \Delta\theta,\ \Delta\alpha,\ \Delta\beta$), channel-covariance Frobenius distance, autocorrelation $L_2$, and distributional metrics (MMD/PRD); (ii) specificity via class-conditional recovery with lightweight $k$NN/classifiers; and (iii) utility via augmentation effects on artifact recognition. In our setting, WGAN-GP achieves closer spectral alignment and lower MMD to real data, while both models exhibit weak class-conditional recovery, limiting immediate augmentation gains and revealing opportunities for stronger conditioning and coverage. We release a reproducible pipeline -- data manifests, training configurations, and evaluation scripts -- to establish a baseline for EEG artifact synthesis and to surface actionable failure modes for future work.
【16】The Domain Mixed Unit: A New Neural Arithmetic Layer
标题：域混合单元：一种新的神经算术层
链接：https://arxiv.org/abs/2509.08180
备注：7 pages, 5 tables, includes results on the NALM benchmark
摘要：域混合单元（Domain Mixed Unit，DMU）是一种新的神经算术单元，它学习一个单参数门，在执行加法（DMU add）或减法（DMU sub）时混合对数空间和线性空间表示。提出了DMU的两种初始化方法：一种覆盖加法和乘法，另一种覆盖减法和除法。DMU在NALM Benchmark上实现了最先进的性能，NALM Benchmark是一个旨在测试神经算术单元泛化算术运算能力的数据集，特别是在乘法和除法的所有种子上解决的最高百分比。DMU将作为pull request提交给开源NALM基准测试，其代码可在GitHub上获得，网址为https://github.com/marict? tab=存储库
摘要：The Domain Mixed Unit (DMU) is a new neural arithmetic unit that learns a single parameter gate that mixes between log-space and linear-space representations while performing either addition (DMU add) or subtraction (DMU sub). Two initializations are proposed for the DMU: one covering addition and multiplication, and another covering subtraction and division. The DMU achieves state-of-the-art performance on the NALM Benchmark, a dataset designed to test the ability of neural arithmetic units to generalize arithmetic operations, specifically performing with the highest percentage solved over all seeds on multiplication and division. The DMU will be submitted as a pull request to the open-source NALM benchmark, and its code is available on GitHub at https://github.com/marict?tab=repositories
【17】MMM-fair: An Interactive Toolkit for Exploring and Operationalizing Multi-Fairness Trade-offs
标题：MMM-fair：探索和操作多重公平权衡的交互式工具包
链接：https://arxiv.org/abs/2509.08156
备注：Accepted to be published in the Proceedings of the 34th ACM International Conference on Information and Knowledge Management, November 10--14, 2025, Seoul, Republic of Korea
摘要：公平意识分类需要平衡性能和公平性，这往往会因交叉偏见而加剧。不确定公平的定义使任务更加复杂，难以确定普遍公平的解决方案。尽管监管和社会对公平人工智能的需求不断增长，但流行的工具包对探索多维公平和相关权衡的支持有限。为了解决这个问题，我们提出了mmm-fair，这是一个开源工具包，它利用基于提升的集成方法，动态优化模型权重，以最大限度地减少分类错误和各种公平性违规，从而实现灵活的多目标优化。该系统使用户能够部署符合其特定背景需求的模型，同时可靠地发现最先进的方法经常遗漏的交叉偏差。简而言之，mmm-fair独特地将深入的多属性公平性，多目标优化，无代码，基于聊天的界面，LLM支持的解释，用于模型选择的交互式Pareto探索，自定义公平约束定义和部署就绪模型结合在一个开源工具包中，这是现有公平工具中很少发现的组合。演示演练可在以下网址获得：https://youtu.be/_rcpjlXFqkw。
摘要：Fairness-aware classification requires balancing performance and fairness, often intensified by intersectional biases. Conflicting fairness definitions further complicate the task, making it difficult to identify universally fair solutions. Despite growing regulatory and societal demands for equitable AI, popular toolkits offer limited support for exploring multi-dimensional fairness and related trade-offs. To address this, we present mmm-fair, an open-source toolkit leveraging boosting-based ensemble approaches that dynamically optimizes model weights to jointly minimize classification errors and diverse fairness violations, enabling flexible multi-objective optimization. The system empowers users to deploy models that align with their context-specific needs while reliably uncovering intersectional biases often missed by state-of-the-art methods. In a nutshell, mmm-fair uniquely combines in-depth multi-attribute fairness, multi-objective optimization, a no-code, chat-based interface, LLM-powered explanations, interactive Pareto exploration for model selection, custom fairness constraint definition, and deployment-ready models in a single open-source toolkit, a combination rarely found in existing fairness tools. Demo walkthrough available at: https://youtu.be/_rcpjlXFqkw.
