|
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92篇
大模型相关(12篇)
【1】ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms
标题：ButterflyQuant：通过可学习的垂直蝴蝶变换进行超低位LLM量化
链接：https://arxiv.org/abs/2509.09679
备注：Replace discrete Hadamard transforms with continuous Butterfly transforms to facilitate the learning of rotation matrices in LLM quantization
摘要：大型语言模型需要占用大量内存，严重限制了在消费者硬件上的部署。量化通过较低的数值精度减少了内存，但极端的2位量化由于激活中的异常值而遭受灾难性的性能损失。基于旋转的方法（如QuIP和RISTORot）在量化之前应用正交变换来消除离群值，使用计算不变性：对于正交$\mathbf {Q}$，$\mathbf{y} = \mathbf {Wx} =（\mathbf{WQ}^T）（\mathbf {Qx}）$。然而，这些方法使用固定的变换-Hadamard矩阵实现最佳的最坏情况下的一致性$\mu = 1/\sqrt{n}$-不能适应特定的权重分布。我们发现，不同的Transformer层表现出不同的离群模式，激励层自适应旋转，而不是一刀切的方法。我们提出了ButterflyQuant，它取代阿达玛旋转与可学习的蝴蝶变换参数化的连续Givens旋转角度。与Hadamard的离散$\{+1，-1\}$项不可微并且禁止基于梯度的学习不同，蝶形变换的连续参数化能够实现平滑优化，同时通过构造来保证正交性。这种正交约束确保了离群值抑制的理论保证，同时仅使用$\frac{n \log n}{2}$可学习参数实现$O（n \log n）$计算复杂度。我们还引入了一个均匀性正则化后转换激活，以促进更平滑的分布服从量化。学习只需要128个校准样本，并在单个GPU上几分钟内收敛-一次性成本可以忽略不计。在具有2位量化的LLaMA-2- 7 B上，ButterflyQuant实现了15.4的困惑度，而对于RightRot则为22.1。
摘要：Large language models require massive memory footprints, severely limiting deployment on consumer hardware. Quantization reduces memory through lower numerical precision, but extreme 2-bit quantization suffers from catastrophic performance loss due to outliers in activations. Rotation-based methods such as QuIP and QuaRot apply orthogonal transforms to eliminate outliers before quantization, using computational invariance: $\mathbf{y} = \mathbf{Wx} = (\mathbf{WQ}^T)(\mathbf{Qx})$ for orthogonal $\mathbf{Q}$. However, these methods use fixed transforms--Hadamard matrices achieving optimal worst-case coherence $\mu = 1/\sqrt{n}$--that cannot adapt to specific weight distributions. We identify that different transformer layers exhibit distinct outlier patterns, motivating layer-adaptive rotations rather than one-size-fits-all approaches. We propose ButterflyQuant, which replaces Hadamard rotations with learnable butterfly transforms parameterized by continuous Givens rotation angles. Unlike Hadamard's discrete $\{+1, -1\}$ entries that are non-differentiable and prohibit gradient-based learning, butterfly transforms' continuous parameterization enables smooth optimization while guaranteeing orthogonality by construction. This orthogonal constraint ensures theoretical guarantees in outlier suppression while achieving $O(n \log n)$ computational complexity with only $\frac{n \log n}{2}$ learnable parameters. We further introduce a uniformity regularization on post-transformation activations to promote smoother distributions amenable to quantization. Learning requires only 128 calibration samples and converges in minutes on a single GPU--a negligible one-time cost. On LLaMA-2-7B with 2-bit quantization, ButterflyQuant achieves 15.4 perplexity versus 22.1 for QuaRot.
【2】CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
标题：ADE：好奇心驱动的大型语言模型中高效强化学习探索
链接：https://arxiv.org/abs/2509.09675
备注：21 pages
摘要：具有可验证奖励的强化学习（RLVR）是增强大型语言模型（LLM）推理能力的强大范例。然而，目前的RLVR方法往往探索不佳，导致过早收敛和熵崩溃。为了应对这一挑战，我们引入了好奇心驱动的探索（CDE），这是一个利用模型自身内在的好奇心来指导探索的框架。我们用来自演员和评论家的信号将好奇心形式化：对于演员，我们对其生成的响应使用困惑，对于评论家，我们使用来自多头架构的价值估计的方差。这两个信号都是RLVR框架内的探索奖励，以指导模型。我们的理论分析表明，演员明智的奖金本质上惩罚过度自信的错误，并促进正确的反应之间的多样性，此外，我们连接的批评明智的奖金，以完善的计数为基础的探索奖金在RL。从经验上讲，我们的方法在AIME基准测试中使用GRPO/PPO比标准RLVR实现了大约+3点的改进。进一步的分析确定了RLVR内的校准崩溃机制，揭示了常见的LLM故障模式。
摘要：Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for enhancing the reasoning ability of Large Language Models (LLMs). Yet current RLVR methods often explore poorly, leading to premature convergence and entropy collapse. To address this challenge, we introduce Curiosity-Driven Exploration (CDE), a framework that leverages the model's own intrinsic sense of curiosity to guide exploration. We formalize curiosity with signals from both the actor and the critic: for the actor, we use perplexity over its generated response, and for the critic, we use the variance of value estimates from a multi-head architecture. Both signals serve as an exploration bonus within the RLVR framework to guide the model. Our theoretical analysis shows that the actor-wise bonus inherently penalizes overconfident errors and promotes diversity among correct responses; moreover, we connect the critic-wise bonus to the well-established count-based exploration bonus in RL. Empirically, our method achieves an approximate +3 point improvement over standard RLVR using GRPO/PPO on AIME benchmarks. Further analysis identifies a calibration collapse mechanism within RLVR, shedding light on common LLM failure modes.
【3】Steering MoE LLMs via Expert (De)Activation
标题：通过专家（去）激活MoE LLM
链接：https://arxiv.org/abs/2509.09660
摘要：大型语言模型（LLM）中的专家混合（MoE）通过专用前馈网络（FFN）的子集（称为专家）路由每个令牌。我们提出了SteerMoE，一个框架，用于通过检测和控制与行为相关的专家来引导MoE模型。我们的检测方法识别专家与不同的激活模式，在成对的输入表现出对比的行为。通过在推理过程中选择性地激活（去激活）这些专家，我们可以控制忠诚和安全等行为，而无需重新训练或修改权重。在11个基准和6个LLM中，我们的转向将安全性提高了20%，忠诚度提高了27%。在对抗攻击模式下，它的安全性下降了41%，与现有的越狱方法结合使用时，安全性下降了100%，绕过了所有的安全护栏，并暴露了隐藏在专家内部的对齐伪造的新维度。
摘要：Mixture-of-Experts (MoE) in Large Language Models (LLMs) routes each token through a subset of specialized Feed-Forward Networks (FFN), known as experts. We present SteerMoE, a framework for steering MoE models by detecting and controlling behavior-linked experts. Our detection method identifies experts with distinct activation patterns across paired inputs exhibiting contrasting behaviors. By selectively (de)activating such experts during inference, we control behaviors like faithfulness and safety without retraining or modifying weights. Across 11 benchmarks and 6 LLMs, our steering raises safety by up to +20% and faithfulness by +27%. In adversarial attack mode, it drops safety by -41% alone, and -100% when combined with existing jailbreak methods, bypassing all safety guardrails and exposing a new dimension of alignment faking hidden within experts.
【4】LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations
标题：法学硕士不知道自己的决策边界：自发反事实解释的不可靠性
链接：https://arxiv.org/abs/2509.09396
备注：Accepted to EMNLP 2025 Main
摘要：为了有效地与人类协作，语言模型必须能够用自然语言解释它们的决策。我们研究了一种特定类型的自我解释：自我生成的反事实解释（SCE），其中模型通过修改输入来解释其预测，从而预测不同的结果。我们评估LLM是否可以产生有效的SCE，实现预期的结果，并最小化，修改输入不超过必要的。当被要求生成反事实时，我们发现LLM通常会产生有效的SCE，但远非最小，对他们的决策行为几乎没有什么洞察力。令人担忧的是，当被要求生成最小的反事实时，LLM通常会进行过小的编辑，无法改变预测。观察到的有效性-最小值权衡在几个LLM、数据集和评估设置中是一致的。我们的研究结果表明，SCE是，在最好的情况下，一个无效的解释工具，在最坏的情况下，可以提供误导性的见解模型的行为。在高风险环境中部署LLM的建议必须考虑不可靠的自我解释对下游决策的影响。我们的代码可在https://github.com/HarryMayne/SCEs上获得。
摘要：To collaborate effectively with humans, language models must be able to explain their decisions in natural language. We study a specific type of self-explanation: self-generated counterfactual explanations (SCEs), where a model explains its prediction by modifying the input such that it would have predicted a different outcome. We evaluate whether LLMs can produce SCEs that are valid, achieving the intended outcome, and minimal, modifying the input no more than necessary. When asked to generate counterfactuals, we find that LLMs typically produce SCEs that are valid, but far from minimal, offering little insight into their decision-making behaviour. Worryingly, when asked to generate minimal counterfactuals, LLMs typically make excessively small edits that fail to change predictions. The observed validity-minimality trade-off is consistent across several LLMs, datasets, and evaluation settings. Our findings suggest that SCEs are, at best, an ineffective explainability tool and, at worst, can provide misleading insights into model behaviour. Proposals to deploy LLMs in high-stakes settings must consider the impact of unreliable self-explanations on downstream decision-making. Our code is available at https://github.com/HarryMayne/SCEs.
【5】MetaLLMix : An XAI Aided LLM-Meta-learning Based Approach for Hyper-parameters Optimization
标题：MetaLLMix：一种基于XAI辅助LLM-Meta学习的超参数优化方法
链接：https://arxiv.org/abs/2509.09387
摘要：有效的模型和超参数选择仍然是深度学习的主要挑战，通常需要大量的专业知识和计算。虽然AutoML和大型语言模型（LLM）承诺自动化，但当前基于LLM的方法依赖于试错和昂贵的API，这提供了有限的可解释性和可推广性。我们提出了MetaLLMiX，一个结合元学习，可解释AI和高效LLM推理的zero-shot超参数优化框架。通过利用SHAP解释的历史实验结果，MetaLLMiX推荐最佳超参数和预训练模型，而无需额外的试验。我们进一步采用LLM作为判断评估来控制输出格式，准确性和完整性。使用9个开源轻量级LLM对8个医学成像数据集进行的实验表明，MetaLLMiX在大幅降低计算成本的同时，实现了与传统HPO方法相比具有竞争力或优越性的性能。我们的本地部署优于之前基于API的方法，在8个任务中的5个任务上实现了最佳结果，响应时间缩短了99.6- 99.9%，在6个数据集上的训练时间最快（快2.4- 15.7倍），精度保持在最佳性能基线的1-5%以内。
摘要：Effective model and hyperparameter selection remains a major challenge in deep learning, often requiring extensive expertise and computation. While AutoML and large language models (LLMs) promise automation, current LLM-based approaches rely on trial and error and expensive APIs, which provide limited interpretability and generalizability. We propose MetaLLMiX, a zero-shot hyperparameter optimization framework combining meta-learning, explainable AI, and efficient LLM reasoning. By leveraging historical experiment outcomes with SHAP explanations, MetaLLMiX recommends optimal hyperparameters and pretrained models without additional trials. We further employ an LLM-as-judge evaluation to control output format, accuracy, and completeness. Experiments on eight medical imaging datasets using nine open-source lightweight LLMs show that MetaLLMiX achieves competitive or superior performance to traditional HPO methods while drastically reducing computational cost. Our local deployment outperforms prior API-based approaches, achieving optimal results on 5 of 8 tasks, response time reductions of 99.6-99.9%, and the fastest training times on 6 datasets (2.4-15.7x faster), maintaining accuracy within 1-5% of best-performing baselines.
【6】Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents
标题：利用不确定性：长期LLM代理人的熵调节政策因素
链接：https://arxiv.org/abs/2509.09265
备注：ICLR 2026 Under review
摘要：在长期任务中，最近基于大型语言模型（LLM）的代理面临着一个重大挑战，即稀疏的基于结果的奖励使得难以将信用分配给中间步骤。以前的方法主要集中在创建密集的奖励信号来指导学习，无论是通过传统的强化学习技术，如反向强化学习，还是通过使用过程奖励模型进行逐步反馈。在本文中，我们确定了LLM学习动态中的一个基本问题：策略梯度的大小与熵固有地耦合在一起，这会导致对自信的正确操作进行低效的小更新，并可能使不确定操作的大更新不稳定。为了解决这个问题，我们提出了熵调制策略约束（EMPG），这是一个基于逐步不确定性和最终任务结果重新校准学习信号的框架。EMPG放大了自信的正确动作的更新，惩罚自信的错误，并衰减不确定步骤的更新以稳定探索。我们还引入了一个奖励条款，以鼓励代理人找到更可预测的解决方案路径。通过对WebShop、ALFWorld和Deep Search这三个具有挑战性的代理任务进行综合实验，我们证明了EMPG实现了显著的性能提升，并显著优于强策略梯度基线。项目页面位于https://empgseed-seed.github.io/
摘要：In long-horizon tasks, recent agents based on Large Language Models (LLMs) face a significant challenge that sparse, outcome-based rewards make it difficult to assign credit to intermediate steps. Previous methods mainly focus on creating dense reward signals to guide learning, either through traditional reinforcement learning techniques like inverse reinforcement learning or by using Process Reward Models for step-by-step feedback. In this paper, we identify a fundamental problem in the learning dynamics of LLMs: the magnitude of policy gradients is inherently coupled with the entropy, which leads to inefficient small updates for confident correct actions and potentially destabilizes large updates for uncertain ones. To resolve this, we propose Entropy-Modulated Policy Gradients (EMPG), a framework that re-calibrates the learning signal based on step-wise uncertainty and the final task outcome. EMPG amplifies updates for confident correct actions, penalizes confident errors, and attenuates updates from uncertain steps to stabilize exploration. We further introduce a bonus term for future clarity that encourages agents to find more predictable solution paths. Through comprehensive experiments on three challenging agent tasks, WebShop, ALFWorld, and Deep Search, we demonstrate that EMPG achieves substantial performance gains and significantly outperforms strong policy gradient baselines. Project page is at https://empgseed-seed.github.io/
【7】Constructing a Question-Answering Simulator through the Distillation of LLMs
标题：通过LLM的蒸馏构建志愿服务模拟器
链接：https://arxiv.org/abs/2509.09226
摘要 ：问答（QA）模拟器是一种模拟真实学生学习行为并预测他们对问题的回答正确性的模型。QA模拟器使教育推荐系统（ERS）能够在不与真实学生交互的情况下收集大量的训练数据，从而防止训练不足的ERS提出的有害建议破坏实际的学生学习。给定QA历史，有两类解决方案来预测正确性，进行仿真：（1）LLM自由方法，其应用传统的顺序模型将QA历史首先转换为向量表示，并基于表示进行预测;（2）基于LLM的方法，其利用LLM的领域知识和推理能力来增强预测。无LLM方法提供快速推理，但通常会产生次优性能。相比之下，大多数基于LLM的方法可以获得更好的结果，但代价是推理速度较慢，GPU内存消耗较高。在本文中，我们提出了一种名为LLM蒸馏基于模拟器（LDSim）的方法，该方法从LLM中提取领域知识和推理能力，以更好地辅助预测，从而提高仿真性能。大量的实验表明，我们的LDSim取得了很好的结果，在模拟任务和知识跟踪（KT）任务。我们的代码可在https://anonymous.4open.science/r/LDSim-05A9上公开获取。
摘要：The question-answering (QA) simulator is a model that mimics real student learning behaviors and predicts their correctness of their responses to questions. QA simulators enable educational recommender systems (ERS) to collect large amounts of training data without interacting with real students, thereby preventing harmful recommendations made by an undertrained ERS from undermining actual student learning. Given the QA history, there are two categories of solutions to predict the correctness, conducting the simulation: (1) LLM-free methods, which apply a traditional sequential model to transfer the QA history into a vector representation first, and make predictions based on the representation; (2) LLM-based methods, which leverage the domain knowledge and reasoning capability of LLM to enhence the prediction. LLM-free methods offer fast inference but generally yield suboptimal performance. In contrast, most LLM-based methods achieve better results, but at the cost of slower inference speed and higher GPU memory consumption. In this paper, we propose a method named LLM Distillation based Simulator (LDSim), which distills domain knowledge and reasoning capability from an LLM to better assist prediction, thereby improving simulation performance. Extensive experiments demonstrate that our LDSim achieves strong results on both the simulation task and the knowledge tracing (KT) task. Our code is publicly available at https://anonymous.4open.science/r/LDSim-05A9.
【8】Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models
标题：Sensitivity-LoRA：针对大型语言模型的低负载基于灵敏度的微调
链接：https://arxiv.org/abs/2509.09119
备注：15 pages
摘要：大型语言模型（LLM）已经改变了日常生活和科学研究。然而，使LLM从通用模型适应专门任务仍然具有挑战性，特别是在资源受限的环境中。低秩自适应（LoRA）是参数有效微调（PEFT）中的一种重要方法，通过使用低秩分解近似模型权重更新，已成为LLM的一种有前途的方法。然而，LoRA受限于其对每个增量矩阵的均匀秩（r）分配，并且旨在解决该问题的现有秩分配技术仍然计算效率低、复杂且不稳定，阻碍了实际应用。为了解决这些限制，我们提出了灵敏度LoRA，一个有效的微调方法，动态分配排名的权重矩阵的基础上，他们的全球和局部的敏感性。它利用损失函数的二阶导数（Hessian矩阵）来有效地捕获权重敏感性，从而以最小的计算开销实现最佳秩分配。我们的实验结果表明，灵敏度LoRA在不同的任务和基准测试中具有强大的有效性，效率和稳定性。
摘要：Large Language Models (LLMs) have transformed both everyday life and scientific research. However, adapting LLMs from general-purpose models to specialized tasks remains challenging, particularly in resource-constrained environments. Low-Rank Adaptation (LoRA), a prominent method within Parameter-Efficient Fine-Tuning (PEFT), has emerged as a promising approach to LLMs by approximating model weight updates using low-rank decomposition. However, LoRA is limited by its uniform rank ( r ) allocation to each incremental matrix, and existing rank allocation techniques aimed at addressing this issue remain computationally inefficient, complex, and unstable, hindering practical applications. To address these limitations, we propose Sensitivity-LoRA, an efficient fine-tuning method that dynamically allocates ranks to weight matrices based on both their global and local sensitivities. It leverages the second-order derivatives (Hessian Matrix) of the loss function to effectively capture weight sensitivity, enabling optimal rank allocation with minimal computational overhead. Our experimental results have demonstrated robust effectiveness, efficiency and stability of Sensitivity-LoRA across diverse tasks and benchmarks.
【9】Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M
标题：使用SFT和DPO提高LLM的安全性和帮助性：OPT-350 M的研究
链接：https://arxiv.org/abs/2509.09055
备注：17 pages, 3 figures. Code and dataset available at this https URL
摘要：本研究探讨对齐技术，监督微调（SFT），直接偏好优化（DPO），并结合SFT+DPO的方法，提高OPT-350 M语言模型的安全性和有用性的有效性。利用人类有益无害RLHF数据集，我们训练和评估四个模型：基础OPT 350 M，SFT模型，DPO模型，以及用SFT和DPO训练的模型。我们引入了三个关键的评估指标：无害率（HmR），帮助率（HpR）和组合对齐分数（CAS），所有这些都来自奖励模型的输出。结果表明，虽然SFT优于DPO，但组合的SFT+DPO模型在所有指标上都优于所有其他模型，表明这些技术的互补性。我们的研究结果还强调了噪声数据、有限的GPU资源和训练限制带来的挑战。这项研究提供了一个全面的观点，微调策略如何影响模型对齐，并提供了一个基础，在未来的工作更强大的对齐管道。
摘要：This research investigates the effectiveness of alignment techniques, Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and a combined SFT+DPO approach on improving the safety and helpfulness of the OPT-350M language model. Utilizing the Anthropic Helpful-Harmless RLHF dataset, we train and evaluate four models: the base OPT350M, an SFT model, a DPO model, and a model trained with both SFT and DPO. We introduce three key evaluation metrics: Harmlessness Rate (HmR), Helpfulness Rate (HpR), and a Combined Alignment Score (CAS), all derived from reward model outputs. The results show that while SFT outperforms DPO, The combined SFT+DPO model outperforms all others across all metrics, demonstrating the complementary nature of these techniques. Our findings also highlight challenges posed by noisy data, limited GPU resources, and training constraints. This study offers a comprehensive view of how fine-tuning strategies affect model alignment and provides a foundation for more robust alignment pipelines in future work.
【10】Open-sci-ref-0.01: open and reproducible reference baselines for language model and dataset comparison
标题：Open-sci-ref-0.01：用于语言模型和数据集比较的开放且可重复的参考基线
链接：https://arxiv.org/abs/2509.09009
备注：Model weights and intermediate checkpoints are available at \url{this https URL}; code for reproducing training, evaluation and raw experiments data at \url{this https URL}
摘要：我们引入了open-sci-ref，这是一系列密集的Transformer模型，它们在8个最近的开放参考数据集上被训练为多个模型（0.13 B到1.7 B参数）和令牌尺度（高达1 T）的研究基线。在各种标准化基准上评估模型，我们的训练运行集建立了参考点，使研究人员能够评估跨尺度和数据集的替代训练方法的合理性和质量。中间检查点允许比较和研究培训动态。已建立的参考基线允许通过其缩放趋势对培训程序进行比较，将其与共同的计算轴对齐。开放参考数据集的比较显示，NemoTron-CC HQ的训练始终优于其他参考数据集，其次是DCLM基线和FineWeb-Edu。除了中间培训检查点之外，该版本还包括日志、代码和下游评估，以简化复制、标准化比较并促进未来的研究。
摘要 ：We introduce open-sci-ref, a family of dense transformer models trained as research baselines across multiple model (0.13B to 1.7B parameters) and token scales (up to 1T) on 8 recent open reference datasets. Evaluating the models on various standardized benchmarks, our training runs set establishes reference points that enable researchers to assess the sanity and quality of alternative training approaches across scales and datasets. Intermediate checkpoints allow comparison and studying of the training dynamics. The established reference baselines allow training procedures to be compared through their scaling trends, aligning them on a common compute axis. Comparison of open reference datasets reveals that training on NemoTron-CC HQ consistently outperforms other reference datasets, followed by DCLM-baseline and FineWeb-Edu. In addition to intermediate training checkpoints, the release includes logs, code, and downstream evaluations to simplify reproduction, standardize comparison, and facilitate future research.