【18】Performance Assessment Strategies for Generative AI Applications in Healthcare
标题：医疗保健领域生成人工智能应用的性能评估策略
链接：https://arxiv.org/abs/2509.08087
摘要：生成式人工智能（GenAI）代表了人工智能中的一种新兴范式，其应用遍及整个医疗企业。评估GenAI应用程序需要全面了解临床任务，并了解在实际临床环境中实施时的性能变化。目前，一个流行的方法来评估生成模型的性能依赖于定量基准。这样的基准测试具有局限性，并且可能遭受训练到测试的过拟合，以其他任务和数据分布的可推广性为代价优化指定测试集的性能。利用人类专门知识和利用具有成本效益的计算模型作为评价者的评价战略正引起人们的兴趣。我们讨论了当前最先进的方法，用于评估医疗保健和医疗设备中GenAI应用程序的性能。
摘要：Generative artificial intelligence (GenAI) represent an emerging paradigm within artificial intelligence, with applications throughout the medical enterprise. Assessing GenAI applications necessitates a comprehensive understanding of the clinical task and awareness of the variability in performance when implemented in actual clinical environments. Presently, a prevalent method for evaluating the performance of generative models relies on quantitative benchmarks. Such benchmarks have limitations and may suffer from train-to-the-test overfitting, optimizing performance for a specified test set at the cost of generalizability across other task and data distributions. Evaluation strategies leveraging human expertise and utilizing cost-effective computational models as evaluators are gaining interest. We discuss current state-of-the-art methodologies for assessing the performance of GenAI applications in healthcare and medical devices.
【19】How Far Are We from True Unlearnability?
标题：我们距离真正的不可学习还有多远？
链接：https://arxiv.org/abs/2509.08058
备注：This paper has been accepted by ICLR 2025
摘要：高质量的数据在大模型时代起着不可或缺的作用，但使用未经授权的数据进行模型训练，极大地损害了数据所有者的利益。为了克服这种威胁，已经提出了几种不可学习的方法，这些方法通过损害数据的训练可用性来生成不可学习的示例（UE）。显然，由于未知的训练目的和现有模型强大的表示学习能力，这些数据预计对于跨多个任务的模型是不可学习的，即，它们不会帮助改进模型的性能。然而，出乎意料的是，我们发现在多任务数据集Taskonomy上，UE在语义分割等任务中仍然表现良好，未能表现出跨任务的不可学习性。这一现象让我们不禁要问：我们离获得真正不可学的例子还有多远？我们试图从模型优化的角度来回答这个问题。为此，我们使用一个简单的模型架构，观察干净和中毒模型之间的收敛过程中的差异。随后，从损失景观，我们发现，只有一部分的关键参数优化路径显示出显着的差异，这意味着损失景观和不可学习性之间的密切关系。因此，我们采用损失景观来解释UE的根本原因，并提出了清晰度感知可学习性（SAL）来量化基于这种解释的参数的不可学习性。此外，我们提出了一个不可学习的距离（UD）来衡量数据的不可学习性的基础上SAL分布的参数在清洁和中毒模型。最后，我们使用建议的UD对主流不可学习方法进行基准测试，旨在促进社区对现有不可学习方法的能力边界的认识。
摘要：High-quality data plays an indispensable role in the era of large models, but the use of unauthorized data for model training greatly damages the interests of data owners. To overcome this threat, several unlearnable methods have been proposed, which generate unlearnable examples (UEs) by compromising the training availability of data. Clearly, due to unknown training purposes and the powerful representation learning capabilities of existing models, these data are expected to be unlearnable for models across multiple tasks, i.e., they will not help improve the model's performance. However, unexpectedly, we find that on the multi-task dataset Taskonomy, UEs still perform well in tasks such as semantic segmentation, failing to exhibit cross-task unlearnability. This phenomenon leads us to question: How far are we from attaining truly unlearnable examples? We attempt to answer this question from the perspective of model optimization. To this end, we observe the difference in the convergence process between clean and poisoned models using a simple model architecture. Subsequently, from the loss landscape we find that only a part of the critical parameter optimization paths show significant differences, implying a close relationship between the loss landscape and unlearnability. Consequently, we employ the loss landscape to explain the underlying reasons for UEs and propose Sharpness-Aware Learnability (SAL) to quantify the unlearnability of parameters based on this explanation. Furthermore, we propose an Unlearnable Distance (UD) to measure the unlearnability of data based on the SAL distribution of parameters in clean and poisoned models. Finally, we conduct benchmark tests on mainstream unlearnable methods using the proposed UD, aiming to promote community awareness of the capability boundaries of existing unlearnable methods.
【20】Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
标题：视频并行缩放：聚合VideoLLM的不同帧子集
链接：https://arxiv.org/abs/2509.08016
备注：his https URL
摘要：视频大语言模型（VideoLLM）面临着一个关键的瓶颈：增加输入帧的数量来捕捉细粒度的时间细节，导致高昂的计算成本和性能下降，从长的上下文长度。我们介绍了视频并行缩放（VPS），推理时间的方法，扩大了模型的感知带宽，而不增加其上下文窗口。VPS通过运行多个并行推理流来运行，每个推理流处理视频帧的唯一的、不相交的子集。通过聚合来自这些互补流的输出概率，VPS集成了比单次通过更丰富的视觉信息集。我们从理论上证明，这种方法通过利用不相关的视觉证据有效地收缩了龙猫缩放定律，从而在不进行额外训练的情况下提高了性能。在Video-MME和EventHalusion等基准测试中，各种模型架构和规模（2B-32 B）的广泛实验表明，VPS始终显着提高性能。它比其他并行替代方案（例如自一致性）更有利地扩展，并且与其他解码策略互补，为增强VideoLLM的时间推理能力提供了一个高效的存储器和强大的框架。
摘要：Video Large Language Models (VideoLLMs) face a critical bottleneck: increasing the number of input frames to capture fine-grained temporal detail leads to prohibitive computational costs and performance degradation from long context lengths. We introduce Video Parallel Scaling (VPS), an inference-time method that expands a model's perceptual bandwidth without increasing its context window. VPS operates by running multiple parallel inference streams, each processing a unique, disjoint subset of the video's frames. By aggregating the output probabilities from these complementary streams, VPS integrates a richer set of visual information than is possible with a single pass. We theoretically show that this approach effectively contracts the Chinchilla scaling law by leveraging uncorrelated visual evidence, thereby improving performance without additional training. Extensive experiments across various model architectures and scales (2B-32B) on benchmarks such as Video-MME and EventHallusion demonstrate that VPS consistently and significantly improves performance. It scales more favorably than other parallel alternatives (e.g. Self-consistency) and is complementary to other decoding strategies, offering a memory-efficient and robust framework for enhancing the temporal reasoning capabilities of VideoLLMs.