【11】Decentralising LLM Alignment: A Case for Context, Pluralism, and Participation
标题：分散LLM对齐：背景，多元化和参与的案例
链接：https://arxiv.org/abs/2509.08858
备注：Accepted at AIES 2025
摘要：大型语言模型（LLM）对齐方法被认为是ChatGPT等产品的商业成功，因为它们在引导LLM向用户友好的输出方面发挥了作用。然而，目前的对齐技术主要反映了一个狭窄的参考群体的规范性偏好，有效地将其价值观强加给广泛的用户基础。根据权力/知识关系的理论，这项工作认为，目前的调整做法集中控制知识生产和治理已经有影响力的机构。为了解决这一问题，我们建议通过三个特征：背景，多元化和参与分散对齐。此外，本文还通过将这些功能中的每一个都建立在具体的用例中，论证了在形成对齐实践时，描述使用环境的至关重要性。这项工作做出了以下贡献：（1）突出背景，多元化和参与分散对齐的作用;（2）提供具体的例子来说明这些策略;（3）展示与在不同的使用环境中应用对齐相关的细微差别要求。最终，本文将LLM对齐定位为抵抗认识不公正和民主进程侵蚀的潜在场所，同时承认这些策略本身不能取代更广泛的社会变革。
摘要：Large Language Models (LLMs) alignment methods have been credited with the commercial success of products like ChatGPT, given their role in steering LLMs towards user-friendly outputs. However, current alignment techniques predominantly mirror the normative preferences of a narrow reference group, effectively imposing their values on a wide user base. Drawing on theories of the power/knowledge nexus, this work argues that current alignment practices centralise control over knowledge production and governance within already influential institutions. To counter this, we propose decentralising alignment through three characteristics: context, pluralism, and participation. Furthermore, this paper demonstrates the critical importance of delineating the context-of-use when shaping alignment practices by grounding each of these features in concrete use cases. This work makes the following contributions: (1) highlighting the role of context, pluralism, and participation in decentralising alignment; (2) providing concrete examples to illustrate these strategies; and (3) demonstrating the nuanced requirements associated with applying alignment across different contexts of use. Ultimately, this paper positions LLM alignment as a potential site of resistance against epistemic injustice and the erosion of democratic processes, while acknowledging that these strategies alone cannot substitute for broader societal changes.
【12】Automated Unity Game Template Generation from GDDs via NLP and Multi-Modal LLMs
标题：通过NLP和多模式LLM从GDD自动生成Unity游戏模板
链接：https://arxiv.org/abs/2509.08847
摘要：本文提出了一种新的框架，通过使用自然语言处理（NLP）和多模态大型语言模型（LLM）将游戏设计文档（GDD）转换为功能性Unity游戏原型，自动生成游戏模板。我们介绍了一个端到端的系统，解析GDD，提取结构化的游戏规范，并合成Unity兼容的C#代码，实现设计文档中定义的核心机制，系统和架构。我们的方法将专门用于Unity代码生成的微调LLaMA-3模型与简化实现过程的自定义Unity集成包相结合。评估结果表明，与基线模型相比，我们的微调模型在编译成功，GDD遵守，最佳实践采用和代码模块化指标方面与最先进的LLM相比，实现了卓越的性能（4.8/5.0平均得分）。生成的模板在多个游戏类型中表现出对GDD规范的高度遵守。我们的系统有效地解决了AI辅助游戏开发中的关键差距，将LLM定位为简化从游戏设计到实现过渡的宝贵工具。
摘要：This paper presents a novel framework for automated game template generation by transforming Game Design Documents (GDDs) into functional Unity game prototypes using Natural Language Processing (NLP) and multi-modal Large Language Models (LLMs). We introduce an end-to-end system that parses GDDs, extracts structured game specifications, and synthesizes Unity-compatible C# code that implements the core mechanics, systems, and architecture defined in the design documentation. Our approach combines a fine-tuned LLaMA-3 model specialized for Unity code generation with a custom Unity integration package that streamlines the implementation process. Evaluation results demonstrate significant improvements over baseline models, with our fine-tuned model achieving superior performance (4.8/5.0 average score) compared to state-of-the-art LLMs across compilation success, GDD adherence, best practices adoption, and code modularity metrics. The generated templates demonstrate high adherence to GDD specifications across multiple game genres. Our system effectively addresses critical gaps in AI-assisted game development, positioning LLMs as valuable tools in streamlining the transition from game design to implementation.
Graph相关(图学习|图神经网络|图优化等)(7篇)
【1】Graph Alignment via Dual-Pass Spectral Encoding and Latent Space Communication
标题：通过双通频谱编码和潜在空间通信的图形对齐
链接：https://arxiv.org/abs/2509.09597
备注：23 pages
摘要：图分解-在多个图中识别对应节点的问题-是许多应用程序的基础。大多数现有的无监督方法将节点特征嵌入到潜在表示中，以实现交叉图比较，而无需地面实况对应。然而，这些方法受到两个关键限制：由于基于GNN的嵌入中的过度平滑而导致的节点独特性的退化，以及由结构噪声，特征异质性和训练不稳定性引起的图中潜在空间的不对齐，最终导致不可靠的节点对应。我们提出了一种新的图对齐框架，同时增强节点的独特性，并强制执行潜在空间的几何一致性。我们的方法引入了一个双通编码器，它结合了低通和高通频谱滤波器来生成结构感知和高度区分的嵌入。为了解决潜在的空间不对齐问题，我们引入了一个几何感知的功能映射模块，该模块可以学习图嵌入之间的双射和等距变换，确保不同表示之间的几何关系一致。在图基准上进行的大量实验表明，我们的方法始终优于现有的无监督对齐基线，对结构不一致和具有挑战性的对齐场景表现出卓越的鲁棒性。此外，使用不同的预训练模型对视觉语言基准进行的综合评估表明，我们的框架有效地推广了图域，实现了视觉和语言表示的无监督对齐。
摘要：Graph alignment-the problem of identifying corresponding nodes across multiple graphs-is fundamental to numerous applications. Most existing unsupervised methods embed node features into latent representations to enable cross-graph comparison without ground-truth correspondences. However, these methods suffer from two critical limitations: the degradation of node distinctiveness due to oversmoothing in GNN-based embeddings, and the misalignment of latent spaces across graphs caused by structural noise, feature heterogeneity, and training instability, ultimately leading to unreliable node correspondences. We propose a novel graph alignment framework that simultaneously enhances node distinctiveness and enforces geometric consistency across latent spaces. Our approach introduces a dual-pass encoder that combines low-pass and high-pass spectral filters to generate embeddings that are both structure-aware and highly discriminative. To address latent space misalignment, we incorporate a geometry-aware functional map module that learns bijective and isometric transformations between graph embeddings, ensuring consistent geometric relationships across different representations. Extensive experiments on graph benchmarks demonstrate that our method consistently outperforms existing unsupervised alignment baselines, exhibiting superior robustness to structural inconsistencies and challenging alignment scenarios. Additionally, comprehensive evaluation on vision-language benchmarks using diverse pretrained models shows that our framework effectively generalizes beyond graph domains, enabling unsupervised alignment of vision and language representations.
【2】CountTRuCoLa: Rule Confidence Learning for Temporal Knowledge Graph Forecasting
标题：CountTRuCoLa：用于时态知识图预测的规则置信度学习
链接：https://arxiv.org/abs/2509.09474
摘要：我们通过引入一种基于时间规则的完全可解释的方法来解决时间知识图（TKG）预测的任务。最近的工作提出了一个强有力的基线使用反复出现的事实的动机，我们的方法学习四个简单类型的规则与置信度函数，考虑了近度和频率。在九个数据集上进行评估，我们的方法匹配或超越了八个最先进的模型和两个基线的性能，同时提供了完全可解释的预测。
摘要：We address the task of temporal knowledge graph (TKG) forecasting by introducing a fully explainable method based on temporal rules. Motivated by recent work proposing a strong baseline using recurrent facts, our approach learns four simple types of rules with a confidence function that considers both recency and frequency. Evaluated on nine datasets, our method matches or surpasses the performance of eight state-of-the-art models and two baselines, while providing fully interpretable predictions.
【3】Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generation
标题：多条件分子生成的可组合分数图扩散模型
链接：https://arxiv.org/abs/2509.09451
摘要：可控分子图生成对于材料和药物发现是必不可少的，其中生成的分子必须满足不同的性质约束。虽然图扩散模型的最新进展提高了生成质量，但由于依赖于联合条件或连续松弛，其在多条件设置中的有效性仍然有限，这会损害保真度。为了解决这些限制，我们提出了基于组合分数的图扩散模型（CSGD），这是第一个通过具体分数将分数匹配扩展到离散图的模型，可以灵活和有原则地操纵条件指导。在此基础上，我们引入了两种基于分数的技术：可组合指导（CoG），它允许在采样期间对任意条件子集进行细粒度控制，以及概率校准（PC），它调整估计的转移概率以减轻训练测试的不匹配。四个分子数据集的实证结果表明，CSGD实现了最先进的性能，与现有方法相比，可控性平均提高了15.3%，同时保持了较高的有效性和分布保真度。我们的研究结果强调了基于分数的建模用于离散图生成的实际优势及其灵活、多属性分子设计的能力。
摘要：Controllable molecular graph generation is essential for material and drug discovery, where generated molecules must satisfy diverse property constraints. While recent advances in graph diffusion models have improved generation quality, their effectiveness in multi-conditional settings remains limited due to reliance on joint conditioning or continuous relaxations that compromise fidelity. To address these limitations, we propose Composable Score-based Graph Diffusion model (CSGD), the first model that extends score matching to discrete graphs via concrete scores, enabling flexible and principled manipulation of conditional guidance. Building on this foundation, we introduce two score-based techniques: Composable Guidance (CoG), which allows fine-grained control over arbitrary subsets of conditions during sampling, and Probability Calibration (PC), which adjusts estimated transition probabilities to mitigate train-test mismatches. Empirical results on four molecular datasets show that CSGD achieves state-of-the-art performance, with a 15.3% average improvement in controllability over prior methods, while maintaining high validity and distributional fidelity. Our findings highlight the practical advantages of score-based modeling for discrete graph generation and its capacity for flexible, multi-property molecular design.
【4】MoSE: Unveiling Structural Patterns in Graphs via Mixture of Subgraph Experts
标题：MSE：通过混合子图专家揭示图中的结构模式
链接：https://arxiv.org/abs/2509.09337
备注：16 pages, 11 figures
摘要：虽然图神经网络（GNN）在从图结构数据中学习方面取得了巨大成功，但它们对本地成对消息传递的依赖限制了它们捕获复杂高阶子图模式的能力。导致结构表现力不足。最近的努力试图通过将随机游走内核集成到GNN中来增强结构表达能力。然而，这些方法本质上是为图级任务设计的，这限制了它们对其他下游任务（如节点分类）的适用性。此外，它们的固定内核配置阻碍了模型在捕获不同子图结构方面的灵活性。为了解决这些局限性，本文提出了一种新的混合子图专家（MoSE）框架，用于在不同的图任务中进行灵活和富有表现力的基于子图的表示学习。具体而言，MoSE通过匿名遍历提取信息子图，并基于结构语义将其动态路由到专业专家，使模型能够捕获不同的子图模式，提高灵活性和可解释性。我们进一步提供了一个理论分析的MoSE的表现力内的子图Weisfeiler-Lehman（SWL）测试，证明它是更强大的SWL。大量的实验，以及学习的子图专家的可视化，表明MoSE不仅优于竞争基线，而且还提供了对模型学习的结构模式的可解释的见解。
摘要：While graph neural networks (GNNs) have achieved great success in learning from graph-structured data, their reliance on local, pairwise message passing restricts their ability to capture complex, high-order subgraph patterns. leading to insufficient structural expressiveness. Recent efforts have attempted to enhance structural expressiveness by integrating random walk kernels into GNNs. However, these methods are inherently designed for graph-level tasks, which limits their applicability to other downstream tasks such as node classification. Moreover, their fixed kernel configurations hinder the model's flexibility in capturing diverse subgraph structures. To address these limitations, this paper proposes a novel Mixture of Subgraph Experts (MoSE) framework for flexible and expressive subgraph-based representation learning across diverse graph tasks. Specifically, MoSE extracts informative subgraphs via anonymous walks and dynamically routes them to specialized experts based on structural semantics, enabling the model to capture diverse subgraph patterns with improved flexibility and interpretability. We further provide a theoretical analysis of MoSE's expressivity within the Subgraph Weisfeiler-Lehman (SWL) Test, proving that it is more powerful than SWL. Extensive experiments, together with visualizations of learned subgraph experts, demonstrate that MoSE not only outperforms competitive baselines but also provides interpretable insights into structural patterns learned by the model.
【5】Vejde: A Framework for Inductive Deep Reinforcement Learning Based on Factor Graph Color Refinement
标题：Vejde：基于因子图颜色细化的归纳深度强化学习框架
链接：https://arxiv.org/abs/2509.09219
摘要：我们提出并评估Vejde;一个框架，它结合了数据抽象，图形神经网络和强化学习，为具有丰富结构化状态（如对象类和关系）的决策问题产生归纳策略函数。MDP状态表示为关于实体的事实的数据库，Vejde将每个状态转换为二分图，通过神经消息传递将其映射到潜在状态。状态和动作的分解表示允许Vejde代理处理不同大小和结构的问题。我们测试了Vejde代理在Rounds中定义的8个问题域，每个问题域有10个问题实例，其中使用监督学习和强化学习来训练策略。为了测试策略泛化，我们将问题实例分为两组，一组用于训练，另一组仅用于测试。Vejde代理的未见过的实例的测试结果进行了比较，MLP代理在每个问题的情况下，以及在线规划算法Prost训练。我们的结果表明，Vejde策略平均推广到测试实例，而得分没有显着损失。此外，归纳代理收到的分数看不见的测试实例，平均接近的实例特定的MLP代理。
摘要：We present and evaluate Vejde; a framework which combines data abstraction, graph neural networks and reinforcement learning to produce inductive policy functions for decision problems with richly structured states, such as object classes and relations. MDP states are represented as data bases of facts about entities, and Vejde converts each state to a bipartite graph, which is mapped to latent states through neural message passing. The factored representation of both states and actions allows Vejde agents to handle problems of varying size and structure. We tested Vejde agents on eight problem domains defined in RDDL, with ten problem instances each, where policies were trained using both supervised and reinforcement learning. To test policy generalization, we separate problem instances in two sets, one for training and the other solely for testing. Test results on unseen instances for the Vejde agents were compared to MLP agents trained on each problem instance, as well as the online planning algorithm Prost. Our results show that Vejde policies in average generalize to the test instances without a significant loss in score. Additionally, the inductive agents received scores on unseen test instances that on average were close to the instance-specific MLP agents.
【6】CryptGNN: Enabling Secure Inference for Graph Neural Networks
标题：CryptGNN：为图神经网络实现安全推理
链接：https://arxiv.org/abs/2509.09107
摘要：我们提出了CryptGNN，这是一种安全有效的推理解决方案，适用于云中的第三方图神经网络（GNN）模型，客户端可以将其作为ML即服务（MLaaS）访问。CryptGNN的主要新颖之处在于它的安全消息传递和特征转换层使用分布式安全多方计算（SMPC）技术。CryptGNN保护客户端的输入数据和图形结构不受云提供商和第三方模型所有者的影响，并保护模型参数不受云提供商和客户端的影响。CryptGNN可以与任何数量的SMPC方一起工作，不需要可信的服务器，并且即使云中的P-1方勾结，也可以证明是安全的。理论分析和实验验证了CryptGNN的安全性和有效性。
摘要：We present CryptGNN, a secure and effective inference solution for third-party graph neural network (GNN) models in the cloud, which are accessed by clients as ML as a service (MLaaS). The main novelty of CryptGNN is its secure message passing and feature transformation layers using distributed secure multi-party computation (SMPC) techniques. CryptGNN protects the client's input data and graph structure from the cloud provider and the third-party model owner, and it protects the model parameters from the cloud provider and the clients. CryptGNN works with any number of SMPC parties, does not require a trusted server, and is provably secure even if P-1 out of P parties in the cloud collude. Theoretical analysis and empirical experiments demonstrate the security and efficiency of CryptGNN.
【7】The Role of Community Detection Methods in Performance Variations of Graph Mining Tasks
标题：社区检测方法在图挖掘任务性能变化中的作用
链接：https://arxiv.org/abs/2509.09045
摘要：在现实世界中，大型图表示复杂系统中实体之间的关系。挖掘这些通常包含数百万个节点和边的大型图有助于揭示结构模式和有意义的见解。将大型图划分为较小的子图，通过揭示局部信息来促进复杂系统分析。社区检测基于统计方法和使用各种优化技术的机器学习模型来提取图的集群或社区。基于结构的社区检测方法更适合应用于图，因为它们不依赖于丰富的节点或边属性信息。从这些社区衍生的特征可以改进下游图挖掘任务，例如链接预测和节点分类。在现实世界的应用中，我们经常缺乏真实的社区信息。此外，既没有一个普遍接受的社区检测金标准，也没有一个单一的方法，在不同的应用程序中始终是最佳的。在许多情况下，不清楚从业人员如何选择社区检测方法，并且通常在没有明确考虑其对下游任务的潜在影响的情况下做出选择。在这项研究中，我们调查社区检测算法的选择是否显着影响下游应用程序的性能。我们提出了一个框架，能够集成各种社区检测方法，系统地评估其对下游任务结果的影响。我们的比较分析表明，特定的社区检测算法在某些应用程序中产生优越的结果，突出方法选择大大影响性能。
摘要：In real-world scenarios, large graphs represent relationships among entities in complex systems. Mining these large graphs often containing millions of nodes and edges helps uncover structural patterns and meaningful insights. Dividing a large graph into smaller subgraphs facilitates complex system analysis by revealing local information. Community detection extracts clusters or communities of graphs based on statistical methods and machine learning models using various optimization techniques. Structure based community detection methods are more suitable for applying to graphs because they do not rely heavily on rich node or edge attribute information. The features derived from these communities can improve downstream graph mining tasks, such as link prediction and node classification. In real-world applications, we often lack ground truth community information. Additionally, there is neither a universally accepted gold standard for community detection nor a single method that is consistently optimal across diverse applications. In many cases, it is unclear how practitioners select community detection methods, and choices are often made without explicitly considering their potential impact on downstream tasks. In this study, we investigate whether the choice of community detection algorithm significantly influences the performance of downstream applications. We propose a framework capable of integrating various community detection methods to systematically evaluate their effects on downstream task outcomes. Our comparative analysis reveals that specific community detection algorithms yield superior results in certain applications, highlighting that method selection substantially affects performance.
Transformer(3篇)
【1】AquaCast: Urban Water Dynamics Forecasting with Precipitation-Informed Multi-Input Transformer
标题：AcquaCast：利用监测多输入Transformer进行城市水动态预测
链接：https://arxiv.org/abs/2509.09458
备注：This work has been submitted to Journal of Hydrology, Elsevier, and a preprint version is also available at SSRN https://doi.org/10.2139/ssrn.5399833
摘要：这项工作通过开发一个多输入、多输出的深度学习模型来解决预测城市水动态的挑战，该模型包含内生变量（例如，水位或流量）和外源因素（例如，降水历史和预报报告）。与传统的预测，所提出的模型，AquaCast，捕获所有输入的变量和时间的依赖关系，而预测只集中在内生变量。外部输入通过嵌入层进行融合，消除了预测它们的需要，使模型能够更有效地关注它们的短期影响。我们评估了我们的方法在LausanneCity数据集，其中包括从四个城市排水传感器的测量，并证明了最先进的性能时，只使用内生变量。通过纳入外生变量和预测报告，业绩也得到改善。为了评估泛化和可扩展性，我们还在三个大规模的合成数据集上测试了该模型，这些数据集是由MeteoSwiss记录、Lorenz Attractor模型和Random Fields模型生成的，每个模型都代表了100个节点上不同级别的时间复杂度。结果证实，我们的模型始终优于现有的基线，并在真实和合成数据集上保持稳健和准确的预测。
摘要：This work addresses the challenge of forecasting urban water dynamics by developing a multi-input, multi-output deep learning model that incorporates both endogenous variables (e.g., water height or discharge) and exogenous factors (e.g., precipitation history and forecast reports). Unlike conventional forecasting, the proposed model, AquaCast, captures both inter-variable and temporal dependencies across all inputs, while focusing forecast solely on endogenous variables. Exogenous inputs are fused via an embedding layer, eliminating the need to forecast them and enabling the model to attend to their short-term influences more effectively. We evaluate our approach on the LausanneCity dataset, which includes measurements from four urban drainage sensors, and demonstrate state-of-the-art performance when using only endogenous variables. Performance also improves with the inclusion of exogenous variables and forecast reports. To assess generalization and scalability, we additionally test the model on three large-scale synthesized datasets, generated from MeteoSwiss records, the Lorenz Attractors model, and the Random Fields model, each representing a different level of temporal complexity across 100 nodes. The results confirm that our model consistently outperforms existing baselines and maintains a robust and accurate forecast across both real and synthetic datasets.
【2】Unsupervised Multi-Attention Meta Transformer for Rotating Machinery Fault Diagnosis
标题：用于旋转机械故障诊断的无监督多关注Meta Transformer
链接：https://arxiv.org/abs/2509.09251
摘要 ：旋转机械设备的智能故障诊断通常需要大量的标记样本数据。然而，在实际的工业应用中，获取足够的数据在时间和成本方面既具有挑战性又昂贵。此外，具有不同独特机械特性的不同类型的旋转机械设备需要针对每种情况单独训练诊断模型。为了解决实际工程应用中故障样本有限和预测模型缺乏可推广性的挑战，我们提出了一种用于Few-Shot无监督旋转机械故障诊断（MMT-FD）的多注意力Meta Transformer方法。该框架从未标记的数据中提取潜在的故障表示，并展示了强大的泛化能力，使其适用于诊断各种类型的机械设备的故障。MMT-FD框架集成了时频域编码器和元学习泛化模型。时频域编码器预测通过时频域中的随机增强生成的状态表示。然后，这些增强的数据被馈送到元学习网络中进行分类和泛化训练，然后使用有限数量的标记数据进行微调。该模型使用少量的对比学习迭代进行迭代优化，从而提高了效率。为了验证该框架，我们进行了实验的轴承故障数据集和转子测试台架数据。结果表明，MMT-FD模型仅用1%的标记样本数据就能达到99%的故障诊断准确率，具有较强的泛化能力。
摘要：The intelligent fault diagnosis of rotating mechanical equipment usually requires a large amount of labeled sample data. However, in practical industrial applications, acquiring enough data is both challenging and expensive in terms of time and cost. Moreover, different types of rotating mechanical equipment with different unique mechanical properties, require separate training of diagnostic models for each case. To address the challenges of limited fault samples and the lack of generalizability in prediction models for practical engineering applications, we propose a Multi-Attention Meta Transformer method for few-shot unsupervised rotating machinery fault diagnosis (MMT-FD). This framework extracts potential fault representations from unlabeled data and demonstrates strong generalization capabilities, making it suitable for diagnosing faults across various types of mechanical equipment. The MMT-FD framework integrates a time-frequency domain encoder and a meta-learning generalization model. The time-frequency domain encoder predicts status representations generated through random augmentations in the time-frequency domain. These enhanced data are then fed into a meta-learning network for classification and generalization training, followed by fine-tuning using a limited amount of labeled data. The model is iteratively optimized using a small number of contrastive learning iterations, resulting in high efficiency. To validate the framework, we conducted experiments on a bearing fault dataset and rotor test bench data. The results demonstrate that the MMT-FD model achieves 99\% fault diagnosis accuracy with only 1\% of labeled sample data, exhibiting robust generalization capabilities.