【21】Bregman Douglas-Rachford Splitting Method
标题：Bregman Douglas-Rachford分裂法
链接：https://arxiv.org/abs/2509.08739
摘要 ：本文提出了求解极大单调包含问题的Bregman Douglas-Rachford分裂（BDRS）方法及其变形Bregman Douglas-Rachford分裂方法.我们表明，BDRS是等价的Bregman交替方向的乘法器（ADMM）时，适用于对偶的问题。Bregman ADMM的一个特例是指数乘子法的交替方向版本。据我们所知，本文提出的算法是新的文献。我们还讨论了如何使用我们的算法来解决离散最优运输（OT）问题。我们证明了一定的假设下的算法的收敛性，虽然我们指出，一个假设不适用于OT问题。
摘要：In this paper, we propose the Bregman Douglas-Rachford splitting (BDRS) method and its variant Bregman Peaceman-Rachford splitting method for solving maximal monotone inclusion problem. We show that BDRS is equivalent to a Bregman alternating direction method of multipliers (ADMM) when applied to the dual of the problem. A special case of the Bregman ADMM is an alternating direction version of the exponential multiplier method. To the best of our knowledge, algorithms proposed in this paper are new to the literature. We also discuss how to use our algorithms to solve the discrete optimal transport (OT) problem. We prove the convergence of the algorithms under certain assumptions, though we point out that one assumption does not apply to the OT problem.
【22】Tokenizing Loops of Antibodies
标题：标记抗体环
链接：https://arxiv.org/abs/2509.08707
备注：21 pages, 7 figures, 10 tables, code available at this https URL
摘要：抗体的互补决定区是其与抗原相互作用的关键环结构，并且对于新型生物制剂的设计具有高度重要性。自20世纪80年代以来，将CDR结构的多样性分类为规范簇已经使得能够鉴定抗体的关键结构基序。然而，现有的方法具有有限的覆盖范围，并且不能容易地并入蛋白质基础模型。在这里，我们介绍ImmunoGlobulin LOOp Tokenizer，Igloo，一种编码主链二面角和序列的多模式抗体环标记器。Igloo使用对比学习目标进行训练，以在潜在空间中更紧密地映射具有相似骨架二面角的循环。Igloo可以有效地从结构抗体数据库中检索最接近的匹配环结构，在识别相似的H3环方面优于现有方法5.9%。Igloo将标记分配给所有循环，解决了规范簇的有限覆盖问题，同时保留了恢复规范循环构象的能力。为了证明Igloo令牌的多功能性，我们展示了它们可以通过IglooLM和IglooALM并入蛋白质语言模型。在预测重链变体的结合亲和力时，IglooLM在10个抗体-抗原靶标中的8个上优于基础蛋白质语言模型。此外，它与现有的最先进的基于序列和多模式蛋白质语言模型相当，可以使用多7倍的参数执行多模式模型。IglooALM样品抗体环在序列上是多样的，并且在结构上比最先进的抗体反向折叠模型更一致。Igloo展示了引入抗体环的多模态标记的益处，用于编码抗体环的多样性景观，改进蛋白质基础模型，以及用于抗体CDR设计。
摘要：The complementarity-determining regions of antibodies are loop structures that are key to their interactions with antigens, and of high importance to the design of novel biologics. Since the 1980s, categorizing the diversity of CDR structures into canonical clusters has enabled the identification of key structural motifs of antibodies. However, existing approaches have limited coverage and cannot be readily incorporated into protein foundation models. Here we introduce ImmunoGlobulin LOOp Tokenizer, Igloo, a multimodal antibody loop tokenizer that encodes backbone dihedral angles and sequence. Igloo is trained using a contrastive learning objective to map loops with similar backbone dihedral angles closer together in latent space. Igloo can efficiently retrieve the closest matching loop structures from a structural antibody database, outperforming existing methods on identifying similar H3 loops by 5.9\%. Igloo assigns tokens to all loops, addressing the limited coverage issue of canonical clusters, while retaining the ability to recover canonical loop conformations. To demonstrate the versatility of Igloo tokens, we show that they can be incorporated into protein language models with IglooLM and IglooALM. On predicting binding affinity of heavy chain variants, IglooLM outperforms the base protein language model on 8 out of 10 antibody-antigen targets. Additionally, it is on par with existing state-of-the-art sequence-based and multimodal protein language models, performing comparably to models with $7\times$ more parameters. IglooALM samples antibody loops which are diverse in sequence and more consistent in structure than state-of-the-art antibody inverse folding models. Igloo demonstrates the benefit of introducing multimodal tokens for antibody loops for encoding the diverse landscape of antibody loops, improving protein foundation models, and for antibody CDR design.