【3】Adaptive Pareto-Optimal Token Merging for Edge Transformer Models in Semantic Communication
标题：语义通信中边缘Transformer模型的自适应帕累托最优令牌合并
链接：https://arxiv.org/abs/2509.09168
备注：To appear in IEEE Globecom 2025
摘要：大规模的Transformer模型已经成为语义通信系统的强大工具，使边缘设备能够提取丰富的表示，以便在嘈杂的无线信道上进行鲁棒的推理。然而，它们大量的计算需求仍然是资源受限的6G网络中实际部署的主要障碍。在本文中，我们提出了一个免训练的框架，用于在预训练的Vision Transformers中进行自适应令牌合并，以共同减少推理时间和传输资源的使用。我们制定了每层合并比例的选择作为一个多目标优化问题，以平衡精度和计算成本。我们采用高斯过程为基础的贝叶斯优化构建一个帕累托前沿的最佳配置，使灵活的运行时适应动态应用程序的要求和信道条件。大量的实验表明，我们的方法始终优于其他基线，并实现了浮点运算的显着减少，同时保持竞争力的准确性在广泛的信噪比（SNR）条件。额外的结果突出了自适应政策的有效性，调整合并的侵略性，以响应信道质量，提供了一个实用的机制来权衡延迟和语义保真度的需求。这些发现为在未来的边缘智能系统中部署基于transformer的语义通信建立了一种可扩展且高效的方法。
摘要：Large-scale transformer models have emerged as a powerful tool for semantic communication systems, enabling edge devices to extract rich representations for robust inference across noisy wireless channels. However, their substantial computational demands remain a major barrier to practical deployment in resource-constrained 6G networks. In this paper, we present a training-free framework for adaptive token merging in pretrained vision transformers to jointly reduce inference time and transmission resource usage. We formulate the selection of per-layer merging proportions as a multi-objective optimization problem to balance accuracy and computational cost. We employ Gaussian process-based Bayesian optimization to construct a Pareto frontier of optimal configurations, enabling flexible runtime adaptation to dynamic application requirements and channel conditions. Extensive experiments demonstrate that our method consistently outperforms other baselines and achieves significant reductions in floating-point operations while maintaining competitive accuracy across a wide range of signal-to-noise ratio (SNR) conditions. Additional results highlight the effectiveness of adaptive policies that adjust merging aggressiveness in response to channel quality, providing a practical mechanism to trade off latency and semantic fidelity on demand. These findings establish a scalable and efficient approach for deploying transformer-based semantic communication in future edge intelligence systems.
GAN|对抗|攻击|生成相关(2篇)
【1】Retrieval-Augmented Generation for Reliable Interpretation of Radio Regulations
标题：可靠解释无线电法规的检索增强生成
链接：https://arxiv.org/abs/2509.09651
摘要：我们研究无线电法规领域的问题回答，这是一个法律敏感和高风险的领域。我们提出了一个电信特定的检索增强生成（RAG）管道，并介绍，据我们所知，第一个多项选择的评价集，这个领域，从权威来源使用自动过滤和人工验证。为了评估检索质量，我们定义了一个特定于域的检索指标，根据该指标，检索器的准确率约为97%。除了检索之外，我们的方法还始终如一地提高了所有测试模型的生成精度。特别是，虽然在没有结构化检索的情况下天真地插入文档只能为GPT-4 o带来边际收益（不到1%），但应用我们的管道可以带来近12%的相对改善。这些发现表明，精心定位的基础为监管问题解答提供了简单而强大的基线和有效的特定于领域的解决方案。所有代码和评估脚本，以及我们派生的问答数据集，都可以在https://github.com/Zakaria010/Radio-RAG上找到。
摘要：We study question answering in the domain of radio regulations, a legally sensitive and high-stakes area. We propose a telecom-specific Retrieval-Augmented Generation (RAG) pipeline and introduce, to our knowledge, the first multiple-choice evaluation set for this domain, constructed from authoritative sources using automated filtering and human validation. To assess retrieval quality, we define a domain-specific retrieval metric, under which our retriever achieves approximately 97% accuracy. Beyond retrieval, our approach consistently improves generation accuracy across all tested models. In particular, while naively inserting documents without structured retrieval yields only marginal gains for GPT-4o (less than 1%), applying our pipeline results in nearly a 12% relative improvement. These findings demonstrate that carefully targeted grounding provides a simple yet strong baseline and an effective domain-specific solution for regulatory question answering. All code and evaluation scripts, along with our derived question-answer dataset, are available at https://github.com/Zakaria010/Radio-RAG.
【2】Boosting Embodied AI Agents through Perception-Generation Disaggregation and Asynchronous Pipeline Execution
标题：通过感知生成分解和同步管道执行来提升预定的人工智能代理
链接：https://arxiv.org/abs/2509.09560
摘要：人工智能系统在动态环境中运行，需要无缝集成感知和生成模块，以处理高频输入和输出需求。传统的顺序计算模式虽然在确保准确性方面有效，但在实现现实世界应用程序所需的“思考”频率方面面临着重大限制。在这项工作中，我们提出了Auras，一个算法系统协同设计的推理框架，以优化体现AI代理的推理频率。Auras将感知和生成分解，并为它们提供受控的流水线并行性，以实现高而稳定的吞吐量。面对并行性增加时出现的数据陈旧问题，Auras为感知和生成建立了一个公共上下文，从而保证了具体代理的准确性。实验结果表明，Auras平均将吞吐量提高了2.54倍，同时达到了原始准确率的102.7%，证明了其在克服顺序计算约束和提供高吞吐量方面的有效性。
摘要 ：Embodied AI systems operate in dynamic environments, requiring seamless integration of perception and generation modules to process high-frequency input and output demands. Traditional sequential computation patterns, while effective in ensuring accuracy, face significant limitations in achieving the necessary "thinking" frequency for real-world applications. In this work, we present Auras, an algorithm-system co-designed inference framework to optimize the inference frequency of embodied AI agents. Auras disaggregates the perception and generation and provides controlled pipeline parallelism for them to achieve high and stable throughput. Faced with the data staleness problem that appears when the parallelism is increased, Auras establishes a public context for perception and generation to share, thereby promising the accuracy of embodied agents. Experimental results show that Auras improves throughput by 2.54x on average while achieving 102.7% of the original accuracy, demonstrating its efficacy in overcoming the constraints of sequential computation and providing high throughput.
半/弱/无/有监督|不确定性|主动学习(4篇)
【1】Semantic Concentration for Self-Supervised Dense Representations Learning
标题：自我监督密集表示学习的语义集中
链接：https://arxiv.org/abs/2509.09429
摘要：图像级自监督学习（SSL）的最新进展已经取得了重大进展，但学习补丁的密集表示仍然具有挑战性。主流方法会遇到过度分散现象，即来自相同实例/类别的补丁分散，从而损害密集任务的下游性能。这项工作表明，图像级SSL通过涉及隐式语义集中来避免过度分散。具体来说，非严格的空间对齐确保了实例内的一致性，而共享模式，即，输入空间中类内实例的相似部分，确保图像间的一致性。不幸的是，这些方法是不可行的密集SSL由于其空间敏感性和复杂的场景为中心的数据。这些观察促使我们探索密集SSL的显式语义集中。首先，为了打破严格的空间对齐，我们提出了提取补丁对应。面对噪声和不平衡的伪标签，我们提出了一个噪声容忍的排名损失。其核心思想是将平均精度（AP）损失扩展到连续目标，从而使其决策不可知和自适应聚焦特性防止学生模型被误导。其次，为了区分复杂场景中的共享模式，我们提出了对象感知的过滤器来将输出空间映射到基于对象的空间。具体来说，补丁表示通过交叉注意的对象的可学习的原型。最后但并非最不重要的是，跨各种任务的实证研究充分支持我们的方法的有效性。代码可在https://github.com/KID-7391/CoTAP中找到。
摘要：Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods encounter an over-dispersion phenomenon that patches from the same instance/category scatter, harming downstream performance on dense tasks. This work reveals that image-level SSL avoids over-dispersion by involving implicit semantic concentration. Specifically, the non-strict spatial alignment ensures intra-instance consistency, while shared patterns, i.e., similar parts of within-class instances in the input space, ensure inter-image consistency. Unfortunately, these approaches are infeasible for dense SSL due to their spatial sensitivity and complicated scene-centric data. These observations motivate us to explore explicit semantic concentration for dense SSL. First, to break the strict spatial alignment, we propose to distill the patch correspondences. Facing noisy and imbalanced pseudo labels, we propose a noise-tolerant ranking loss. The core idea is extending the Average Precision (AP) loss to continuous targets, such that its decision-agnostic and adaptive focusing properties prevent the student model from being misled. Second, to discriminate the shared patterns from complicated scenes, we propose the object-aware filter to map the output space to an object-based space. Specifically, patches are represented by learnable prototypes of objects via cross-attention. Last but not least, empirical studies across various tasks soundly support the effectiveness of our method. Code is available in https://github.com/KID-7391/CoTAP.
【2】Active Learning and Explainable AI for Multi-Objective Optimization of Spin Coated Polymers
标题：主动学习和可解释人工智能用于旋转涂层聚合物的多目标优化
链接：https://arxiv.org/abs/2509.08988
备注：8 pages, 7 figures, Presented at 2025 AAAI Spring Symposium Series
摘要：旋涂聚合物薄膜以获得特定的力学性能本质上是一个多目标优化问题。我们提出了一个框架，该框架将主动帕累托前沿学习算法（PyePAL）与可视化和可解释的AI技术相结合，以优化处理参数。PyePAL使用高斯过程模型从设计变量（旋转速度、稀释度和聚合物混合物）预测目标值（硬度和弹性），指导样品的自适应选择朝向设计空间的有希望区域。为了实现对高维设计空间的可解释的见解，我们利用UMAP（均匀流形近似和投影）对帕累托前沿探索进行二维可视化。此外，我们将模糊语言摘要，翻译成语言语句的过程参数和性能目标之间的学习关系，从而提高了可解释性和理解的优化结果。实验结果表明，我们的方法有效地识别有前途的聚合物设计，而视觉和语言的解释，促进专家驱动的分析和知识发现。
摘要：Spin coating polymer thin films to achieve specific mechanical properties is inherently a multi-objective optimization problem. We present a framework that integrates an active Pareto front learning algorithm (PyePAL) with visualization and explainable AI techniques to optimize processing parameters. PyePAL uses Gaussian process models to predict objective values (hardness and elasticity) from the design variables (spin speed, dilution, and polymer mixture), guiding the adaptive selection of samples toward promising regions of the design space. To enable interpretable insights into the high-dimensional design space, we utilize UMAP (Uniform Manifold Approximation and Projection) for two-dimensional visualization of the Pareto front exploration. Additionally, we incorporate fuzzy linguistic summaries, which translate the learned relationships between process parameters and performance objectives into linguistic statements, thus enhancing the explainability and understanding of the optimization results. Experimental results demonstrate that our method efficiently identifies promising polymer designs, while the visual and linguistic explanations facilitate expert-driven analysis and knowledge discovery.
【3】Group Distributionally Robust Machine Learning under Group Level Distributional Uncertainty
标题：群体级分布不确定性下的群体分布鲁棒机器学习
链接：https://arxiv.org/abs/2509.08942
摘要：机器学习（ML）模型的性能关键取决于训练数据的质量和代表性。在具有多个异构数据生成源的应用中，标准ML方法通常会学习到虚假的相关性，这些相关性平均表现良好，但会降低非典型或代表性不足的群体的性能。先前的工作通过优化最差组性能来解决这个问题。然而，这些方法通常假设每个组的基础数据分布可以使用训练数据准确估计，这是在嘈杂，非平稳和不断变化的环境中经常违反的条件。在这项工作中，我们提出了一种新的框架，依赖于基于Wasserstein的分布鲁棒优化（DRO），以考虑每个组内的分布不确定性，同时保持提高最差组性能的目标。我们开发了一个梯度下降上升算法来解决建议的DRO问题，并提供收敛结果。最后，我们验证了我们的方法对现实世界的数据的有效性。
摘要：The performance of machine learning (ML) models critically depends on the quality and representativeness of the training data. In applications with multiple heterogeneous data generating sources, standard ML methods often learn spurious correlations that perform well on average but degrade performance for atypical or underrepresented groups. Prior work addresses this issue by optimizing the worst-group performance. However, these approaches typically assume that the underlying data distributions for each group can be accurately estimated using the training data, a condition that is frequently violated in noisy, non-stationary, and evolving environments. In this work, we propose a novel framework that relies on Wasserstein-based distributionally robust optimization (DRO) to account for the distributional uncertainty within each group, while simultaneously preserving the objective of improving the worst-group performance. We develop a gradient descent-ascent algorithm to solve the proposed DRO problem and provide convergence results. Finally, we validate the effectiveness of our method on real-world data.
【4】Uncertainty Estimation using Variance-Gated Distributions
标题：使用方差门控分布的不确定性估计
链接：https://arxiv.org/abs/2509.08846
摘要：从神经网络中评估每个样本的不确定性量化对于涉及高风险应用的决策是必不可少的。一种常见的方法是使用贝叶斯或近似模型的预测分布，并将相应的预测不确定性分解为认知（模型相关）和任意（数据相关）分量。然而，添加剂分解最近受到质疑。在这项工作中，我们提出了一个直观的框架，不确定性估计和分解的基础上，在不同的模型预测类概率分布的信噪比。我们引入了一个方差选通的措施，规模预测的置信因子来自合奏。我们用这种方法来讨论委员会机器多样性崩溃的存在。
摘要：Evaluation of per-sample uncertainty quantification from neural networks is essential for decision-making involving high-risk applications. A common approach is to use the predictive distribution from Bayesian or approximation models and decompose the corresponding predictive uncertainty into epistemic (model-related) and aleatoric (data-related) components. However, additive decomposition has recently been questioned. In this work, we propose an intuitive framework for uncertainty estimation and decomposition based on the signal-to-noise ratio of class probability distributions across different model predictions. We introduce a variance-gated measure that scales predictions by a confidence factor derived from ensembles. We use this measure to discuss the existence of a collapse in the diversity of committee machines.
迁移|Zero/Few/One-Shot|自适应(5篇)
【1】Feasibility-Guided Fair Adaptive Offline Reinforcement Learning for Medicaid Care Management
标题：用于医疗补助护理管理的公平自适应离线强化学习
链接：https://arxiv.org/abs/2509.09655
备注：12 pages, 5 figures, 3 tables
摘要：我们引入了脆弱性引导的公平自适应强化学习（FG-FARL），这是一种离线RL过程，可以校准每组安全阈值以减少伤害，同时在受保护的子组中均衡所选的公平目标（覆盖或伤害）。使用来自医疗补助人口健康管理计划的去识别纵向轨迹，我们评估了FG-FARL对行为克隆（BC）和HACO（混合自适应适形离线RL;全球适形安全基线）的影响。我们报告了具有bootstrap 95%置信区间的政策外价值估计值和具有p值的亚组差异分析。FG-FARL实现了与基线相当的价值，同时改善了公平性指标，展示了一条通往更安全、更公平的决策支持的实用途径。
摘要：We introduce Feasibility-Guided Fair Adaptive Reinforcement Learning (FG-FARL), an offline RL procedure that calibrates per-group safety thresholds to reduce harm while equalizing a chosen fairness target (coverage or harm) across protected subgroups. Using de-identified longitudinal trajectories from a Medicaid population health management program, we evaluate FG-FARL against behavior cloning (BC) and HACO (Hybrid Adaptive Conformal Offline RL; a global conformal safety baseline). We report off-policy value estimates with bootstrap 95% confidence intervals and subgroup disparity analyses with p-values. FG-FARL achieves comparable value to baselines while improving fairness metrics, demonstrating a practical path to safer and more equitable decision support.
【2】Cough Classification using Few-Shot Learning
标题：使用Few-shot学习的咳嗽分类
链接：https://arxiv.org/abs/2509.09515
备注：8 pages 8 images Has been accepted in Pervasive Health 2025
摘要：本文研究了Few-Shot学习对呼吸声分类的有效性，重点是COVID-19、流感和健康状况的咳嗽检测。我们利用具有咳嗽声音的频谱图表示的原型网络来解决有限的标记数据的挑战。我们的研究评估了Few-Shot学习是否可以使模型在使用显著更少的训练样本的情况下实现与传统深度学习方法相当的性能。此外，我们比较了多类和二进制分类模型，以评估多类模型是否可以执行二进制模型。实验结果表明，Few-Shot学习模型可以达到有竞争力的准确性。我们的模型在多类分类中达到了74.87%的准确率，每个类只有15个支持示例，而二进制分类在所有类对中达到了70%以上的准确率。类别分析显示流感是最可区分的类别，健康是最具挑战性的类别。统计检验（配对t检验p = 0.149，Wilcoxon p = 0.125）表明二元和多类模型之间没有显著的性能差异，支持在这种情况下多类分类的可行性。这些结果突出了在医学诊断中应用Few-Shot学习的可行性，特别是当大型标记数据集不可用时。
摘要：This paper investigates the effectiveness of few-shot learning for respiratory sound classification, focusing on coughbased detection of COVID-19, Flu, and healthy conditions. We leverage Prototypical Networks with spectrogram representations of cough sounds to address the challenge of limited labeled data. Our study evaluates whether few-shot learning can enable models to achieve performance comparable to traditional deep learning approaches while using significantly fewer training samples. Additionally, we compare multi-class and binary classification models to assess whether multi-class models can perform comparably to their binary counterparts. Experimental findings show that few-shot learning models can achieve competitive accuracy. Our model attains 74.87% accuracy in multi-class classification with only 15 support examples per class, while binary classification achieves over 70% accuracy across all class pairs. Class-wise analysis reveals Flu as the most distinguishable class, and Healthy as the most challenging. Statistical tests (paired t-test p = 0.149, Wilcoxon p = 0.125) indicate no significant performance difference between binary and multiclass models, supporting the viability of multi-class classification in this setting. These results highlight the feasibility of applying few-shot learning in medical diagnostics, particularly when large labeled datasets are unavailable.
【3】Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment
标题：探索跨领域预训练以进行Few-Shot手术技能评估
链接：https://arxiv.org/abs/2509.09327
备注：Accepted at MICCAI 2025 DEMI Workshop
摘要：自动手术技能评估（SSA）是手术计算机视觉的核心任务。由于技能注释的稀缺性，开发强大的SSA模型具有挑战性，这些注释的生成非常耗时，并且需要专家共识。Few-Shot learning（FSL）提供了一种可扩展的替代方案，使模型开发具有最小的监督，尽管其成功关键取决于有效的预训练。虽然广泛研究了几个手术下游任务，但在SSA中，预训练在很大程度上仍未被探索。在这项工作中，我们制定SSA作为一个Few-Shot任务，并研究如何自我监督的预训练策略影响下游Few-Shot SSA的性能。我们用技术技能的客观结构化评估（OSATS）分数注释了一个公开的机器人手术数据集，并在三个Few-Shot设置中评估了各种预训练源。我们量化了域相似性，并分析了域差距和将特定于过程的数据纳入预训练如何影响可移植性。我们的研究结果表明，小但领域相关的数据集可以优于大规模，不太对齐的数据集，在1次，2次和5次拍摄设置中分别达到60.16%，66.03%和73.65%的准确率。此外，将特定于过程的数据与领域相关的外部数据集结合到预训练中，可以显著提高下游性能，准确率平均提高+1.22%，F1得分平均提高+2.28%;然而，对不太相似但规模较大的源应用相同的策略反而会导致性能下降。代码和模型可在https://github.com/anastadimi/ssa-fsl上获得。
摘要 ：Automated surgical skill assessment (SSA) is a central task in surgical computer vision. Developing robust SSA models is challenging due to the scarcity of skill annotations, which are time-consuming to produce and require expert consensus. Few-shot learning (FSL) offers a scalable alternative enabling model development with minimal supervision, though its success critically depends on effective pre-training. While widely studied for several surgical downstream tasks, pre-training has remained largely unexplored in SSA. In this work, we formulate SSA as a few-shot task and investigate how self-supervised pre-training strategies affect downstream few-shot SSA performance. We annotate a publicly available robotic surgery dataset with Objective Structured Assessment of Technical Skill (OSATS) scores, and evaluate various pre-training sources across three few-shot settings. We quantify domain similarity and analyze how domain gap and the inclusion of procedure-specific data into pre-training influence transferability. Our results show that small but domain-relevant datasets can outperform large scale, less aligned ones, achieving accuracies of 60.16%, 66.03%, and 73.65% in the 1-, 2-, and 5-shot settings, respectively. Moreover, incorporating procedure-specific data into pre-training with a domain-relevant external dataset significantly boosts downstream performance, with an average gain of +1.22% in accuracy and +2.28% in F1-score; however, applying the same strategy with less similar but large-scale sources can instead lead to performance degradation. Code and models are available at https://github.com/anastadimi/ssa-fsl.
【4】Representation-Aware Distributionally Robust Optimization: A Knowledge Transfer Framework
标题：感知表示的分布鲁棒优化：知识转移框架
链接：https://arxiv.org/abs/2509.09371
摘要：我们提出了代表意识分布鲁棒估计（READ），一种新的框架Wasserstein分布鲁棒学习，占预测表示时，防止分布的变化。与同等对待所有特征扰动的经典方法不同，READ将多维对齐参数嵌入到运输成本中，允许模型以差异方式阻止与信息表示相关的方向上的扰动。这产生了对特征变化的鲁棒性，同时保持不变的结构。我们的第一个贡献是一个理论基础：我们表明，Wasserstein分布鲁棒目标的线性回归和二进制分类的正则化，从而提供了易于处理的READ和统一的DRO镜头下的正则化估计的广泛的类。其次，我们采用了一个原则性的程序，选择Wasserstein半径使用强大的Wasserstein轮廓推断技术。这进一步使得能够为具有不同几何特征的模型参数构建有效的、感知表示的置信区域。最后，我们分析了几何形状的READ估计的对齐参数的变化，并提出了一个优化算法来估计投影到这个解决方案的表面上的全局最优。该过程在同样稳健的估计中进行选择，同时最佳地构建表示结构。最后，我们通过广泛的模拟和真实世界的研究证明了我们的框架的有效性，提供了一个强大的鲁棒估计接地学习表示。
摘要：We propose REpresentation-Aware Distributionally Robust Estimation (READ), a novel framework for Wasserstein distributionally robust learning that accounts for predictive representations when guarding against distributional shifts. Unlike classical approaches that treat all feature perturbations equally, READ embeds a multidimensional alignment parameter into the transport cost, allowing the model to differentially discourage perturbations along directions associated with informative representations. This yields robustness to feature variation while preserving invariant structure. Our first contribution is a theoretical foundation: we show that seminorm regularizations for linear regression and binary classification arise as Wasserstein distributionally robust objectives, thereby providing tractable reformulations of READ and unifying a broad class of regularized estimators under the DRO lens. Second, we adopt a principled procedure for selecting the Wasserstein radius using the techniques of robust Wasserstein profile inference. This further enables the construction of valid, representation-aware confidence regions for model parameters with distinct geometric features. Finally, we analyze the geometry of READ estimators as the alignment parameters vary and propose an optimization algorithm to estimate the projection of the global optimum onto this solution surface. This procedure selects among equally robust estimators while optimally constructing a representation structure. We conclude by demonstrating the effectiveness of our framework through extensive simulations and a real-world study, providing a powerful robust estimation grounded in learning representation.
【5】Personalized Sleep Prediction via Deep Adaptive Spatiotemporal Modeling and Sparse Data
标题：基于深度自适应时空模型和稀疏数据的个性化睡眠预测
链接：https://arxiv.org/abs/2509.09018
备注：The paper has been acceptted and presented in the 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
摘要：睡眠预测允许个人和医疗保健提供者预测并主动解决影响休息的因素，最终改善身心健康。这项工作提出了一个自适应的空间和时间模型（AdaST-Sleep）预测睡眠分数。我们提出的模型结合了卷积层来捕获多个特征之间的空间特征交互，并结合了递归神经网络层来处理长期的时间健康相关数据。一个领域分类器被进一步整合，以概括不同的主题。我们进行了几个实验，使用五个输入窗口大小（3，5，7，9，11天）和五个预测窗口大小（1，3，5，7，9天）。我们的方法始终优于四个基线模型，在七天的输入窗口和一天的预测窗口下实现了最低的RMSE（0.282）。此外，该方法即使在预测未来多天时也保持了强大的性能，证明了其在现实世界应用中的多功能性。视觉比较显示，该模型准确地跟踪了整体睡眠评分水平和日常波动。这些发现证明，所提出的框架提供了一个强大的和适应性强的解决方案，个性化的睡眠预测使用稀疏数据从商业可穿戴设备和域适应技术。
摘要：A sleep forecast allows individuals and healthcare providers to anticipate and proactively address factors influencing restful rest, ultimately improving mental and physical well-being. This work presents an adaptive spatial and temporal model (AdaST-Sleep) for predicting sleep scores. Our proposed model combines convolutional layers to capture spatial feature interactions between multiple features and recurrent neural network layers to handle longer-term temporal health-related data. A domain classifier is further integrated to generalize across different subjects. We conducted several experiments using five input window sizes (3, 5, 7, 9, 11 days) and five predicting window sizes (1, 3, 5, 7, 9 days). Our approach consistently outperformed four baseline models, achieving its lowest RMSE (0.282) with a seven-day input window and a one-day predicting window. Moreover, the method maintained strong performance even when forecasting multiple days into the future, demonstrating its versatility for real-world applications. Visual comparisons reveal that the model accurately tracks both the overall sleep score level and daily fluctuations. These findings prove that the proposed framework provides a robust and adaptable solution for personalized sleep forecasting using sparse data from commercial wearable devices and domain adaptation techniques.
强化学习(4篇)
【1】SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
标题：SimpleVLA-RL：通过强化学习扩展VLA训练
链接：https://arxiv.org/abs/2509.09674
摘要：视觉-语言-动作（VLA）模型最近已经成为机器人操作的一个强大的范例。尽管通过大规模预训练和监督微调（SFT）实现了实质性进展，但这些模型面临两个基本挑战：（i）SFT缩放所需的大规模人工操作机器人轨迹的稀缺性和高成本，以及（ii）对涉及分布转移的任务的泛化有限。大型推理模型（LRM）的最新突破表明，强化学习（RL）可以显着增强逐步推理能力，这就提出了一个自然的问题：RL是否可以类似地改善VLA的长期逐步行动规划？在这项工作中，我们介绍了SimpleVLA-RL，一个高效的RL框架VLA模型量身定制。在veRL的基础上，我们引入了特定于VLA的轨迹采样、可扩展的并行化、多环境渲染和优化的损失计算。当应用于OpenVLA-OFT时，SimpleVLA-RL在LIBERO上实现了SoTA性能，甚至在RoboTwin 1.0\&2.0上使用我们介绍的探索增强策略优于$\pi_0$。SimpleVLA-RL不仅减少了对大规模数据的依赖，实现了鲁棒的泛化，而且在现实世界的任务中显着优于SFT。此外，我们在RL训练过程中发现了一种新的现象“pushcuts”，其中该策略发现了以前未见过的模式，超出了以前的训练过程中所看到的模式。Github网站：https://github.com/PRIME-RL/SimpleVLA-RL
摘要 ：Vision-Language-Action (VLA) models have recently emerged as a powerful paradigm for robotic manipulation. Despite substantial progress enabled by large-scale pretraining and supervised fine-tuning (SFT), these models face two fundamental challenges: (i) the scarcity and high cost of large-scale human-operated robotic trajectories required for SFT scaling, and (ii) limited generalization to tasks involving distribution shift. Recent breakthroughs in Large Reasoning Models (LRMs) demonstrate that reinforcement learning (RL) can dramatically enhance step-by-step reasoning capabilities, raising a natural question: Can RL similarly improve the long-horizon step-by-step action planning of VLA? In this work, we introduce SimpleVLA-RL, an efficient RL framework tailored for VLA models. Building upon veRL, we introduce VLA-specific trajectory sampling, scalable parallelization, multi-environment rendering, and optimized loss computation. When applied to OpenVLA-OFT, SimpleVLA-RL achieves SoTA performance on LIBERO and even outperforms $\pi_0$ on RoboTwin 1.0\&2.0 with the exploration-enhancing strategies we introduce. SimpleVLA-RL not only reduces dependence on large-scale data and enables robust generalization, but also remarkably surpasses SFT in real-world tasks. Moreover, we identify a novel phenomenon ``pushcut'' during RL training, wherein the policy discovers previously unseen patterns beyond those seen in the previous training process. Github: https://github.com/PRIME-RL/SimpleVLA-RL
【2】Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning
标题：激励约束强化学习的政策优化中的更安全行动
链接：https://arxiv.org/abs/2509.09208
备注：11 pages, Accepted to the 34th International Joint Conference on Artificial Intelligence (IJCAI) 2025, Main Track
摘要：约束强化学习（RL）旨在最大化回报，同时遵守预定义的约束限制，这些限制代表特定于领域的安全要求。在连续控制设置中，学习代理管理系统动作，平衡奖励最大化和约束满足之间的权衡仍然是一个重大的挑战。策略优化方法通常在约束边界附近表现出不稳定性，从而导致次优的训练性能。为了解决这个问题，我们引入了一种新的方法，它集成了自适应激励机制，除了奖励结构，以保持在约束范围内接近约束边界。基于这一见解，我们提出了增量惩罚邻近策略优化（IP3O），这是一种实用的算法，它强制执行逐渐增加的惩罚以稳定训练动态。通过对基准环境的实证评估，我们证明了IP3O与最先进的安全RL算法的性能相比的有效性。此外，我们提供了理论上的保证，推导出的最坏情况下的错误，我们的算法实现的最优性的界限。
摘要：Constrained Reinforcement Learning (RL) aims to maximize the return while adhering to predefined constraint limits, which represent domain-specific safety requirements. In continuous control settings, where learning agents govern system actions, balancing the trade-off between reward maximization and constraint satisfaction remains a significant challenge. Policy optimization methods often exhibit instability near constraint boundaries, resulting in suboptimal training performance. To address this issue, we introduce a novel approach that integrates an adaptive incentive mechanism in addition to the reward structure to stay within the constraint bound before approaching the constraint boundary. Building on this insight, we propose Incrementally Penalized Proximal Policy Optimization (IP3O), a practical algorithm that enforces a progressively increasing penalty to stabilize training dynamics. Through empirical evaluation on benchmark environments, we demonstrate the efficacy of IP3O compared to the performance of state-of-the-art Safe RL algorithms. Furthermore, we provide theoretical guarantees by deriving a bound on the worst-case error of the optimality achieved by our algorithm.
【3】Quantum Machine Learning, Quantitative Trading, Reinforcement Learning, Deep Learning
标题：量子机器学习、量化交易、强化学习、深度学习
链接：https://arxiv.org/abs/2509.09176
摘要：量子启发的神经网络和深度强化学习的融合为金融交易提供了一个有前途的途径。我们通过将用于短期趋势预测的量子长短期记忆（QLSTM）与量子异步优势演员评论家（QA 3C）（经典A3 C的量子增强变体）集成在一起，实现了USD/TWD的交易代理。根据2000-01-01至2025-04-30的数据进行训练（80%训练，20%测试），仅做多代理在大约5年的时间内实现了11.87%的回报率，最大跌幅为0.92%，优于几种货币ETF。我们详细介绍了状态设计（QLSTM功能和指标），趋势跟踪/风险控制的奖励函数，以及多核训练。结果表明，混合模型产生有竞争力的外汇交易性能。影响包括QLSTM的有效性，为小利润的交易，严格的风险和未来的增强。关键超参数：QLSTM序列长度$=$4，QA 3C worker $=$8。局限性：经典量子模拟和简化策略。本文中表达的观点是作者的观点，不代表富国银行的观点。本文仅供参考。本文中的任何内容都不应被解释为投资建议。富国银行不作任何明示或暗示的保证，并明确否认与本文有关的所有法律，税务和会计影响。
摘要：The convergence of quantum-inspired neural networks and deep reinforcement learning offers a promising avenue for financial trading. We implemented a trading agent for USD/TWD by integrating Quantum Long Short-Term Memory (QLSTM) for short-term trend prediction with Quantum Asynchronous Advantage Actor-Critic (QA3C), a quantum-enhanced variant of the classical A3C. Trained on data from 2000-01-01 to 2025-04-30 (80\% training, 20\% testing), the long-only agent achieves 11.87\% return over around 5 years with 0.92\% max drawdown, outperforming several currency ETFs. We detail state design (QLSTM features and indicators), reward function for trend-following/risk control, and multi-core training. Results show hybrid models yield competitive FX trading performance. Implications include QLSTM's effectiveness for small-profit trades with tight risk and future enhancements. Key hyperparameters: QLSTM sequence length$=$4, QA3C workers$=$8. Limitations: classical quantum simulation and simplified strategy. \footnote{The views expressed in this article are those of the authors and do not represent the views of Wells Fargo. This article is for informational purposes only. Nothing contained in this article should be construed as investment advice. Wells Fargo makes no express or implied warranties and expressly disclaims all legal, tax, and accounting implications related to this article.
【4】Continuous-Time Value Iteration for Multi-Agent Reinforcement Learning
标题：多智能体强化学习的连续时间值迭代
链接：https://arxiv.org/abs/2509.09135
备注：19 pages, 10 figures
摘要：现有的强化学习（RL）方法与复杂的动态系统斗争，这些系统需要以高频率或不规则的时间间隔进行交互。连续时间RL（CTRL）已成为一个有前途的替代方案，取代离散时间贝尔曼递归与微分值函数定义为粘度解决方案的汉密尔顿-雅可比-贝尔曼（HJB）方程。虽然CTRL显示出了希望，但其应用程序在很大程度上仅限于单代理域。这种限制源于两个关键挑战：（i）HJB方程的传统求解方法受到维数灾难（CoD）的影响，使得它们在高维系统中难以处理;（ii）即使使用基于HJB的学习方法，在多智能体环境中准确逼近集中式值函数仍然很困难，这反过来又会破坏策略训练。在本文中，我们提出了一个CT-MARL框架，该框架使用物理信息神经网络（PINN）来近似基于HJB的值函数。为了确保值与其差分结构一致，我们通过引入值梯度迭代（VGI）模块来将值学习与值梯度学习结合起来，该模块沿着轨迹迭代地细化值梯度。这提高了梯度保真度，从而产生更准确的值和更强大的策略学习。我们使用标准基准的连续时间变量来评估我们的方法，包括多智能体粒子环境（MPE）和多智能体MuJoCo。我们的研究结果表明，我们的方法始终优于现有的连续时间RL基线和复杂的多智能体动态的规模。
摘要：Existing reinforcement learning (RL) methods struggle with complex dynamical systems that demand interactions at high frequencies or irregular time intervals. Continuous-time RL (CTRL) has emerged as a promising alternative by replacing discrete-time Bellman recursion with differential value functions defined as viscosity solutions of the Hamilton--Jacobi--Bellman (HJB) equation. While CTRL has shown promise, its applications have been largely limited to the single-agent domain. This limitation stems from two key challenges: (i) conventional solution methods for HJB equations suffer from the curse of dimensionality (CoD), making them intractable in high-dimensional systems; and (ii) even with HJB-based learning approaches, accurately approximating centralized value functions in multi-agent settings remains difficult, which in turn destabilizes policy training. In this paper, we propose a CT-MARL framework that uses physics-informed neural networks (PINNs) to approximate HJB-based value functions at scale. To ensure the value is consistent with its differential structure, we align value learning with value-gradient learning by introducing a Value Gradient Iteration (VGI) module that iteratively refines value gradients along trajectories. This improves gradient fidelity, in turn yielding more accurate values and stronger policy learning. We evaluate our method using continuous-time variants of standard benchmarks, including multi-agent particle environment (MPE) and multi-agent MuJoCo. Our results demonstrate that our approach consistently outperforms existing continuous-time RL baselines and scales to complex multi-agent dynamics.
元学习(1篇)
【1】PIPES: A Meta-dataset of Machine Learning Pipelines
标题：Pipes：机器学习Pipeline的元数据集
链接：https://arxiv.org/abs/2509.09512
摘要：机器学习中算法选择问题（ASP）的解决方案面临着与评估给定数据集上各种算法性能相关的高计算成本的挑战。为了降低这种成本，元学习领域可以利用以前在OpenML等在线存储库中共享的实验。OpenML提供了大量的机器学习实验。然而，对OpenML记录的分析揭示了其局限性。它在管道中缺乏多样性，特别是在探索数据预处理步骤/块时，例如缩放或插补，从而导致有限的表示。它的实验通常集中在每个流水线块中的一些流行技术上，导致样本不平衡。为了克服OpenML的局限性，我们提出了PIPES，这是一组涉及多个管道的实验，旨在代表所选技术的所有组合，旨在实现多样性和完整性。PIPES存储了将9，408个管道应用于300个数据集的实验结果。它包括有关管道块、训练和测试时间、预测、性能和最终错误消息的详细信息。这种全面的结果集合使研究人员能够在各种具有代表性的管道和数据集上进行分析。PIPES还提供了扩展的潜力，因为可以纳入更多的数据和实验来进一步支持元学习社区。数据、代码、补充材料和所有实验都可以在https://github.com/cynthiamaia/PIPES.git上找到。
摘要：Solutions to the Algorithm Selection Problem (ASP) in machine learning face the challenge of high computational costs associated with evaluating various algorithms' performances on a given dataset. To mitigate this cost, the meta-learning field can leverage previously executed experiments shared in online repositories such as OpenML. OpenML provides an extensive collection of machine learning experiments. However, an analysis of OpenML's records reveals limitations. It lacks diversity in pipelines, specifically when exploring data preprocessing steps/blocks, such as scaling or imputation, resulting in limited representation. Its experiments are often focused on a few popular techniques within each pipeline block, leading to an imbalanced sample. To overcome the observed limitations of OpenML, we propose PIPES, a collection of experiments involving multiple pipelines designed to represent all combinations of the selected sets of techniques, aiming at diversity and completeness. PIPES stores the results of experiments performed applying 9,408 pipelines to 300 datasets. It includes detailed information on the pipeline blocks, training and testing times, predictions, performances, and the eventual error messages. This comprehensive collection of results allows researchers to perform analyses across diverse and representative pipelines and datasets. PIPES also offers potential for expansion, as additional data and experiments can be incorporated to support the meta-learning community further. The data, code, supplementary material, and all experiments can be found at https://github.com/cynthiamaia/PIPES.git.
医学相关(1篇)
【1】FoundationalECGNet: A Lightweight Foundational Model for ECG-based Multitask Cardiac Analysis
标题：FoundationalECGNet：基于心电图的多任务心脏分析的轻量级基础模型
链接：https://arxiv.org/abs/2509.08961
摘要：心血管疾病（CVD）仍然是全球死亡的主要原因，强调了准确和可扩展诊断系统的重要性。心电图（ECG）分析是检测心脏异常的核心，但噪声、类别不平衡和数据集异质性等挑战限制了当前的方法。为了解决这些问题，我们提出了FoundationalECGNet，自动心电图分类的基础框架。该模型集成了Morlet和Daubechies小波变换、卷积块注意模块（CBAM）、图注意网络（GAT）和时间序列Transformers（TST）的双阶段去噪，以联合捕获多通道ECG信号的空间和时间依赖性。FoundationalECGNet首先区分正常和异常ECG信号，然后将异常信号分类为五种心脏疾病之一：心律失常、传导障碍、心肌梗死、QT间期缩短或肥大。在多个数据集上，该模型在正常与异常分类方面实现了99%的F1评分，并在多类疾病检测方面表现出最先进的性能，包括传导障碍和肥大的99% F1评分以及心律失常的98.9% F1评分。此外，该模型提供了风险水平估计，以促进临床决策。总之，FoundationalECGNet是一种可扩展、可解释和可推广的自动ECG分析解决方案，有可能提高医疗保健环境中的诊断精度和患者结局。我们将在接受后共享代码。
摘要：Cardiovascular diseases (CVDs) remain a leading cause of mortality worldwide, underscoring the importance of accurate and scalable diagnostic systems. Electrocardiogram (ECG) analysis is central to detecting cardiac abnormalities, yet challenges such as noise, class imbalance, and dataset heterogeneity limit current methods. To address these issues, we propose FoundationalECGNet, a foundational framework for automated ECG classification. The model integrates a dual-stage denoising by Morlet and Daubechies wavelets transformation, Convolutional Block Attention Module (CBAM), Graph Attention Networks (GAT), and Time Series Transformers (TST) to jointly capture spatial and temporal dependencies in multi-channel ECG signals. FoundationalECGNet first distinguishes between Normal and Abnormal ECG signals, and then classifies the Abnormal signals into one of five cardiac conditions: Arrhythmias, Conduction Disorders, Myocardial Infarction, QT Abnormalities, or Hypertrophy. Across multiple datasets, the model achieves a 99% F1-score for Normal vs. Abnormal classification and shows state-of-the-art performance in multi-class disease detection, including a 99% F1-score for Conduction Disorders and Hypertrophy, as well as a 98.9% F1-score for Arrhythmias. Additionally, the model provides risk level estimations to facilitate clinical decision-making. In conclusion, FoundationalECGNet represents a scalable, interpretable, and generalizable solution for automated ECG analysis, with the potential to improve diagnostic precision and patient outcomes in healthcare settings. We'll share the code after acceptance.
蒸馏|知识提取(1篇)
【1】AEGIS: An Agent for Extraction and Geographic Identification in Scholarly Proceedings
标题：AEGIS：学术论文集中的提取和地理识别代理
链接：https://arxiv.org/abs/2509.09470
备注：5 pages, 2 figures
摘要：跟上学术文献的快速增长，对研究人员、资助机构和学术团体提出了重大挑战。为了解决学术发现所需的耗时的手动工作，我们提出了一种新颖的，完全自动化的系统，从数据发现过渡到直接行动。我们的流水线演示了一个专门的人工智能代理“Agent-E”如何在会议程序中识别来自特定地理区域的论文，然后执行机器人流程自动化（RPA）来完成预定义的操作，例如提交提名表格。我们在来自五个不同会议的586篇论文上验证了我们的系统，它成功地识别了每一篇目标论文，召回率为100%，准确率接近99.4%。该演示突出了面向任务的人工智能代理的潜力，不仅可以过滤信息，还可以积极参与和加速学术界的工作流程。
摘要：Keeping pace with the rapid growth of academia literature presents a significant challenge for researchers, funding bodies, and academic societies. To address the time-consuming manual effort required for scholarly discovery, we present a novel, fully automated system that transitions from data discovery to direct action. Our pipeline demonstrates how a specialized AI agent, 'Agent-E', can be tasked with identifying papers from specific geographic regions within conference proceedings and then executing a Robotic Process Automation (RPA) to complete a predefined action, such as submitting a nomination form. We validated our system on 586 papers from five different conferences, where it successfully identified every target paper with a recall of 100% and a near perfect accuracy of 99.4%. This demonstration highlights the potential of task-oriented AI agents to not only filter information but also to actively participate in and accelerate the workflows of the academic community.