【23】A hierarchical entropy method for the delocalization of bias in high-dimensional Langevin Monte Carlo
标题：多维Langevin Monte Carlo中偏差离域的分层熵方法
链接：https://arxiv.org/abs/2509.08619
摘要：非调整Langevin算法被广泛用于复杂高维分布的采样。众所周知，它是有偏差的，当以平方Wasserstein距离测量时，偏差通常与维度线性缩放。然而，Chen et al.（2024）最近的论文确定了一个有趣的新离域效应：对于一类具有稀疏相互作用的分布，低维边缘之间的偏差仅与较低维度有关，而不是全维度。在这项工作中，我们通过删除对数因子，测量相对熵（a.k.a.）中的距离，加强了Chen等人（2024）在稀疏相互作用机制中的结果。KL-发散），并放松强对数-方差假设。此外，我们扩大了范围的离域现象表明，它适用于一类分布弱相互作用。我们的证明是基于边缘相对熵的层次分析，作者最近的工作混沌传播的启发。
摘要：The unadjusted Langevin algorithm is widely used for sampling from complex high-dimensional distributions. It is well known to be biased, with the bias typically scaling linearly with the dimension when measured in squared Wasserstein distance. However, the recent paper of Chen et al. (2024) identifies an intriguing new delocalization effect: For a class of distributions with sparse interactions, the bias between low-dimensional marginals scales only with the lower dimension, not the full dimension. In this work, we strengthen the results of Chen et al. (2024) in the sparse interaction regime by removing a logarithmic factor, measuring distance in relative entropy (a.k.a. KL-divergence), and relaxing the strong log-concavity assumption. In addition, we expand the scope of the delocalization phenomenon by showing that it holds for a class of distributions with weak interactions. Our proofs are based on a hierarchical analysis of the marginal relative entropies, inspired by the authors' recent work on propagation of chaos.
【24】PEHRT: A Common Pipeline for Harmonizing Electronic Health Record data for Translational Research
标题：PEHRT：协调电子健康记录数据以进行转化研究的通用管道
链接：https://arxiv.org/abs/2509.08553
摘要：多机构电子健康记录（EHR）数据的综合分析通过利用更大，更多样化的患者队列并结合多种数据模式，增强了转化研究的可靠性和普遍性。然而，由于数据异构性、语义差异和隐私问题，协调各机构的EHR数据构成了重大挑战。为了应对这些挑战，我们引入了$\textit{PEHRT}$，这是一个标准化的管道，用于有效的EHR数据协调，包括两个核心模块：（1）数据预处理和（2）表示学习。PEHRT将EHR数据映射到标准编码系统，并使用先进的机器学习来生成研究就绪的数据集，而无需个人层面的数据共享。我们的管道也是数据模型不可知的，旨在根据我们广泛的实际经验简化跨机构的执行。我们提供了一套完整的开源软件，并附有用户友好的教程，并使用来自不同医疗保健系统的数据演示了PEHRT在各种任务中的实用性。
摘要：Integrative analysis of multi-institutional Electronic Health Record (EHR) data enhances the reliability and generalizability of translational research by leveraging larger, more diverse patient cohorts and incorporating multiple data modalities. However, harmonizing EHR data across institutions poses major challenges due to data heterogeneity, semantic differences, and privacy concerns. To address these challenges, we introduce $\textit{PEHRT}$, a standardized pipeline for efficient EHR data harmonization consisting of two core modules: (1) data pre-processing and (2) representation learning. PEHRT maps EHR data to standard coding systems and uses advanced machine learning to generate research-ready datasets without requiring individual-level data sharing. Our pipeline is also data model agnostic and designed for streamlined execution across institutions based on our extensive real-world experience. We provide a complete suite of open source software, accompanied by a user-friendly tutorial, and demonstrate the utility of PEHRT in a variety of tasks using data from diverse healthcare systems.