推荐(2篇)
【1】Personality-Enhanced Social Recommendations in SAMI: Exploring the Role of Personality Detection in Matchmaking
标题：SAMI中个性增强的社会推荐：探索个性检测在婚介中的作用
链接：https://arxiv.org/abs/2509.09583
摘要：社会联系是学习的重要组成部分，然而在线课程环境对社会群体的有机形成构成了障碍。SAMI提供了一个解决方案，促进学生的联系，但其有效性受到不完整的心理理论的限制，限制了其创建有效的学生心理模型的能力。其中一个方面是它无法凭直觉感知个性，这可能会影响其建议的相关性。为了探索这一点，我们提出了一个人格检测模型，利用GPT的zero-shot能力来推断大五人格特质，从论坛介绍职位，经常鼓励在网上课程。我们将其性能与已建立的模型进行基准测试，证明其在这项任务中的有效性。此外，我们将此模型集成到SAMIs基于实体的匹配系统中，从而实现个性化的社交推荐。初步整合表明，人格特质可以补充现有的匹配因素，但需要额外的评估，以确定他们对学生参与和匹配质量的全面影响。
摘要：Social connection is a vital part of learning, yet online course environments present barriers to the organic formation of social groups. SAMI offers one solution by facilitating student connections, but its effectiveness is constrained by an incomplete Theory of Mind, limiting its ability to create an effective mental model of a student. One facet of this is its inability to intuit personality, which may influence the relevance of its recommendations. To explore this, we propose a personality detection model utilizing GPTs zero-shot capability to infer Big-Five personality traits from forum introduction posts, often encouraged in online courses. We benchmark its performance against established models, demonstrating its efficacy in this task. Furthermore, we integrate this model into SAMIs entity-based matchmaking system, enabling personality-informed social recommendations. Initial integration suggests personality traits can complement existing matching factors, though additional evaluation is required to determine their full impact on student engagement and match quality.
【2】Peering Partner Recommendation for ISPs using Machine Learning
标题：使用机器学习为ISP提供的对等合作伙伴建议
链接：https://arxiv.org/abs/2509.09146
备注：Submitted to IEEE Transactions on Machine Learning in Communications and Networking
摘要：互联网服务提供商（ISP）需要与其他ISP连接，以向其用户提供全球连接服务。为了确保全球连通性，ISP可以使用中转服务，也可以通过互联网交换点（IXP）在彼此之间建立直接对等关系。对等为特定于ISP的优化提供了更多的空间，是首选，但它通常涉及一个漫长而复杂的过程。自动化对等伙伴选择可以提高全球互联网生态系统的效率。我们探索使用ISP上的公开数据来开发一个机器学习（ML）模型，该模型可以预测ISP对是否应该对等。首先，我们探索公共数据库，例如，PeeringDB、CAIDA等，收集互联网服务提供商的数据然后，我们评估了用于预测对等关系的三种广泛类型的ML模型的性能：基于树的，基于神经网络的和基于transformer的。其中，我们观察到基于树的模型在我们的实验中达到了最高的准确性和效率。使用公开数据训练的XGBoost模型表现出良好的性能，在预测对等伙伴方面的准确率为98%。此外，该模型对时间、空间和缺失数据的变化表现出很大的弹性。我们设想，互联网服务提供商可以采用我们的方法来完全自动化对等伙伴选择过程，从而过渡到一个更有效和优化的互联网生态系统。
摘要：Internet service providers (ISPs) need to connect with other ISPs to provide global connectivity services to their users. To ensure global connectivity, ISPs can either use transit service(s) or establish direct peering relationships between themselves via Internet exchange points (IXPs). Peering offers more room for ISP-specific optimizations and is preferred, but it often involves a lengthy and complex process. Automating peering partner selection can enhance efficiency in the global Internet ecosystem. We explore the use of publicly available data on ISPs to develop a machine learning (ML) model that can predict whether an ISP pair should peer or not. At first, we explore public databases, e.g., PeeringDB, CAIDA, etc., to gather data on ISPs. Then, we evaluate the performance of three broad types of ML models for predicting peering relationships: tree-based, neural network-based, and transformer-based. Among these, we observe that tree-based models achieve the highest accuracy and efficiency in our experiments. The XGBoost model trained with publicly available data showed promising performance, with a 98% accuracy rate in predicting peering partners. In addition, the model demonstrated great resilience to variations in time, space, and missing data. We envision that ISPs can adopt our method to fully automate the peering partner selection process, thus transitioning to a more efficient and optimized Internet ecosystem.
自动驾驶|车辆|车道检测等(1篇)
【1】What Does Normal Even Mean? Evaluating Benign Traffic in Intrusion Detection Datasets
标题：正常到底是什么意思？评估入侵检测数据集中的良性流量
链接：https://arxiv.org/abs/2509.09564
备注：10 pages; accepted to SBP-BRiMS 2025 Poster Session
摘要：监督机器学习技术依赖于标记数据来实现高任务性能，但这需要标签捕获底层数据结构中的一些有意义的差异。为了训练网络入侵检测算法，大多数数据集包含一系列攻击类和一个捕获所有非攻击网络流量的大型良性类。对明确说明其数据预处理步骤的入侵检测论文和指南的回顾表明，大多数人在训练算法时都采用了数据集的标记类别。本文评估了几个常见入侵检测数据集（NSL-KDD，UNSW-NB 15和CIC-IDS 2017）中良性流量的结构，并确定此流量中是否存在有意义的子类别，这些子类别可以使用常见的机器学习技术提高整体多分类性能。我们提出了一些无监督聚类技术的概述（例如，HDBSCAN，均值漂移聚类），并显示他们如何差异集群良性交通空间。
摘要：Supervised machine learning techniques rely on labeled data to achieve high task performance, but this requires the labels to capture some meaningful differences in the underlying data structure. For training network intrusion detection algorithms, most datasets contain a series of attack classes and a single large benign class which captures all non-attack network traffic. A review of intrusion detection papers and guides that explicitly state their data preprocessing steps identified that the majority took the labeled categories of the dataset at face value when training their algorithms. The present paper evaluates the structure of benign traffic in several common intrusion detection datasets (NSL-KDD, UNSW-NB15, and CIC-IDS 2017) and determines whether there are meaningful sub-categories within this traffic which may improve overall multi-classification performance using common machine learning techniques. We present an overview of some unsupervised clustering techniques (e.g., HDBSCAN, Mean Shift Clustering) and show how they differentially cluster the benign traffic space.
联邦学习|隐私保护|加密(2篇)
【1】ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning
标题：ProDiGamma：基于邻近性和异化的拜占庭稳健联邦学习
链接：https://arxiv.org/abs/2509.09534
摘要：联邦学习（FL）是分布式学习的一个被广泛研究的范例。尽管FL具有许多优点，但它仍然容易受到对抗性攻击，特别是在数据异构的情况下。我们提出了一个新的拜占庭强大的FL算法称为ProDiGy。关键的新颖性在于使用基于梯度的接近性和相异性的联合双评分系统来评估客户端梯度。我们通过大量的数值实验证明，ProDiGy在各种情况下优于现有的防御。特别是，当客户端的数据不遵循IID分布，而其他防御机制失败时，ProDiGy保持强大的防御能力和模型准确性。这些发现突出了双重视角方法的有效性，该方法促进诚实客户之间的自然相似性，同时检测可疑的一致性作为攻击的潜在指标。
摘要 ：Federated Learning (FL) emerged as a widely studied paradigm for distributed learning. Despite its many advantages, FL remains vulnerable to adversarial attacks, especially under data heterogeneity. We propose a new Byzantine-robust FL algorithm called ProDiGy. The key novelty lies in evaluating the client gradients using a joint dual scoring system based on the gradients' proximity and dissimilarity. We demonstrate through extensive numerical experiments that ProDiGy outperforms existing defenses in various scenarios. In particular, when the clients' data do not follow an IID distribution, while other defense mechanisms fail, ProDiGy maintains strong defense capabilities and model accuracy. These findings highlight the effectiveness of a dual perspective approach that promotes natural similarity among honest clients while detecting suspicious uniformity as a potential indicator of an attack.
【2】Green Federated Learning via Carbon-Aware Client and Time Slot Scheduling
标题：通过碳感知客户端和时段安排的绿色联邦学习
链接：https://arxiv.org/abs/2509.08980
摘要：训练大规模机器学习模型会产生大量的碳排放。联邦学习（FL）通过在地理上分散的客户端上分布计算，提供了一个自然的框架来利用碳强度（CI）的区域和时间变化。本文研究了如何通过碳意识客户选择和培训计划来减少FL的排放。我们首先量化了碳意识调度政策的减排量，该政策利用了空闲时间-允许适度延长培训时间，以便客户可以将本地培训轮推迟到低碳时期。然后，我们研究这种调度的性能权衡，这源于客户端之间的统计异质性，参与的选择偏差，以及模型更新的时间相关性。为了利用这些权衡，我们构建了一个碳感知调度，集成了松弛时间，$\alpha$-公平的碳分配，和一个全球性的微调阶段。在真实CI数据上的实验表明，我们的调度器优于松弛不可知的基线，在广泛的碳预算范围内实现了更高的模型准确性，在严格的碳约束下具有特别强的增益。
摘要：Training large-scale machine learning models incurs substantial carbon emissions. Federated Learning (FL), by distributing computation across geographically dispersed clients, offers a natural framework to leverage regional and temporal variations in Carbon Intensity (CI). This paper investigates how to reduce emissions in FL through carbon-aware client selection and training scheduling. We first quantify the emission savings of a carbon-aware scheduling policy that leverages slack time -- permitting a modest extension of the training duration so that clients can defer local training rounds to lower-carbon periods. We then examine the performance trade-offs of such scheduling which stem from statistical heterogeneity among clients, selection bias in participation, and temporal correlation in model updates. To leverage these trade-offs, we construct a carbon-aware scheduler that integrates slack time, $\alpha$-fair carbon allocation, and a global fine-tuning phase. Experiments on real-world CI data show that our scheduler outperforms slack-agnostic baselines, achieving higher model accuracy across a wide range of carbon budgets, with especially strong gains under tight carbon constraints.
推理|分析|理解|解释(7篇)
【1】Database Views as Explanations for Relational Deep Learning
标题：数据库视图作为关系深度学习的解释
链接：https://arxiv.org/abs/2509.09482
摘要：近年来，在关系数据库上开发深度学习模型方面取得了重大进展，包括基于异构图神经网络（hetero-GNN）和异构图Transformers的架构。实际上，这样的体系结构说明了数据库如何记录和链接（例如，外键引用）转换成一个大的、复杂的数值表达式，涉及许多可学习的参数。这种复杂性使得很难用人类可以理解的术语来解释模型如何使用可用数据来得出给定的预测。我们提出了一个新的框架，用于解释机器学习模型的关系数据库，其中的解释是视图定义，突出重点部分的数据库，主要有助于模型的预测。我们通过调整Nash，Segoufin和Vianu（2010）的经典确定性概念来建立这种全局溯因解释。除了调整确定性和简洁性之间的权衡，该框架允许通过采用不同的视图定义片段来控制粒度级别，例如突出显示整个列，表之间的外键，相关元组组等。我们开发的启发式算法，避免了所有数据库的空间上的穷举搜索。我们提出了与模型无关的技术，以及其他通过可学习掩码概念为异质GNN量身定制的技术。我们的方法是通过一个广泛的实证研究RelBench收集，涵盖了各种领域和不同的记录级任务进行评估。结果表明所提出的解释的有用性，以及它们的生成效率。
摘要：In recent years, there has been significant progress in the development of deep learning models over relational databases, including architectures based on heterogeneous graph neural networks (hetero-GNNs) and heterogeneous graph transformers. In effect, such architectures state how the database records and links (e.g., foreign-key references) translate into a large, complex numerical expression, involving numerous learnable parameters. This complexity makes it hard to explain, in human-understandable terms, how a model uses the available data to arrive at a given prediction. We present a novel framework for explaining machine-learning models over relational databases, where explanations are view definitions that highlight focused parts of the database that mostly contribute to the model's prediction. We establish such global abductive explanations by adapting the classic notion of determinacy by Nash, Segoufin, and Vianu (2010). In addition to tuning the tradeoff between determinacy and conciseness, the framework allows controlling the level of granularity by adopting different fragments of view definitions, such as ones highlighting whole columns, foreign keys between tables, relevant groups of tuples, and so on. We investigate the realization of the framework in the case of hetero-GNNs. We develop heuristic algorithms that avoid the exhaustive search over the space of all databases. We propose techniques that are model-agnostic, and others that are tailored to hetero-GNNs via the notion of learnable masking. Our approach is evaluated through an extensive empirical study on the RelBench collection, covering a variety of domains and different record-level tasks. The results demonstrate the usefulness of the proposed explanations, as well as the efficiency of their generation.
【2】Fused Lasso Improves Accuracy of Co-occurrence Network Inference in Grouped Samples
标题：融合套索提高了分组样本中同现网络推理的准确性
链接：https://arxiv.org/abs/2509.09413
摘要：共现网络推理算法大大提高了我们对微生物群落的理解。然而，这些算法通常分析从单个环境小生境收集的样品内的微生物关联，通常仅捕获静态快照而不是动态微生物过程。以前的研究通常将来自不同环境小生境的样本分组在一起，而没有充分考虑微生物群落在面临不同生态条件时如何适应它们的关联。我们的研究通过明确调查微生物群落的空间和时间动态来解决这一限制。我们分析了多个地点和时间点的公开微生物丰度数据，以评估使用我们提出的Same-All Cross-validation（SAC）框架预测微生物关联的算法性能。SAC在两种不同的场景中评估算法：在同一环境小生境中进行训练和测试（Same），以及在来自多个环境小生境的组合数据上进行训练和测试（All）。为了克服传统算法的局限性，我们提出了融合器，这是一种算法，虽然在机器学习中不是全新的，但对于微生物群落网络推理来说是新颖的。它保留子样本特定的信号，同时在训练期间跨环境共享相关信息。与从组合数据推断单个广义网络的标准方法不同，fuser生成独特的、特定于环境的预测网络。我们的研究结果表明，融合器实现可比的预测性能，现有的算法，如glmnet在同质环境（相同）内进行评估时，并显着降低测试误差相比，基线算法在跨环境（所有）的情况下。
摘要 ：Co-occurrence network inference algorithms have significantly advanced our understanding of microbiome communities. However, these algorithms typically analyze microbial associations within samples collected from a single environmental niche, often capturing only static snapshots rather than dynamic microbial processes. Previous studies have commonly grouped samples from different environmental niches together without fully considering how microbial communities adapt their associations when faced with varying ecological conditions. Our study addresses this limitation by explicitly investigating both spatial and temporal dynamics of microbial communities. We analyzed publicly available microbiome abundance data across multiple locations and time points, to evaluate algorithm performance in predicting microbial associations using our proposed Same-All Cross-validation (SAC) framework. SAC evaluates algorithms in two distinct scenarios: training and testing within the same environmental niche (Same), and training and testing on combined data from multiple environmental niches (All). To overcome the limitations of conventional algorithms, we propose fuser, an algorithm that, while not entirely new in machine learning, is novel for microbiome community network inference. It retains subsample-specific signals while simultaneously sharing relevant information across environments during training. Unlike standard approaches that infer a single generalized network from combined data, fuser generates distinct, environment-specific predictive networks. Our results demonstrate that fuser achieves comparable predictive performance to existing algorithms such as glmnet when evaluated within homogeneous environments (Same), and notably reduces test error compared to baseline algorithms in cross-environment (All) scenarios.
【3】Tree-OPO: Off-policy Monte Carlo Tree-Guided Advantage Optimization for Multistep Reasoning
标题：Tree-OPO：用于多步推理的非政策蒙特卡罗树引导优势优化
链接：https://arxiv.org/abs/2509.09284
摘要：大型语言模型（LLM）推理的最新进展表明，蒙特卡洛树搜索（MCTS）生成高质量的中间轨迹，特别是在数学和符号领域的有效性。受此启发，我们探讨了如何将传统上用于训练价值或奖励模型的MCTS导出的轨迹重新用于改进基于偏好的强化学习（RL）中的策略优化。具体来说，我们专注于组相对策略优化（GRPO），这是一种最新的算法，可以在没有价值网络的情况下实现偏好一致的策略学习。我们提出了一个分阶段的GRPO训练范式，其中完成来自部分显示MCTS推出，引入了一种新的树结构设置的优势估计。这导致了丰富的前缀条件奖励信号，我们从理论和经验上进行分析。我们的初步结果表明，虽然结构化优势估计可以稳定更新，更好地反映组合推理质量，但优势饱和和奖励信号崩溃等挑战仍然存在。我们提出了启发式和统计的解决方案，以减轻这些问题，并讨论了开放的挑战下学习阶段或树状奖励结构。
摘要：Recent advances in reasoning with large language models (LLMs) have shown the effectiveness of Monte Carlo Tree Search (MCTS) for generating high-quality intermediate trajectories, particularly in math and symbolic domains. Inspired by this, we explore how MCTS-derived trajectories, traditionally used for training value or reward models, can be repurposed to improve policy optimization in preference-based reinforcement learning (RL). Specifically, we focus on Group Relative Policy Optimization (GRPO), a recent algorithm that enables preference-consistent policy learning without value networks. We propose a staged GRPO training paradigm where completions are derived from partially revealed MCTS rollouts, introducing a novel tree-structured setting for advantage estimation. This leads to a rich class of prefix-conditioned reward signals, which we analyze theoretically and empirically. Our initial results indicate that while structured advantage estimation can stabilize updates and better reflect compositional reasoning quality, challenges such as advantage saturation and reward signal collapse remain. We propose heuristic and statistical solutions to mitigate these issues and discuss open challenges for learning under staged or tree-like reward structures.
【4】Video Understanding by Design: How Datasets Shape Architectures and Insights
标题：视频通过设计理解：数据集如何塑造架构和见解
链接：https://arxiv.org/abs/2509.09151
备注：Research report
摘要：在日益复杂的数据集和强大的架构的推动下，视频理解发展迅速。然而，现有的调查在很大程度上根据任务或家族对模型进行分类，忽略了数据集引导架构演变的结构压力。这项调查是第一次采用一个小齿轮驱动的角度来看，显示如何运动的复杂性，时间跨度，层次结构和多模态的丰富性施加模型应该编码的归纳偏见。我们重新解释里程碑，从双流和3D CNN到顺序，Transformer和多模态基础模型，作为对这些压力驱动的压力的具体响应。在此综合的基础上，我们为调整模型设计与数据集不变性提供了实用的指导，同时平衡了可扩展性和任务需求。通过将数据集、归纳偏差和架构统一到一个连贯的框架中，这项调查为推进通用视频理解提供了一个全面的回顾性和规范性的路线图。
摘要：Video understanding has advanced rapidly, fueled by increasingly complex datasets and powerful architectures. Yet existing surveys largely classify models by task or family, overlooking the structural pressures through which datasets guide architectural evolution. This survey is the first to adopt a dataset-driven perspective, showing how motion complexity, temporal span, hierarchical composition, and multimodal richness impose inductive biases that models should encode. We reinterpret milestones, from two-stream and 3D CNNs to sequential, transformer, and multimodal foundation models, as concrete responses to these dataset-driven pressures. Building on this synthesis, we offer practical guidance for aligning model design with dataset invariances while balancing scalability and task demands. By unifying datasets, inductive biases, and architectures into a coherent framework, this survey provides both a comprehensive retrospective and a prescriptive roadmap for advancing general-purpose video understanding.
【5】"A 6 or a 9?": Ensemble Learning Through the Multiplicity of Performant Models and Explanations
链接：https://arxiv.org/abs/2509.09073
备注：Paper accepted to the ACM Transactions on Knowledge Discovery from Data (TKDD) for publication (preprint version)
摘要：从过去的观察中创建模型并确保它们对新数据的有效性是机器学习的本质。然而，选择推广良好的模型仍然是一项具有挑战性的任务。与此相关，罗生门效应是指对于给定的学习问题，多个模型表现相似的情况。这通常发生在现实世界的场景中，如制造过程或医疗诊断，其中不同的数据模式导致多个高性能解决方案。我们提出了罗生门Entrance，一种从这些不同的高性能解决方案中策略性地选择模型以提高泛化能力的方法。通过根据模型的性能和解释对模型进行分组，我们构建了在保持预测准确性的同时最大化多样性的集合。这种选择确保每个模型覆盖解决方案空间的不同区域，使集合对分布变化和不可见数据的变化更加鲁棒。我们在开放和专有的协作真实世界数据集上验证了我们的方法，在罗生门比率很大的情况下，AUROC的改进高达0.20+。此外，我们在各种现实应用中为企业展示了切实的好处，突出了我们方法的鲁棒性，实用性和有效性。
摘要：Creating models from past observations and ensuring their effectiveness on new data is the essence of machine learning. However, selecting models that generalize well remains a challenging task. Related to this topic, the Rashomon Effect refers to cases where multiple models perform similarly well for a given learning problem. This often occurs in real-world scenarios, like the manufacturing process or medical diagnosis, where diverse patterns in data lead to multiple high-performing solutions. We propose the Rashomon Ensemble, a method that strategically selects models from these diverse high-performing solutions to improve generalization. By grouping models based on both their performance and explanations, we construct ensembles that maximize diversity while maintaining predictive accuracy. This selection ensures that each model covers a distinct region of the solution space, making the ensemble more robust to distribution shifts and variations in unseen data. We validate our approach on both open and proprietary collaborative real-world datasets, demonstrating up to 0.20+ AUROC improvements in scenarios where the Rashomon ratio is large. Additionally, we demonstrate tangible benefits for businesses in various real-world applications, highlighting the robustness, practicality, and effectiveness of our approach.
【6】Value bounds and Convergence Analysis for Averages of LRP attributions
标题：LRP属性的值界和收敛性分析
链接：https://arxiv.org/abs/2509.08963
备注：37 pages
摘要：我们分析了分层相关传播（LRP）型属性方法的数值特性，将它们表示为修改后的梯度矩阵的乘积。这种表示创建了一个类似的雅可比矩阵的矩阵乘法，产生于微分的链式法则。为了阐明属性值的分布，我们推导出奇异值的上界。此外，我们推导出组件的属性图值的界限。作为一个主要的结果，我们应用这些组件明智的界限，以获得乘法常数。这些常数决定了归因的经验平均值与归因图期望值的趋同性。这一发现具有重要的意义的情况下，多个非几何数据扩增适用于个人的测试样本，以及Smoothgrad-type归因方法。特别是，我们的分析表明，LRP-β的常数保持独立的重量规范，一个显着的区别，从基于梯度的方法和LRP-β。
摘要 ：We analyze numerical properties of Layer-wise relevance propagation (LRP)-type attribution methods by representing them as a product of modified gradient matrices. This representation creates an analogy to matrix multiplications of Jacobi-matrices which arise from the chain rule of differentiation. In order to shed light on the distribution of attribution values, we derive upper bounds for singular values. Furthermore we derive component-wise bounds for attribution map values. As a main result, we apply these component-wise bounds to obtain multiplicative constants. These constants govern the convergence of empirical means of attributions to expectations of attribution maps. This finding has important implications for scenarios where multiple non-geometric data augmentations are applied to individual test samples, as well as for Smoothgrad-type attribution methods. In particular, our analysis reveals that the constants for LRP-beta remain independent of weight norms, a significant distinction from both gradient-based methods and LRP-epsilon.
【7】Explainable AI for Accelerated Microstructure Imaging: A SHAP-Guided Protocol on the Connectome 2.0 scanner
标题：用于加速微结构成像的可解释AI：Connectome 2.0扫描仪上的SHAP引导协议
链接：https://arxiv.org/abs/2509.09513
备注：Submitted to IEEE Transactions on Medical Imaging (TMI). This all-in-one version includes supplementary materials. 18 pages, 14 figures, 2 tables
摘要：扩散MRI神经突交换成像模型提供了一个很有前途的框架，通过估计参数，如房室大小，扩散率和房室间水交换时间探测灰质微结构。然而，现有的协议需要长的扫描时间。本研究提出了一种用于Connectome 2.0扫描仪的简化采集方案，该方案在保持模型准确性的同时大大缩短了扫描持续时间。我们开发了一个数据驱动的框架，使用可解释的人工智能与指导递归特征消除策略，以确定一个最佳的8个特征子集从15个特征的协议。该优化方案的性能在体内进行了验证，并以完全采集和替代还原策略为基准。对参数准确度、解剖对比度的保留和重测重现性进行了评估。简化方案产生的参数估计值和皮质地图与完整方案相当，合成数据的估计误差较低，对重测变异性的影响最小。与理论驱动和启发式简化方案相比，优化后的协议表现出更好的鲁棒性，将水交换时间估计的偏差降低了两倍以上。总之，这种混合优化框架能够在14分钟内实现神经突交换的可行成像，而不会损失参数保真度。这种方法支持交换敏感扩散磁共振成像在神经科学和临床研究中的更广泛应用，并提供了一种可推广的方法，用于设计有效的采集协议，在生物物理参数映射。
摘要：The diffusion MRI Neurite Exchange Imaging model offers a promising framework for probing gray matter microstructure by estimating parameters such as compartment sizes, diffusivities, and inter-compartmental water exchange time. However, existing protocols require long scan times. This study proposes a reduced acquisition scheme for the Connectome 2.0 scanner that preserves model accuracy while substantially shortening scan duration. We developed a data-driven framework using explainable artificial intelligence with a guided recursive feature elimination strategy to identify an optimal 8-feature subset from a 15-feature protocol. The performance of this optimized protocol was validated in vivo and benchmarked against the full acquisition and alternative reduction strategies. Parameter accuracy, preservation of anatomical contrast, and test-retest reproducibility were assessed. The reduced protocol yielded parameter estimates and cortical maps comparable to the full protocol, with low estimation errors in synthetic data and minimal impact on test-retest variability. Compared to theory-driven and heuristic reduction schemes, the optimized protocol demonstrated superior robustness, reducing the deviation in water exchange time estimates by over two-fold. In conclusion, this hybrid optimization framework enables viable imaging of neurite exchange in 14 minutes without loss of parameter fidelity. This approach supports the broader application of exchange-sensitive diffusion magnetic resonance imaging in neuroscience and clinical research, and offers a generalizable method for designing efficient acquisition protocols in biophysical parameter mapping.
检测相关(5篇)
【1】OpenFake: An Open Dataset and Platform Toward Large-Scale Deepfake Detection
标题：OpenFake：面向大规模Deepfake检测的开放数据集和平台
链接：https://arxiv.org/abs/2509.09495
备注：25 pages, 12 figures
摘要：Deepfakes是使用先进的人工智能技术创建的合成媒体，它加剧了错误信息的传播，特别是在政治敏感的背景下。现有的deepfake检测数据集通常是有限的，依赖于过时的生成方法，低真实性或单面图像，限制了一般合成图像检测的有效性。通过分析社交媒体帖子，我们确定了deepfake传播错误信息的多种方式。此外，我们的人类感知研究表明，最近开发的专有模型产生的合成图像越来越难以与真实图像区分，使公众的准确识别变得复杂。因此，我们提出了一个全面的，以政治为重点的数据集，专门用于对现代生成模型进行基准检测。该数据集包含300万张带有描述性标题的真实图像，用于从专有和开源模型的混合中生成963k相应的高质量合成图像。认识到生成技术的不断发展，我们推出了一个创新的众包对抗平台，鼓励参与者生成和提交具有挑战性的合成图像。这项正在进行的社区驱动的举措确保深度造假检测方法保持强大和自适应，主动保护公共话语免受复杂的错误信息威胁。
摘要：Deepfakes, synthetic media created using advanced AI techniques, have intensified the spread of misinformation, particularly in politically sensitive contexts. Existing deepfake detection datasets are often limited, relying on outdated generation methods, low realism, or single-face imagery, restricting the effectiveness for general synthetic image detection. By analyzing social media posts, we identify multiple modalities through which deepfakes propagate misinformation. Furthermore, our human perception study demonstrates that recently developed proprietary models produce synthetic images increasingly indistinguishable from real ones, complicating accurate identification by the general public. Consequently, we present a comprehensive, politically-focused dataset specifically crafted for benchmarking detection against modern generative models. This dataset contains three million real images paired with descriptive captions, which are used for generating 963k corresponding high-quality synthetic images from a mix of proprietary and open-source models. Recognizing the continual evolution of generative techniques, we introduce an innovative crowdsourced adversarial platform, where participants are incentivized to generate and submit challenging synthetic images. This ongoing community-driven initiative ensures that deepfake detection methods remain robust and adaptive, proactively safeguarding public discourse from sophisticated misinformation threats.
【2】Model-Agnostic Open-Set Air-to-Air Visual Object Detection for Reliable UAV Perception
标题：模型不可知的开放式空对空视觉对象检测，实现可靠的无人机感知
链接：https://arxiv.org/abs/2509.09297
摘要：开集检测对于无人机在真实条件下进行空对空目标检测的鲁棒自主性至关重要。传统的闭集检测器在域转移和飞行数据损坏的情况下会显着降低，对安全关键应用构成风险。我们提出了一种新的，模型无关的开集检测框架，专为嵌入式检测器设计。该方法显式处理未知对象拒绝，同时保持对损坏的飞行数据的鲁棒性。它通过嵌入空间中的熵建模来估计语义不确定性，并结合频谱归一化和温度缩放来增强开集区分。我们通过具有挑战性的AOT空中基准测试和广泛的真实飞行测试来验证我们的方法。全面的消融研究表明，与基线方法相比，实现了一致的改进，与基于YOLO的标准探测器相比，实现了高达10%的相对AUROC增益。此外，我们还表明，背景抑制进一步增强了鲁棒性，而不会影响检测精度，使我们的解决方案特别适合在动态空对空环境中进行可靠的无人机感知。
摘要 ：Open-set detection is crucial for robust UAV autonomy in air-to-air object detection under real-world conditions. Traditional closed-set detectors degrade significantly under domain shifts and flight data corruption, posing risks to safety-critical applications. We propose a novel, model-agnostic open-set detection framework designed specifically for embedding-based detectors. The method explicitly handles unknown object rejection while maintaining robustness against corrupted flight data. It estimates semantic uncertainty via entropy modeling in the embedding space and incorporates spectral normalization and temperature scaling to enhance open-set discrimination. We validate our approach on the challenging AOT aerial benchmark and through extensive real-world flight tests. Comprehensive ablation studies demonstrate consistent improvements over baseline methods, achieving up to a 10\% relative AUROC gain compared to standard YOLO-based detectors. Additionally, we show that background rejection further strengthens robustness without compromising detection accuracy, making our solution particularly well-suited for reliable UAV perception in dynamic air-to-air environments.
【3】Breaking the Statistical Similarity Trap in Extreme Convection Detection
标题：打破极端对流检测中的统计相似性陷阱
链接：https://arxiv.org/abs/2509.09195
备注：43 pages, 7 figures
摘要：目前针对深度学习天气模型的评估指标造成了“统计相似性陷阱”，奖励模糊的预测，同时错过罕见的高影响力事件。我们提供了这个陷阱的定量证据，显示复杂的基线达到97.9%的相关性，但0.00 CSI的危险对流检测。我们引入DART（回归任务的双重架构），这是一个解决将粗糙的大气预报转换为针对极端对流检测（低于220 K）优化的高分辨率卫星亮温场的挑战的框架。DART采用双解码器架构，具有显式的背景/极端分解、物理激励的过采样和特定于任务的损失函数。我们提出了四个关键发现：（1）在多个复杂的基线上对统计相似性陷阱进行了实证验证;（2）“IVT粒子”，去除了被广泛认为是大气河流分析所必需的综合水汽输送，将极端对流探测提高了270%;（3）通过操作灵活性证明架构必要性（DART达到CSI = 0.273，偏差= 2.52，而基线为6.72，在同等CSI下），以及（4）以2023年8月吉大港洪水灾害为案例研究的真实世界验证。据我们所知，这是第一个系统地解决这种混合转换-分割-降尺度任务的工作，在现有文献中没有直接的先验基准。我们对不同统计和深度学习基线的验证充分证明了DART的专业设计。该框架通过beta调整实现了精确的操作校准，在标准硬件上的训练时间不到10分钟，并与现有的气象工作流程无缝集成，展示了一条通往可信赖的极端天气准备AI的途径。
摘要：Current evaluation metrics for deep learning weather models create a "Statistical Similarity Trap", rewarding blurry predictions while missing rare, high-impact events. We provide quantitative evidence of this trap, showing sophisticated baselines achieve 97.9% correlation yet 0.00 CSI for dangerous convection detection. We introduce DART (Dual Architecture for Regression Tasks), a framework addressing the challenge of transforming coarse atmospheric forecasts into high-resolution satellite brightness temperature fields optimized for extreme convection detection (below 220 K). DART employs dual-decoder architecture with explicit background/extreme decomposition, physically motivated oversampling, and task-specific loss functions. We present four key findings: (1) empirical validation of the Statistical Similarity Trap across multiple sophisticated baselines; (2) the "IVT Paradox", removing Integrated Water Vapor Transport, widely regarded as essential for atmospheric river analysis, improves extreme convection detection by 270%; (3) architectural necessity demonstrated through operational flexibility (DART achieves CSI = 0.273 with bias = 2.52 vs. 6.72 for baselines at equivalent CSI), and (4) real-world validation with the August 2023 Chittagong flooding disaster as a case study. To our knowledge, this is the first work to systematically address this hybrid conversion-segmentation-downscaling task, with no direct prior benchmarks identified in existing literature. Our validation against diverse statistical and deep learning baselines sufficiently demonstrates DART's specialized design. The framework enables precise operational calibration through beta-tuning, trains in under 10 minutes on standard hardware, and integrates seamlessly with existing meteorological workflows, demonstrating a pathway toward trustworthy AI for extreme weather preparedness.
【4】Deep Context-Conditioned Anomaly Detection for Tabular Data
标题：表格数据的深度上下文条件异常检测
链接：https://arxiv.org/abs/2509.09030
备注：Submitted to WSDM 2026. 11 pages, 4 figures, 5 tables, 1 algorithm, 8 datasets, contextual anomaly detection framework for tabular data
摘要：异常检测在网络安全和金融等领域至关重要，特别是在处理大规模表格数据时。然而，无监督的异常检测-没有标记的异常-仍然是一个重大的挑战。尽管已经提出了各种深度学习方法来对数据集的联合分布进行建模，但现实世界的表格数据通常包含异构上下文（例如，不同的用户），使全球罕见的事件在某些情况下正常。因此，依赖于单一的全局分布可能会忽略这些上下文的细微差别，降低检测性能。在本文中，我们提出了一个上下文条件的异常检测框架定制的表格数据集。我们的方法自动识别上下文特征，并使用简单的深度自动编码器对条件数据分布进行建模。在多个表格基准数据集上进行的大量实验表明，我们的方法优于最先进的方法，强调了上下文在准确区分异常和正常实例方面的重要性。
摘要：Anomaly detection is critical in domains such as cybersecurity and finance, especially when working with large-scale tabular data. Yet, unsupervised anomaly detection -- where no labeled anomalies are available -- remains a significant challenge. Although various deep learning methods have been proposed to model a dataset's joint distribution, real-world tabular data often contain heterogeneous contexts (e.g., different users), making globally rare events normal under certain contexts. Consequently, relying on a single global distribution can overlook these contextual nuances, degrading detection performance. In this paper, we present a context-conditional anomaly detection framework tailored for tabular datasets. Our approach automatically identifies context features and models the conditional data distribution using a simple deep autoencoder. Extensive experiments on multiple tabular benchmark datasets demonstrate that our method outperforms state-of-the-art approaches, underscoring the importance of context in accurately distinguishing anomalous from normal instances.
【5】Similarity-based Outlier Detection for Noisy Object Re-Identification Using Beta Mixtures
标题：使用Beta混合的基于相似性的离群点检测用于有噪对象重新识别
链接：https://arxiv.org/abs/2509.08926
摘要：对象重新识别（Re-ID）方法对标签噪声高度敏感，这通常导致显著的性能下降。我们通过将Re-ID重新构建为监督图像相似性任务并采用经过训练的Siamese网络架构来捕获区分性成对关系来解决这一挑战。我们的方法的核心是一种新的统计离群值检测（OD）框架，称为Beta-SOD（基于Beta混合相似性的离群值检测），它使用双分量Beta分布混合模型对嵌入对之间的余弦相似性分布进行建模。我们为两个Beta分布的混合物建立了一个新的可识别性结果，确保我们的学习任务是适定性的。所提出的OD步骤补充了Re-ID架构，该架构结合了二进制交叉熵，对比度和余弦嵌入损失，共同优化了特征级相似性学习。我们证明了Beta-SOD在去噪和Re-ID任务中的有效性。CUHK 03和Market-1501数据集，以及VeRi-776数据集上的车辆Re-ID。我们的方法在各种噪声水平（10-30\%）下显示出优于最先进方法的性能，证明了在嘈杂的Re-ID场景中的鲁棒性和广泛的适用性。Beta-SOD的实施可在以下网址获得：https://github.com/waqar3411/Beta-SOD
摘要：Object re-identification (Re-ID) methods are highly sensitive to label noise, which typically leads to significant performance degradation. We address this challenge by reframing Re-ID as a supervised image similarity task and adopting a Siamese network architecture trained to capture discriminative pairwise relationships. Central to our approach is a novel statistical outlier detection (OD) framework, termed Beta-SOD (Beta mixture Similarity-based Outlier Detection), which models the distribution of cosine similarities between embedding pairs using a two-component Beta distribution mixture model. We establish a novel identifiability result for mixtures of two Beta distributions, ensuring that our learning task is well-posed.The proposed OD step complements the Re-ID architecture combining binary cross-entropy, contrastive, and cosine embedding losses that jointly optimize feature-level similarity learning.We demonstrate the effectiveness of Beta-SOD in de-noising and Re-ID tasks for person Re-ID, on CUHK03 and Market-1501 datasets, and vehicle Re-ID, on VeRi-776 dataset. Our method shows superior performance compared to the state-of-the-art methods across various noise levels (10-30\%), demonstrating both robustness and broad applicability in noisy Re-ID scenarios. The implementation of Beta-SOD is available at: https://github.com/waqar3411/Beta-SOD
表征(1篇)
【1】A Masked Representation Learning to Model Cardiac Functions Using Multiple Physiological Signals
标题：掩蔽表示学习使用多种生理信号对心脏功能建模
链接：https://arxiv.org/abs/2509.08830
备注：16 pages, 5 figures
摘要：在临床环境中，监测血流动力学对于管理患者预后至关重要，需要对多种生理信号进行综合分析。虽然最近的研究已经分析了单一信号，如心电图（ECG）或光电容积描记（PPG），但还没有提出一种方法，包括实际临床场景中所需的复杂信号分析。在这项研究中，我们介绍了SNUPHY-M（首尔国立大学医院生理信号掩蔽表示学习）模型提取反映电，压力和流体特性的心动周期的生理特征的过程中恢复基于自监督学习（SSL）的三个掩蔽的生理信号：ECG，PPG和动脉血压（ABP）信号。通过采用多种物理特征，该模型可以只使用非侵入性信号来提取更丰富的特征。我们评估了该模型在临床下游任务中的性能，如低血压、每搏输出量、收缩压、舒张压和年龄预测。我们的研究结果表明，SNUPHY-M显著优于监督或SSL模型，特别是在使用非侵入性信号的预测任务中。据我们所知，SNUPHY-M是第一个将多模态SSL应用于心血管分析的模型，包括ECG，PPG和ABP信号。这种方法有效地支持临床决策，并实现精确的诊断，大大有助于早期诊断和无创血流动力学管理。
摘要：In clinical settings, monitoring hemodynamics is crucial for managing patient prognosis, necessitating the integrated analysis of multiple physiological signals. While recent research has analyzed single signals such as electrocardiography (ECG) or photoplethysmography (PPG), there has yet to be a proposal for an approach that encompasses the complex signal analysis required in actual clinical scenarios. In this study, we introduce the SNUPHY-M (Seoul National University hospital PHYsiological signal Masked representation learning) model extracts physiological features reflecting the electrical, pressure, and fluid characteristics of the cardiac cycle in the process of restoring three masked physiological signals based on self-supervised learning (SSL): ECG, PPG, and arterial blood pressure (ABP) signals. By employing multiple physical characteristics, the model can extract more enriched features only using non-invasive signals. We evaluated the model's performance in clinical downstream tasks such as hypotension, stroke volume, systolic blood pressure, diastolic blood pressure, and age prediction. Our results showed that the SNUPHY-M significantly outperformed supervised or SSL models, especially in prediction tasks using non-invasive signals. To the best of our knowledge, SNUPHY-M is the first model to apply multi-modal SSL to cardiovascular analysis involving ECG, PPG, and ABP signals. This approach effectively supports clinical decision-making and enables precise diagnostics, contributing significantly to the early diagnosis and management of hemodynamics without invasiveness.
优化|敛散性(4篇)
【1】Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates
标题：具有近优速率的抗破坏异步Q学习
链接：https://arxiv.org/abs/2509.08933
摘要：我们考虑在折扣，无限时域强化学习（RL）设置中学习最优策略的问题，其中奖励信号受到对抗性腐败的影响。这种腐败，这可能会引起极端的噪声，传感器故障，或恶意攻击，可以严重降低经典算法，如Q学习的性能。为了解决这一挑战，我们提出了一个新的可证明的强大的Q学习算法的变种，有效地运行，即使一小部分的观察到的奖励被任意扰动的对手。在时间相关数据的异步采样模型下，我们建立了尽管对抗性腐败，我们的算法的有限时间收敛速度与非对抗性情况下的现有结果相匹配，直到与腐败样本的分数成比例的附加项。此外，我们推导出一个信息理论的下限揭示了我们的上限中的添加剂腐败项是不可避免的。 接下来，我们提出了一种算法的变体，它不需要真实奖励分布的统计信息的先验知识。这种设置的分析是特别具有挑战性的，并通过仔细利用一个精炼的Azuma-Hoeffding不等式几乎鞅，一个技术工具，可能是独立的利益。总的来说，我们的贡献为异步Q学习提供了第一个有限时间鲁棒性保证，弥合了鲁棒RL的重大差距。
摘要：We consider the problem of learning the optimal policy in a discounted, infinite-horizon reinforcement learning (RL) setting where the reward signal is subject to adversarial corruption. Such corruption, which may arise from extreme noise, sensor faults, or malicious attacks, can severely degrade the performance of classical algorithms such as Q-learning. To address this challenge, we propose a new provably robust variant of the Q-learning algorithm that operates effectively even when a fraction of the observed rewards are arbitrarily perturbed by an adversary. Under the asynchronous sampling model with time-correlated data, we establish that despite adversarial corruption, the finite-time convergence rate of our algorithm matches that of existing results for the non-adversarial case, up to an additive term proportional to the fraction of corrupted samples. Moreover, we derive an information-theoretic lower bound revealing that the additive corruption term in our upper bounds is unavoidable. Next, we propose a variant of our algorithm that requires no prior knowledge of the statistics of the true reward distributions. The analysis of this setting is particularly challenging and is enabled by carefully exploiting a refined Azuma-Hoeffding inequality for almost-martingales, a technical tool that might be of independent interest. Collectively, our contributions provide the first finite-time robustness guarantees for asynchronous Q-learning, bridging a significant gap in robust RL.
【2】Instance-Optimal Matrix Multiplicative Weight Update and Its Quantum Applications
标题：实例最优矩阵乘权更新及其量子应用
链接：https://arxiv.org/abs/2509.08911
备注：47 pages
摘要：矩阵乘性权值更新算法（MMWU）是一种开创性的在线学习算法，具有广泛的应用。应用到矩阵版本的学习专家咨询（LEA）问题上的$d$维spectraplex，众所周知，MMWU达到最小最大最优后悔界$O（\sqrt{T\log d}）$，其中$T$是时间范围。本文提出了一种改进的算法，该算法的实例最优后悔界为O（\sqrt{T\cdot S（X|| d^{-1}I_d）}）$，其中$X$是后悔中的比较器，$I_d$是单位矩阵，$S（\cdot||\cdot）$表示量子相对熵。此外，我们的算法具有相同的计算复杂度MMWU，表明在遗憾界的改善是“免费的”。 在技术上，我们首先开发了一个通用的潜在的框架矩阵LEA，MMWU是其特殊情况下诱导的标准指数势。然后，我们的分析的关键是一个新的“单边”詹森的迹不等式建立在拉普拉斯变换技术，它允许应用的一般潜在的功能超出指数矩阵LEA。我们的算法是最后诱导的最佳潜在的功能，从矢量LEA问题的基础上虚误差函数。 作为对上述算法的补充，我们给出了矩阵LEA的记忆下界，并探讨了该算法在量子学习理论中的应用。我们表明，它优于最先进的学习被去极化噪声，随机量子态和吉布斯态破坏的量子态。此外，将我们的算法应用于线性化凸损失，可以预测非线性量子特性，如纯度，量子虚冷却，和R\'{e}nyi-$2$相关性。
摘要 ：The Matrix Multiplicative Weight Update (MMWU) is a seminal online learning algorithm with numerous applications. Applied to the matrix version of the Learning from Expert Advice (LEA) problem on the $d$-dimensional spectraplex, it is well known that MMWU achieves the minimax-optimal regret bound of $O(\sqrt{T\log d})$, where $T$ is the time horizon. In this paper, we present an improved algorithm achieving the instance-optimal regret bound of $O(\sqrt{T\cdot S(X||d^{-1}I_d)})$, where $X$ is the comparator in the regret, $I_d$ is the identity matrix, and $S(\cdot||\cdot)$ denotes the quantum relative entropy. Furthermore, our algorithm has the same computational complexity as MMWU, indicating that the improvement in the regret bound is ``free''. Technically, we first develop a general potential-based framework for matrix LEA, with MMWU being its special case induced by the standard exponential potential. Then, the crux of our analysis is a new ``one-sided'' Jensen's trace inequality built on a Laplace transform technique, which allows the application of general potential functions beyond exponential to matrix LEA. Our algorithm is finally induced by an optimal potential function from the vector LEA problem, based on the imaginary error function. Complementing the above, we provide a memory lower bound for matrix LEA, and explore the applications of our algorithm in quantum learning theory. We show that it outperforms the state of the art for learning quantum states corrupted by depolarization noise, random quantum states, and Gibbs states. In addition, applying our algorithm to linearized convex losses enables predicting nonlinear quantum properties, such as purity, quantum virtual cooling, and R\'{e}nyi-$2$ correlation.