【25】Agents of Discovery
标题：发现的代理
链接：https://arxiv.org/abs/2509.08535
摘要：在现代粒子物理学和基础物理学研究的其他领域中遇到的大量数据允许（并且需要）使用日益复杂的数据分析工具和工作流程。虽然机器学习（ML）工具用于数据分析的使用最近已经激增，但这些工具通常是依赖于编码物理知识以达到最佳性能的专用算法。在这项工作中，我们研究了一个新的正交方向：使用大型语言模型（LLM）的最新进展来创建一个代理团队-具有特定子任务的LLM实例-以类似于人类研究人员的方式共同解决基于数据分析的研究问题：通过创建代码来操作标准工具和库（包括ML系统）并通过构建以前迭代的结果。如果成功的话，这种基于代理的系统可以被部署来自动化常规分析组件，以抵消现代工具链日益增加的复杂性。为了研究当前一代商业LLM的能力，我们考虑通过公开可用和高度研究的LHC Olympics数据集进行异常检测的任务。研究了OpenAI的几个当前模型（GPT-4 o，o 4-mini，GPT-4.1和GPT-5），并测试了它们的稳定性。总的来说，我们观察的能力，基于代理的系统来解决这个数据分析问题。最好的代理创建的解决方案反映了人类最先进的结果的性能。
摘要：The substantial data volumes encountered in modern particle physics and other domains of fundamental physics research allow (and require) the use of increasingly complex data analysis tools and workflows. While the use of machine learning (ML) tools for data analysis has recently proliferated, these tools are typically special-purpose algorithms that rely, for example, on encoded physics knowledge to reach optimal performance. In this work, we investigate a new and orthogonal direction: Using recent progress in large language models (LLMs) to create a team of agents -- instances of LLMs with specific subtasks -- that jointly solve data analysis-based research problems in a way similar to how a human researcher might: by creating code to operate standard tools and libraries (including ML systems) and by building on results of previous iterations. If successful, such agent-based systems could be deployed to automate routine analysis components to counteract the increasing complexity of modern tool chains. To investigate the capabilities of current-generation commercial LLMs, we consider the task of anomaly detection via the publicly available and highly-studied LHC Olympics dataset. Several current models by OpenAI (GPT-4o, o4-mini, GPT-4.1, and GPT-5) are investigated and their stability tested. Overall, we observe the capacity of the agent-based system to solve this data analysis problem. The best agent-created solutions mirror the performance of human state-of-the-art results.