【3】Global Optimization of Stochastic Black-Box Functions with Arbitrary Noise Distributions using Wilson Score Kernel Density Estimation
标题：使用Wilson得分核密度估计对任意噪音分布的随机黑匣子函数进行全局优化
链接：https://arxiv.org/abs/2509.09238
摘要：机器人技术中的许多优化问题涉及时间昂贵的黑箱函数的优化，例如涉及复杂模拟或真实世界实验评估的优化。此外，这些功能往往是随机的，因为重复的实验受到不可测量的干扰。贝叶斯优化可以用于通过部署概率函数估计器来以给定置信度进行估计，从而可以修剪掉搜索空间的区域，从而以有效的方式优化这种方法。因此，贝叶斯优化的成功取决于函数估计器提供信息性置信界限的能力。现有的函数估计器需要许多函数评估来推断潜在的置信度或依赖于扰动的建模。在本文中，它是由威尔逊得分核密度估计（WS-KDE）提供的置信界限是适用于任何随机函数的输出被限制在封闭的区间[0;1]，而不管输出的分布。这一发现开辟了使用WS-KDE在更广泛的成本函数上进行稳定的全局优化。WS-KDE在贝叶斯优化的背景下的属性在模拟中被证明，并应用于振动部分给料器的自动陷阱设计的问题。
摘要：Many optimization problems in robotics involve the optimization of time-expensive black-box functions, such as those involving complex simulations or evaluation of real-world experiments. Furthermore, these functions are often stochastic as repeated experiments are subject to unmeasurable disturbances. Bayesian optimization can be used to optimize such methods in an efficient manner by deploying a probabilistic function estimator to estimate with a given confidence so that regions of the search space can be pruned away. Consequently, the success of the Bayesian optimization depends on the function estimator's ability to provide informative confidence bounds. Existing function estimators require many function evaluations to infer the underlying confidence or depend on modeling of the disturbances. In this paper, it is shown that the confidence bounds provided by the Wilson Score Kernel Density Estimator (WS-KDE) are applicable as excellent bounds to any stochastic function with an output confined to the closed interval [0;1] regardless of the distribution of the output. This finding opens up the use of WS-KDE for stable global optimization on a wider range of cost functions. The properties of WS-KDE in the context of Bayesian optimization are demonstrated in simulation and applied to the problem of automated trap design for vibrational part feeders.
【4】Convexity of Optimization Curves: Local Sharp Thresholds, Robustness Impossibility, and New Counterexamples
标题：优化曲线的凸性：局部尖锐阈值、鲁棒性不可能性和新反例
链接：https://arxiv.org/abs/2509.08954
摘要：本文研究了一阶方法的最优化曲线--由常数步长迭代产生的序列f（xn）} n ge 0--何时是凸的，等价地研究了前向差分f（xn）-f（x n+1）不增时的最优化曲线.对于凸L-光滑函数的梯度下降（GD），对于所有步长η 1.75/L，曲线都是凸的，并且这个阈值是紧的。此外，梯度范数对所有\$\eta \le 2/L\$都是非增的，并且在连续时间（梯度流）中曲线总是凸的。这些结果补充和完善经典的光滑凸优化工具箱，连接离散和连续动态以及最坏情况下的分析。
摘要：We study when the \emph{optimization curve} of first--order methods -- the sequence \${f(x\_n)}*{n\ge0}\$ produced by constant--stepsize iterations -- is convex, equivalently when the forward differences \$f(x\_n)-f(x*{n+1})\$ are nonincreasing. For gradient descent (GD) on convex \$L\$--smooth functions, the curve is convex for all stepsizes \$\eta \le 1.75/L\$, and this threshold is tight. Moreover, gradient norms are nonincreasing for all \$\eta \le 2/L\$, and in continuous time (gradient flow) the curve is always convex. These results complement and refine the classical smooth convex optimization toolbox, connecting discrete and continuous dynamics as well as worst--case analyses.
预测|估计(3篇)
【1】Functional Groups are All you Need for Chemically Interpretable Molecular Property Prediction
标题：化学可解释分子性质预测所需的全部功能团
链接：https://arxiv.org/abs/2509.09619
摘要：使用深度学习（DL）模型进行分子性质预测加速了药物和材料的发现，但由此产生的DL模型往往缺乏可解释性，阻碍了化学家的采用。这项工作提出了开发分子表示使用化学中的官能团（FG）的概念。我们介绍了官能团表示（FGR）框架，一种新的方法来编码分子的基础上，他们的基本化学亚结构。我们的方法集成了两种类型的官能团：从建立的化学知识（FG）策划，和那些从一个大的分子语料库使用序列模式挖掘（MFG）挖掘。由此产生的FGR框架通过利用未标记分子的大型数据集的预训练将分子编码到低维潜在空间中。此外，所提出的框架允许包含基于2D结构的分子描述符。我们证明了FGR框架在涵盖物理化学，生物物理学，量子力学，生物活性和药代动力学的33个基准数据集上实现了最先进的性能，同时实现了化学可解释性。至关重要的是，该模型的表示本质上与既定的化学原理一致，允许化学家将预测的性质直接与特定的官能团联系起来，并促进对结构-性质关系的新见解。我们的工作为开发高性能，化学可解释的分子发现DL模型迈出了重要的一步。
摘要：Molecular property prediction using deep learning (DL) models has accelerated drug and materials discovery, but the resulting DL models often lack interpretability, hindering their adoption by chemists. This work proposes developing molecule representations using the concept of Functional Groups (FG) in chemistry. We introduce the Functional Group Representation (FGR) framework, a novel approach to encoding molecules based on their fundamental chemical substructures. Our method integrates two types of functional groups: those curated from established chemical knowledge (FG), and those mined from a large molecular corpus using sequential pattern mining (MFG). The resulting FGR framework encodes molecules into a lower-dimensional latent space by leveraging pre-training on a large dataset of unlabeled molecules. Furthermore, the proposed framework allows the inclusion of 2D structure-based descriptors of molecules. We demonstrate that the FGR framework achieves state-of-the-art performance on a diverse range of 33 benchmark datasets spanning physical chemistry, biophysics, quantum mechanics, biological activity, and pharmacokinetics while enabling chemical interpretability. Crucially, the model's representations are intrinsically aligned with established chemical principles, allowing chemists to directly link predicted properties to specific functional groups and facilitating novel insights into structure-property relationships. Our work presents a significant step toward developing high-performing, chemically interpretable DL models for molecular discovery.
【2】Learning What Matters: Causal Time Series Modeling for Arctic Sea Ice Prediction
标题：学习什么是重要的：北极海冰预测的因果时间序列模型
链接：https://arxiv.org/abs/2509.09128
备注：Accepted and presented at the AI4TS Workshop @ IJCAI 2025 (non-archival)
摘要：传统的机器学习和深度学习模型通常依赖于基于相关性的学习，这通常无法区分真正的因果关系和虚假的关联，限制了它们的鲁棒性，可解释性和泛化能力。为了克服这些限制，我们引入了一个感知因果关系的深度学习框架，该框架集成了多变量格兰杰因果关系（MVGC）和PCMCI+，用于混合神经架构中的因果特征选择。利用43年（1979-2021年）的北极海冰范围（SIE）数据和相关的海洋-大气变量在每日和每月的分辨率，所提出的方法确定因果影响的预测，优先考虑SIE动态的直接原因，减少不必要的功能，并提高计算效率。实验结果表明，将因果输入导致提高预测精度和可解释性在不同的前置时间。虽然在北极SIE预测上得到了证明，但该框架广泛适用于其他动态的高维域，提供了一种可扩展的方法，可以提高容度预测建模的理论基础和实际性能。
摘要 ：Conventional machine learning and deep learning models typically rely on correlation-based learning, which often fails to distinguish genuine causal relationships from spurious associations, limiting their robustness, interpretability, and ability to generalize. To overcome these limitations, we introduce a causality-aware deep learning framework that integrates Multivariate Granger Causality (MVGC) and PCMCI+ for causal feature selection within a hybrid neural architecture. Leveraging 43 years (1979-2021) of Arctic Sea Ice Extent (SIE) data and associated ocean-atmospheric variables at daily and monthly resolutions, the proposed method identifies causally influential predictors, prioritizes direct causes of SIE dynamics, reduces unnecessary features, and enhances computational efficiency. Experimental results show that incorporating causal inputs leads to improved prediction accuracy and interpretability across varying lead times. While demonstrated on Arctic SIE forecasting, the framework is broadly applicable to other dynamic, high-dimensional domains, offering a scalable approach that advances both the theoretical foundations and practical performance of causality-informed predictive modeling.
【3】WarpPINN-fibers: improved cardiac strain estimation from cine-MR with physics-informed neural networks
标题：WarpPINN纤维：利用基于物理知识的神经网络从电影MR中改进心脏应变估计
链接：https://arxiv.org/abs/2509.08872
摘要：心脏的收缩运动主要由构成心脏组织的纤维的分布决定。应变分析告知纤维的取向允许描述通常与心肌受损力学相关的几种病理，例如心血管疾病。已经开发了几种方法来从传统成像技术估计应变导出的度量。然而，这些方法的物理模型不包括纤维力学，限制了它们准确解释心脏功能的能力。在这项工作中，我们引入了WarpPINN-fibers，这是一个物理信息神经网络框架，可以准确地获得纤维信息增强的心脏运动和应变。我们训练我们的神经网络，以满足超弹性模型，并促进纤维收缩的目标是预测从电影磁共振图像的心脏的变形场。为此，我们建立了一个损失函数，由三个方面组成：一个参考和扭曲的模板图像之间的数据相似性损失，一个正则化强制执行心脏组织的近不可压缩性和纤维拉伸惩罚，控制应变的方向合成生产的纤维。我们表明，我们的神经网络改进了以前的WarpPINN模型，并在合成体模实验中有效地控制纤维拉伸。然后，我们证明了WarpPINN纤维优于替代方法的地标跟踪和应变曲线预测的电影MRI基准与一个队列的15名健康志愿者。我们希望我们的方法能够通过与纤维生理学一致的准确变形场更精确地量化心脏应变，而不需要比MRI更复杂的成像技术。
摘要：The contractile motion of the heart is strongly determined by the distribution of the fibers that constitute cardiac tissue. Strain analysis informed with the orientation of fibers allows to describe several pathologies that are typically associated with impaired mechanics of the myocardium, such as cardiovascular disease. Several methods have been developed to estimate strain-derived metrics from traditional imaging techniques. However, the physical models underlying these methods do not include fiber mechanics, restricting their capacity to accurately explain cardiac function. In this work, we introduce WarpPINN-fibers, a physics-informed neural network framework to accurately obtain cardiac motion and strains enhanced by fiber information. We train our neural network to satisfy a hyper-elastic model and promote fiber contraction with the goal to predict the deformation field of the heart from cine magnetic resonance images. For this purpose, we build a loss function composed of three terms: a data-similarity loss between the reference and the warped template images, a regularizer enforcing near-incompressibility of cardiac tissue and a fiber-stretch penalization that controls strain in the direction of synthetically produced fibers. We show that our neural network improves the former WarpPINN model and effectively controls fiber stretch in a synthetic phantom experiment. Then, we demonstrate that WarpPINN-fibers outperforms alternative methodologies in landmark-tracking and strain curve prediction for a cine-MRI benchmark with a cohort of 15 healthy volunteers. We expect that our method will enable a more precise quantification of cardiac strains through accurate deformation fields that are consistent with fiber physiology, without requiring imaging techniques more sophisticated than MRI.
其他神经网络|深度学习|模型|建模(8篇)
【1】Conditioning on PDE Parameters to Generalise Deep Learning Emulation of Stochastic and Chaotic Dynamics
标题：对PCE参数进行调节以推广随机和混乱动力学的深度学习仿真
链接：https://arxiv.org/abs/2509.09599
摘要：我们提出了一个随机和混沌时空系统的深度学习仿真器，明确地以底层偏微分方程（PDE）的参数值为条件。我们的方法包括在单个参数域上对模型进行预训练，然后在较小但多样化的数据集上进行微调，从而实现广泛的参数值泛化。通过结合本地注意力机制，网络能够处理不同的域大小和分辨率。这使得在较小的域上进行计算高效的预训练，同时只需要一个小的额外数据集来学习如何推广到更大的域大小。我们展示了该模型的能力，混沌Kuramoto-Sivashinsky方程和随机强迫β-平面湍流，展示了它的能力，捕捉现象插值参数值。仿真器提供了显着的计算速度比传统的数值积分，促进有效的探索参数空间，而概率的仿真器的变体提供了不确定性量化，允许罕见事件的统计研究。
摘要：We present a deep learning emulator for stochastic and chaotic spatio-temporal systems, explicitly conditioned on the parameter values of the underlying partial differential equations (PDEs). Our approach involves pre-training the model on a single parameter domain, followed by fine-tuning on a smaller, yet diverse dataset, enabling generalisation across a broad range of parameter values. By incorporating local attention mechanisms, the network is capable of handling varying domain sizes and resolutions. This enables computationally efficient pre-training on smaller domains while requiring only a small additional dataset to learn how to generalise to larger domain sizes. We demonstrate the model's capabilities on the chaotic Kuramoto-Sivashinsky equation and stochastically-forced beta-plane turbulence, showcasing its ability to capture phenomena at interpolated parameter values. The emulator provides significant computational speed-ups over conventional numerical integration, facilitating efficient exploration of parameter space, while a probabilistic variant of the emulator provides uncertainty quantification, allowing for the statistical study of rare events.
【2】ObjectReact: Learning Object-Relative Control for Visual Navigation
标题：对象反应：学习视觉导航的对象相对控制
链接：https://arxiv.org/abs/2509.09594
备注：CoRL 2025; 23 pages including appendix
摘要：仅使用单个相机和拓扑地图的视觉导航最近已成为需要额外传感器和3D地图的方法的有吸引力的替代方案。这通常是通过一个“图像相关”的方法来估计控制从一个给定的对当前的观察和子目标图像。然而，世界的图像级表示具有局限性，因为图像严格地绑定到代理的姿势和具体化。相比之下，对象，作为地图的属性，提供了一个体现和不变性的世界表示。在这项工作中，我们提出了一种新的学习“对象相关”控制的范例，具有几个理想的特性：a）新的路线可以遍历，而不需要严格模仿以前的经验，b）控制预测问题可以从解决图像匹配问题解耦，和c）高不变性可以实现跨实施例部署的变化在两个训练测试和映射执行设置。我们提出了一个拓扑地图表示的形式“相对”的三维场景图，这是用来获得更多的信息对象级的全局路径规划成本。我们训练一个本地控制器，称为“ObjectReact”，直接以高级“WayObject Costmap”表示为条件，消除了对显式RGB输入的需要。我们展示了在传感器高度变化和挑战潜在空间理解能力的多个导航任务中，学习对象相对于其图像相对控制的优势，例如，在相反方向上导航地图轨迹。我们进一步表明，我们的模拟只有政策是能够推广到现实世界的室内环境。代码和补充材料可通过项目页面访问：https://object-react.github.io/
摘要 ：Visual navigation using only a single camera and a topological map has recently become an appealing alternative to methods that require additional sensors and 3D maps. This is typically achieved through an "image-relative" approach to estimating control from a given pair of current observation and subgoal image. However, image-level representations of the world have limitations because images are strictly tied to the agent's pose and embodiment. In contrast, objects, being a property of the map, offer an embodiment- and trajectory-invariant world representation. In this work, we present a new paradigm of learning "object-relative" control that exhibits several desirable characteristics: a) new routes can be traversed without strictly requiring to imitate prior experience, b) the control prediction problem can be decoupled from solving the image matching problem, and c) high invariance can be achieved in cross-embodiment deployment for variations across both training-testing and mapping-execution settings. We propose a topometric map representation in the form of a "relative" 3D scene graph, which is used to obtain more informative object-level global path planning costs. We train a local controller, dubbed "ObjectReact", conditioned directly on a high-level "WayObject Costmap" representation that eliminates the need for an explicit RGB input. We demonstrate the advantages of learning object-relative control over its image-relative counterpart across sensor height variations and multiple navigation tasks that challenge the underlying spatial understanding capability, e.g., navigating a map trajectory in the reverse direction. We further show that our sim-only policy is able to generalize well to real-world indoor environments. Code and supplementary material are accessible via project page: https://object-react.github.io/
【3】DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning
标题：DeMeVaat LeWiDi-2025：通过上下文学习和标签分布学习建模观点
链接：https://arxiv.org/abs/2509.09524
备注：11 pages, 4 figures; to appear at NLPerspectives@EMNLP-2025
摘要：这篇系统论文介绍了DeMeVa团队对第三版“带分歧学习”共享任务的方法（LeWiDi 2025; Leonardelli et al.，2025年）。我们探索两个方向：使用大型语言模型的上下文学习（ICL），其中我们比较了示例采样策略;以及使用RoBERTa的标签分布学习（LDL）方法（Liu等人，2019年b），在那里我们评估了几种微调方法。我们的贡献有两个方面：（1）我们表明，ICL可以有效地预测特定于注释者的注释（透视主义注释），并且将这些预测聚合到软标签中会产生有竞争力的性能;（2）我们认为LDL方法对软标签预测很有前途，值得透视主义社区进一步探索。
摘要：This system paper presents the DeMeVa team's approaches to the third edition of the Learning with Disagreements shared task (LeWiDi 2025; Leonardelli et al., 2025). We explore two directions: in-context learning (ICL) with large language models, where we compare example sampling strategies; and label distribution learning (LDL) methods with RoBERTa (Liu et al., 2019b), where we evaluate several fine-tuning methods. Our contributions are twofold: (1) we show that ICL can effectively predict annotator-specific annotations (perspectivist annotations), and that aggregating these predictions into soft labels yields competitive performance; and (2) we argue that LDL methods are promising for soft label predictions and merit further exploration by the perspectivist community.
【4】Expressive Power of Deep Networks on Manifolds: Simultaneous Approximation
标题：深度网络在Manifold上的表现力：同时逼近
链接：https://arxiv.org/abs/2509.09362
摘要：A key challenge in scientific machine learning is solving partial differential equations (PDEs) on complex domains, where the curved geometry complicates the approximation of functions and their derivatives required by differential operators. This paper establishes the first simultaneous approximation theory for deep neural networks on manifolds. We prove that a constant-depth $\mathrm{ReLU}^{k-1}$ network with bounded weights--a property that plays a crucial role in controlling generalization error--can approximate any function in the Sobolev space $\mathcal{W}_p^{k}(\mathcal{M}^d)$ to an error of $\varepsilon$ in the $\mathcal{W}_p^{s}(\mathcal{M}^d)$ norm, for $k\geq 3$ and $s摘要：A key challenge in scientific machine learning is solving partial differential equations (PDEs) on complex domains, where the curved geometry complicates the approximation of functions and their derivatives required by differential operators. This paper establishes the first simultaneous approximation theory for deep neural networks on manifolds. We prove that a constant-depth $\mathrm{ReLU}^{k-1}$ network with bounded weights--a property that plays a crucial role in controlling generalization error--can approximate any function in the Sobolev space $\mathcal{W}_p^{k}(\mathcal{M}^d)$ to an error of $\varepsilon$ in the $\mathcal{W}_p^{s}(\mathcal{M}^d)$ norm, for $k\geq 3$ and $s
【5】An entropy formula for the Deep Linear Network
标题：深度线性网络的信息量公式
链接：https://arxiv.org/abs/2509.09088
摘要：我们研究深度线性网络（DLN）的黎曼几何，作为学习过程热力学描述的基础。主要的工具是使用组行动来分析overparametrization和使用黎曼淹没从空间的参数空间的可观的空间。利用群轨道对参数空间中的平衡流形进行叶状，来定义和计算玻尔兹曼熵。我们还证明了在[2]中定义的观测量空间上的黎曼几何是通过平衡流形的黎曼浸没而得到的。主要的技术步骤是一个明确的结构的正交基的切空间的平衡流形的Jacobi矩阵的理论。
摘要 ：We study the Riemannian geometry of the Deep Linear Network (DLN) as a foundation for a thermodynamic description of the learning process. The main tools are the use of group actions to analyze overparametrization and the use of Riemannian submersion from the space of parameters to the space of observables. The foliation of the balanced manifold in the parameter space by group orbits is used to define and compute a Boltzmann entropy. We also show that the Riemannian geometry on the space of observables defined in [2] is obtained by Riemannian submersion of the balanced manifold. The main technical step is an explicit construction of an orthonormal basis for the tangent space of the balanced manifold using the theory of Jacobi matrices.