【26】kNNSampler: Stochastic Imputations for Recovering Missing Value Distributions
标题：kNN Sampler：恢复缺失值分布的随机输入
链接：https://arxiv.org/abs/2509.08366
摘要：我们研究了一个缺失值插补方法，称为kNNSampler，插补一个给定的单位的缺失响应随机抽样的$k$最相似的单位，以给定的单位观察到的协变量的观察响应。该方法可以从缺失值的分布中抽取未知的缺失值，量化缺失值的不确定性，并易于进行多重插补。与流行的kNNImputer不同，它估计给定观测协变量的缺失响应的条件均值，kNNSampler理论上可估计给定观测协变量的缺失响应的条件分布。实验证明了该方法在恢复缺失值分布方面的有效性。kNNSampler的代码是公开的（https：//github.com/SAP/knn-sampler）。
摘要：We study a missing-value imputation method, termed kNNSampler, that imputes a given unit's missing response by randomly sampling from the observed responses of the $k$ most similar units to the given unit in terms of the observed covariates. This method can sample unknown missing values from their distributions, quantify the uncertainties of missing values, and be readily used for multiple imputation. Unlike popular kNNImputer, which estimates the conditional mean of a missing response given an observed covariate, kNNSampler is theoretically shown to estimate the conditional distribution of a missing response given an observed covariate. Experiments demonstrate its effectiveness in recovering the distribution of missing values. The code for kNNSampler is made publicly available (https://github.com/SAP/knn-sampler).
【27】STROKEVISION-BENCH: A Multimodal Video And 2D Pose Benchmark For Tracking Stroke Recovery
标题：Strokevision-Bench：用于跟踪中风恢复的多模式视频和2D姿势基准
链接：https://arxiv.org/abs/2509.07994
备注：6 pages
摘要：尽管康复方案取得了进展，但中风后上肢（UE）功能的临床评估在很大程度上仍然是主观的，严重依赖于治疗师的观察和粗略的评分系统。这种主观性限制了评估的灵敏度，以检测细微的运动改善，这是个性化康复计划的关键。计算机视觉的最新进展为实现UE运动功能的客观，定量和可扩展的评估提供了有希望的途径。在标准化测试中，框块测试（BBT）被广泛用于测量总的手动灵活性和跟踪中风恢复，提供了一个结构化的设置，适合于计算分析。然而，针对中风康复的现有数据集主要关注日常生活活动，并且通常无法捕获临床结构化评估，例如块转移任务。此外，许多可用的数据集包括健康和受中风影响的个体的混合物，限制了它们的特异性和临床实用性。为了解决这些关键的差距，我们引入了StrokeVision-Bench，这是有史以来第一个执行临床结构化块转移任务的中风患者专用数据集。StrokeVision-Bench包含1，000个注释视频，分为四个有临床意义的动作类，每个样本以两种方式表示：原始视频帧和2D骨骼关键点。我们对几种最先进的视频动作识别和基于动作分类的方法进行了基准测试，以建立该领域的性能基线，并促进自动中风康复评估的未来研究。
摘要：Despite advancements in rehabilitation protocols, clinical assessment of upper extremity (UE) function after stroke largely remains subjective, relying heavily on therapist observation and coarse scoring systems. This subjectivity limits the sensitivity of assessments to detect subtle motor improvements, which are critical for personalized rehabilitation planning. Recent progress in computer vision offers promising avenues for enabling objective, quantitative, and scalable assessment of UE motor function. Among standardized tests, the Box and Block Test (BBT) is widely utilized for measuring gross manual dexterity and tracking stroke recovery, providing a structured setting that lends itself well to computational analysis. However, existing datasets targeting stroke rehabilitation primarily focus on daily living activities and often fail to capture clinically structured assessments such as block transfer tasks. Furthermore, many available datasets include a mixture of healthy and stroke-affected individuals, limiting their specificity and clinical utility. To address these critical gaps, we introduce StrokeVision-Bench, the first-ever dedicated dataset of stroke patients performing clinically structured block transfer tasks. StrokeVision-Bench comprises 1,000 annotated videos categorized into four clinically meaningful action classes, with each sample represented in two modalities: raw video frames and 2D skeletal keypoints. We benchmark several state-of-the-art video action recognition and skeleton-based action classification methods to establish performance baselines for this domain and facilitate future research in automated stroke rehabilitation assessment.
机器翻译由腾讯交互翻译提供，仅供参考
点击“阅读原文”获取带摘要的学术速递
Python社区是高质量的Python/Django开发社区
本文地址：http://www.python88.com/topic/186613
本文地址：http://www.python88.com/topic/186613