【6】KoopMotion: Learning Almost Divergence Free Koopman Flow Fields for Motion Planning
标题：KoopMotion：学习几乎无分歧的Koopman流场，用于运动规划
链接：https://arxiv.org/abs/2509.09074
备注：Accepted to CoRL 2025 (Conference on Robot Learning). 15 pages 11 figures
摘要：在这项工作中，我们提出了一种新的基于流场的运动规划方法，驱动机器人从任何初始状态到所需的参考轨迹，使其收敛到轨迹的终点。尽管在使用Koopman算子理论对动态系统建模方面表现出了有效性，但Koopman并不固有地强制收敛到期望的轨迹或指定的目标-这是从演示中学习（LfD）时的要求。我们提出了KoopMotion，它表示运动流场作为动力系统，参数化的Koopman算子来模仿所需的轨迹，并利用学习流场的发散特性，以获得平滑的运动场，收敛到所需的参考轨迹时，机器人被放置远离所需的轨迹，并跟踪轨迹，直到终点。为了证明我们的方法的有效性，我们展示了KoopMotion在LASA人类手写数据集和3D机械手末端执行器轨迹数据集上的评估，包括频谱分析。我们还进行实验的物理机器人，验证KoopMotion的微型自主表面车辆在非静态流体流动环境中运行。我们的方法在空间和时间上都具有很高的采样效率，只需要3%的LASA数据集就可以生成密集的运动计划。此外，KoopMotion在比较衡量空间和时间动态建模效率的指标时，比基线有了显著的改进。
摘要：In this work, we propose a novel flow field-based motion planning method that drives a robot from any initial state to a desired reference trajectory such that it converges to the trajectory's end point. Despite demonstrated efficacy in using Koopman operator theory for modeling dynamical systems, Koopman does not inherently enforce convergence to desired trajectories nor to specified goals -- a requirement when learning from demonstrations (LfD). We present KoopMotion which represents motion flow fields as dynamical systems, parameterized by Koopman Operators to mimic desired trajectories, and leverages the divergence properties of the learnt flow fields to obtain smooth motion fields that converge to a desired reference trajectory when a robot is placed away from the desired trajectory, and tracks the trajectory until the end point. To demonstrate the effectiveness of our approach, we show evaluations of KoopMotion on the LASA human handwriting dataset and a 3D manipulator end-effector trajectory dataset, including spectral analysis. We also perform experiments on a physical robot, verifying KoopMotion on a miniature autonomous surface vehicle operating in a non-static fluid flow environment. Our approach is highly sample efficient in both space and time, requiring only 3\% of the LASA dataset to generate dense motion plans. Additionally, KoopMotion provides a significant improvement over baselines when comparing metrics that measure spatial and temporal dynamics modeling efficacy.
【7】A Scoping Review of Machine Learning Applications in Power System Protection and Disturbance Management
标题：机器学习在电力系统保护和干扰管理中应用的范围审查
链接：https://arxiv.org/abs/2509.09053
摘要：可再生能源和分布式能源的整合重塑了现代电力系统，挑战了传统的保护方案。该范围审查综合了最近关于机器学习（ML）在电力系统保护和干扰管理中应用的文献，遵循PRISMA范围审查框架。基于100多篇出版物，解决了三个关键目标：（i）评估ML在保护任务中的研究范围;（ii）评估ML在不同操作场景中的性能;（iii）确定适合不断变化的电网条件的方法。ML模型通常在模拟数据集上表现出很高的准确性;然而，它们在现实世界条件下的性能仍然没有得到充分的验证。现有的文献是零散的，在方法的严谨性，数据集的质量和评价指标不一致。这种缺乏标准化的情况妨碍了结果的可比性，并限制了调查结果的普遍性。为了应对这些挑战，本次审查介绍了ML为导向的分类保护任务，解决关键的术语不一致，并倡导标准化的报告实践。它还为全面的数据集文件、方法透明度和一致的评估方案提供了指导方针，旨在提高可重复性并增强研究成果的实际相关性。关键的差距仍然存在，包括缺乏真实世界的验证，鲁棒性测试不足，以及对部署可行性的考虑有限。未来的研究应该优先考虑公共基准数据集，现实的验证方法和先进的ML架构。这些步骤对于将基于ML的保护从理论承诺转移到日益动态和分散的电力系统中的实际部署至关重要。
摘要：The integration of renewable and distributed energy resources reshapes modern power systems, challenging conventional protection schemes. This scoping review synthesizes recent literature on machine learning (ML) applications in power system protection and disturbance management, following the PRISMA for Scoping Reviews framework. Based on over 100 publications, three key objectives are addressed: (i) assessing the scope of ML research in protection tasks; (ii) evaluating ML performance across diverse operational scenarios; and (iii) identifying methods suitable for evolving grid conditions. ML models often demonstrate high accuracy on simulated datasets; however, their performance under real-world conditions remains insufficiently validated. The existing literature is fragmented, with inconsistencies in methodological rigor, dataset quality, and evaluation metrics. This lack of standardization hampers the comparability of results and limits the generalizability of findings. To address these challenges, this review introduces a ML-oriented taxonomy for protection tasks, resolves key terminological inconsistencies, and advocates for standardized reporting practices. It further provides guidelines for comprehensive dataset documentation, methodological transparency, and consistent evaluation protocols, aiming to improve reproducibility and enhance the practical relevance of research outcomes. Critical gaps remain, including the scarcity of real-world validation, insufficient robustness testing, and limited consideration of deployment feasibility. Future research should prioritize public benchmark datasets, realistic validation methods, and advanced ML architectures. These steps are essential to move ML-based protection from theoretical promise to practical deployment in increasingly dynamic and decentralized power systems.
【8】ForTIFAI: Fending Off Recursive Training Induced Failure for AI Models
标题：ForTIFAI：抵御AI模型的递归训练导致的失败
链接：https://arxiv.org/abs/2509.08972
摘要：对生成式人工智能模型的日益依赖加快了合成数据的生成速度，一些预测表明，到2030年，大多数可用于训练的新数据都可能是机器生成的。这种向主要合成内容的转变带来了一个关键挑战：在合成数据中重复训练会导致一种称为模型崩溃的现象，即模型性能随着几代人的训练而下降，最终导致模型无效。虽然先前的研究已经探讨了模型崩溃的原因和检测，现有的缓解策略仍然有限。 在本文中，我们将模型对自己生成的数据的过度自信确定为崩溃的关键驱动因素。基于这一观察，我们提出了一个置信度感知的损失函数，在训练过程中降低高置信度预测的权重。我们引入了一个新的损失函数，我们称之为截断交叉熵（TCE）。我们证明，TCE显着延迟模型崩溃的递归训练。 我们提供了一个模型不可知的框架，将损失函数设计与模型崩溃缓解联系起来，并从理论和经验上验证了我们的方法，表明它可以将模型崩溃前的保真度区间扩展2.3倍以上。最后，我们表明，我们的方法推广跨模态。这些研究结果表明，损失函数的设计提供了一个简单而强大的工具，在越来越多的合成数据的时代，保持生成模型的质量。
摘要 ：The increasing reliance on generative AI models has accelerated the generation rate of synthetic data, with some projections suggesting that most available new data for training could be machine-generated by 2030. This shift to a mainly synthetic content presents a critical challenge: repeated training in synthetic data leads to a phenomenon known as model collapse, where model performance degrades over generations of training, eventually rendering the models ineffective. Although prior studies have explored the causes and detection of model collapse, existing mitigation strategies remain limited. In this paper, we identify model overconfidence in their self-generated data as a key driver of collapse. Building on this observation, we propose a confidence-aware loss function that downweights high-confidence predictions during training. We introduce a novel loss function we call Truncated Cross Entropy (TCE). We demonstrate that TCE significantly delays model collapse in recursive training. We provide a model-agnostic framework that links the loss function design to model collapse mitigation and validate our approach both theoretically and empirically, showing that it can extend the model's fidelity interval before collapse by more than 2.3x. Finally, we show that our method generalizes across modalities. These findings suggest that the design of loss functions provides a simple yet powerful tool for preserving the quality of generative models in the era of increasing synthetic data.
其他(19篇)
【1】Explaining Concept Drift through the Evolution of Group Counterfactuals
标题：通过群体反事实演变解释概念漂移
链接：https://arxiv.org/abs/2509.09616
备注：TempXAI Workshop @ ECML PKDD 2025
摘要：动态环境中的机器学习模型通常会遭受概念漂移，其中数据分布的变化会降低性能。虽然检测这种漂移是一个深入研究的主题，但解释模型的决策逻辑如何以及为什么会发生变化仍然是一个重大挑战。在本文中，我们介绍了一种新的方法来解释概念漂移，通过分析的时间演变的群体为基础的反事实解释（GCE）。我们的方法跟踪GCE的集群质心和其相关的反事实动作向量之前和之后的漂移的变化。这些不断发展的GCE作为一个可解释的代理，揭示了模型的决策边界及其基本原理的结构变化。我们在一个三层框架内操作这种分析，该框架协同结合了数据层（分布变化），模型层（预测不一致）和我们提出的解释层的见解。我们表明，这种整体的观点允许更全面的诊断漂移，使人们有可能区分不同的根本原因，如空间数据转移与重新标记的概念。
摘要：Machine learning models in dynamic environments often suffer from concept drift, where changes in the data distribution degrade performance. While detecting this drift is a well-studied topic, explaining how and why the model's decision-making logic changes still remains a significant challenge. In this paper, we introduce a novel methodology to explain concept drift by analyzing the temporal evolution of group-based counterfactual explanations (GCEs). Our approach tracks shifts in the GCEs' cluster centroids and their associated counterfactual action vectors before and after a drift. These evolving GCEs act as an interpretable proxy, revealing structural changes in the model's decision boundary and its underlying rationale. We operationalize this analysis within a three-layer framework that synergistically combines insights from the data layer (distributional shifts), the model layer (prediction disagreement), and our proposed explanation layer. We show that such holistic view allows for a more comprehensive diagnosis of drift, making it possible to distinguish between different root causes, such as a spatial data shift versus a re-labeling of concepts.
【2】ReBaNO: Reduced Basis Neural Operator Mitigating Generalization Gaps and Achieving Discretization Invariance
标题：ReBaNO：简化基础神经运算符缓解概括差距并实现离散化不变性
链接：https://arxiv.org/abs/2509.09611
摘要：我们提出了一种新的数据精益算子学习算法，减少基神经算子（ReBaNO），解决了一组多个不同的输入偏微分方程。受缩减基方法和最近引入的生成式预训练物理信息神经网络的启发，ReBaNO依赖于数学上严格的贪婪算法，从底层开始自适应地离线构建其网络结构。通过特定于任务的激活函数进行知识蒸馏，使ReBaNO具有紧凑的架构，在嵌入物理的同时需要最小的在线计算成本。与PCA-Net、DeepONet、FNO和CNO等最先进的算子学习算法相比，数值结果表明，ReBaNO在消除/缩小分布内和分布外测试的泛化差距方面明显优于它们，并且是唯一实现严格离散化不变性的算子学习算法。
摘要：We propose a novel data-lean operator learning algorithm, the Reduced Basis Neural Operator (ReBaNO), to solve a group of PDEs with multiple distinct inputs. Inspired by the Reduced Basis Method and the recently introduced Generative Pre-Trained Physics-Informed Neural Networks, ReBaNO relies on a mathematically rigorous greedy algorithm to build its network structure offline adaptively from the ground up. Knowledge distillation via task-specific activation function allows ReBaNO to have a compact architecture requiring minimal computational cost online while embedding physics. In comparison to state-of-the-art operator learning algorithms such as PCA-Net, DeepONet, FNO, and CNO, numerical results demonstrate that ReBaNO significantly outperforms them in terms of eliminating/shrinking the generalization gap for both in- and out-of-distribution tests and being the only operator learning algorithm achieving strict discretization invariance.
【3】Finite Scalar Quantization Enables Redundant and Transmission-Robust Neural Audio Compression at Low Bit-rates
标题：有限标量量化实现低比特率冗余和传输鲁棒的神经音频压缩
链接：https://arxiv.org/abs/2509.09550
摘要：神经音频编解码器（NAC）由于其出色的率失真性能以及与作为音频生成的离散特征表示的大型语言模型（LLM）的兼容性，已越来越多地被用于语音处理任务。虽然大多数现有的编解码器依赖于残差矢量量化（RVQ），但有限标量量化（FSQ）最近已成为一种引人注目的替代方案，它简化了训练并原生支持单个码本。我们介绍了NeuCodec，一个基于FSQ的NAC，并表明FSQ编码烘烤的冗余产生的编码，这是强大的，当通过嘈杂的信道传输。首先，通过编码器蒸馏实验，我们表明，两个不同的编码器可以学习编码相同的音频到截然不同的代码序列，同时保持可比的重建质量与相同的量化器和解码器。其次，我们证明了FSQ具有非常优越的比特级扰动鲁棒性，通过比较RVQ和FSQ编解码器的性能时，模拟通过噪声信道的代码序列的传输。
摘要：Neural Audio Codecs (NACs) have become increasingly adopted in speech processing tasks due to their excellent rate-distortion performance and compatibility with Large Language Models (LLMs) as discrete feature representations for audio generation. While most existing codecs rely on Residual Vector Quantization (RVQ), Finite Scalar Quantization (FSQ) has recently emerged as a compelling alternative that simplifies training and natively supports single codebooks. We introduce NeuCodec, an FSQ-based NAC, and show that FSQ encodes baked-in redundancy which produces an encoding which is robust when transmitted through noisy channels. First, through an encoder distillation experiment, we show that two different encoders can learn to encode identical audio into vastly different code sequences whilst maintaining comparable reconstruction quality with the same quantizer and decoder. Second, we demonstrate that FSQ has vastly superior bit-level perturbation robustness by comparing the performance of RVQ and FSQ codecs when simulating the transmission of code sequences through a noisy channel.
【4】Balancing Utility and Privacy: Dynamically Private SGD with Random Projection
标题：平衡公用事业和隐私：动态私人新加坡元与随机投影
链接：https://arxiv.org/abs/2509.09485
备注：27 pages, 13 figures
摘要 ：随机优化是现代机器学习的关键推动因素，为各种任务生成有效的模型。然而，一些现有的工作已经表明，模型参数和梯度信息容易受到隐私泄漏。尽管差分私有SGD（DPSGD）解决了隐私问题，但其静态噪声机制会影响模型性能的误差范围。此外，随着模型参数的指数增长，使用随机优化器对这些模型进行有效学习变得更具挑战性。为了解决这些问题，我们引入了动态差分私有投影SGD（D2 P2-SGD）优化器。在D2 P2-SGD中，我们结合了两个重要的思想：（i）具有自动梯度裁剪的动态差分隐私（DDP）和（ii）具有SGD的随机投影，允许动态调整模型的效用和隐私之间的权衡。它在不同的目标函数上表现出可证明的次线性收敛速度，与最佳可用速度相匹配。理论分析进一步表明，DDP以牺牲隐私为代价获得了更好的效用，而随机投影可以实现更有效的模型学习。在不同数据集上的广泛实验表明，D2 P2-SGD在保持隐私的同时显着提高了准确性。我们的代码在这里可用。
摘要：Stochastic optimization is a pivotal enabler in modern machine learning, producing effective models for various tasks. However, several existing works have shown that model parameters and gradient information are susceptible to privacy leakage. Although Differentially Private SGD (DPSGD) addresses privacy concerns, its static noise mechanism impacts the error bounds for model performance. Additionally, with the exponential increase in model parameters, efficient learning of these models using stochastic optimizers has become more challenging. To address these concerns, we introduce the Dynamically Differentially Private Projected SGD (D2P2-SGD) optimizer. In D2P2-SGD, we combine two important ideas: (i) dynamic differential privacy (DDP) with automatic gradient clipping and (ii) random projection with SGD, allowing dynamic adjustment of the tradeoff between utility and privacy of the model. It exhibits provably sub-linear convergence rates across different objective functions, matching the best available rate. The theoretical analysis further suggests that DDP leads to better utility at the cost of privacy, while random projection enables more efficient model learning. Extensive experiments across diverse datasets show that D2P2-SGD remarkably enhances accuracy while maintaining privacy. Our code is available here.
【5】Kriging prior Regression: A Case for Kriging-Based Spatial Features with TabPFN in Soil Mapping
标题：Kriging先验回归：土壤制图中使用TabPFN基于Kriging的空间特征的案例
链接：https://arxiv.org/abs/2509.09408
摘要：机器学习和地统计学是两种根本不同的土壤性质预测和空间映射框架。地质统计学利用土壤属性的空间结构，而机器学习则捕捉可用的环境特征与土壤属性之间的关系。我们提出了一个混合框架，丰富了ML的空间背景，通过工程的“空间滞后”功能，从普通克里金。我们称这种方法为“克里金先验回归”（KpR），因为它遵循回归克里金的逆逻辑。为了评估这种方法，我们评估了KpR的点和概率预测性能，使用来自LimeSoDa的六个fieldscale数据集的TabPFN模型。这些数据集包括土壤有机碳，粘土含量和pH值，以及来自遥感和原位近端土壤传感的功能。与其他几种空间技术（例如，使用TabPFN的回归/残差克里金法），以及已建立的非空间机器学习算法（例如，随机森林）。最值得注意的是，与没有空间上下文的机器学习算法相比，它将平均R2显著提高了约30%。这种改进是由于TabPFN算法本身的强大预测性能和KpR特征提供的互补空间信息。TabPFN对于精确农业中常见的小样本预测任务特别有效，而KpR可以在近端土壤传感数据有限时补偿传感功能与土壤特性之间的弱关系。因此，我们的结论是，KPR与TabPFN是一个非常强大的和通用的建模框架，在精准农业数字土壤制图。
摘要：Machine learning and geostatistics are two fundamentally different frameworks for predicting and spatially mapping soil properties. Geostatistics leverages the spatial structure of soil properties, while machine learning captures the relationship between available environmental features and soil properties. We propose a hybrid framework that enriches ML with spatial context through engineering of 'spatial lag' features from ordinary kriging. We call this approach 'kriging prior regression' (KpR), as it follows the inverse logic of regression kriging. To evaluate this approach, we assessed both the point and probabilistic prediction performance of KpR, using the TabPFN model across six fieldscale datasets from LimeSoDa. These datasets included soil organic carbon, clay content, and pH, along with features derived from remote sensing and in-situ proximal soil sensing. KpR with TabPFN demonstrated reliable uncertainty estimates and more accurate predictions in comparison to several other spatial techniques (e.g., regression/residual kriging with TabPFN), as well as to established non-spatial machine learning algorithms (e.g., random forest). Most notably, it significantly improved the average R2 by around 30% compared to machine learning algorithms without spatial context. This improvement was due to the strong prediction performance of the TabPFN algorithm itself and the complementary spatial information provided by KpR features. TabPFN is particularly effective for prediction tasks with small sample sizes, common in precision agriculture, whereas KpR can compensate for weak relationships between sensing features and soil properties when proximal soil sensing data are limited. Hence, we conclude that KpR with TabPFN is a very robust and versatile modelling framework for digital soil mapping in precision agriculture.
【6】Robust Non-Linear Correlations via Polynomial Regression
标题：通过多元回归实现稳健的非线性相关性
链接：https://arxiv.org/abs/2509.09380
摘要：赫希-格贝莱因-勒内伊（HGR）相关系数是皮尔逊相关系数的扩展，它不限于线性相关，在算法公平性，科学分析和因果发现中具有潜在的应用。最近，已经提出了以可微方式估计HGR的新算法，以便于将其用作受限机器学习应用中的损失正则化器。然而，HGR固有的不可计算性需要偏差-方差权衡，这可能会损害所提出的方法的鲁棒性，因此如果应用于现实世界的场景中，会引起技术问题。我们介绍了一种新的计算方法HGR依赖于用户可配置的多项式内核，提供更大的鲁棒性相比，以前的方法，并具有更快，但几乎同样有效的限制。我们的方法在鲁棒性和确定性方面提供了显着的优势，使其成为现实世界应用程序的更可靠的选择。此外，我们提出了一个简短的实验分析，以验证我们的方法在一个受约束的机器学习框架内的适用性，表明它的计算产生了一个有见地的次梯度，可以作为一个损失正则化。
摘要：The Hirschfeld-Gebelein-R\'enyi (HGR) correlation coefficient is an extension of Pearson's correlation that is not limited to linear correlations, with potential applications in algorithmic fairness, scientific analysis, and causal discovery. Recently, novel algorithms to estimate HGR in a differentiable manner have been proposed to facilitate its use as a loss regularizer in constrained machine learning applications. However, the inherent uncomputability of HGR requires a bias-variance trade-off, which can possibly compromise the robustness of the proposed methods, hence raising technical concerns if applied in real-world scenarios. We introduce a novel computational approach for HGR that relies on user-configurable polynomial kernels, offering greater robustness compared to previous methods and featuring a faster yet almost equally effective restriction. Our approach provides significant advantages in terms of robustness and determinism, making it a more reliable option for real-world applications. Moreover, we present a brief experimental analysis to validate the applicability of our approach within a constrained machine learning framework, showing that its computation yields an insightful subgradient that can serve as a loss regularizer.
【7】Data Driven Discovery of Emergent Dynamics in Reaction Diffusion Systems from Sparse and Noisy Observations
标题：从稀疏和噪声观测数据驱动发现反应扩散系统的涌现动力学
链接：https://arxiv.org/abs/2509.09278
摘要：数据驱动的涌现动力学发现越来越受欢迎，特别是在反应扩散系统的背景下。这些系统在各个领域得到了广泛的研究，包括神经科学，生态学，流行病学和其他几个处理涌现动力学的学科领域。当前发现过程中的一个挑战是在没有基础物理学先验知识的情况下进行系统识别。我们试图通过学习软人工生命（Soft ALife）模型，如基于Agent和元胞自动机（CA）模型，从反应扩散系统的观测数据来解决这一挑战。在本文中，我们提出了一个概念框架，软人工生命（DRSALife）模型的数据驱动的规则集，学习软ALife规则集，准确地表示紧急动态的反应扩散系统从观测数据的适用性的研究结果。在最近的工作中，该模型已经在基本CA规则30，生命游戏和Vicsek群集问题上表现出了很好的结果。据我们所知，这是为数不多的研究之一，探索基于机器的Soft ALife规则学习和反应扩散动力学系统识别，而无需任何基础物理知识。此外，我们提供了全面的研究结果，从实验调查使用噪声和稀疏的观察数据集对学习新兴动态的潜在影响。此外，我们成功地确定了这些动态的基本偏微分方程（PDE）的结构和参数。实验结果表明，学习模型能够预测紧急动态具有良好的准确性（74%），并表现出相当强大的性能时，高斯噪声和时间稀疏。
摘要 ：Data-driven discovery of emergent dynamics is gaining popularity, particularly in the context of reaction-diffusion systems. These systems are widely studied across various fields, including neuroscience, ecology, epidemiology, and several other subject areas that deal with emergent dynamics. A current challenge in the discovery process relates to system identification when there is no prior knowledge of the underlying physics. We attempt to address this challenge by learning Soft Artificial Life (Soft ALife) models, such as Agent-based and Cellular Automata (CA) models, from observed data for reaction-diffusion systems. In this paper, we present findings on the applicability of a conceptual framework, the Data-driven Rulesets for Soft Artificial Life (DRSALife) model, to learn Soft ALife rulesets that accurately represent emergent dynamics in a reaction-diffusion system from observed data. This model has demonstrated promising results for Elementary CA Rule 30, Game of Life, and Vicsek Flocking problems in recent work. To our knowledge, this is one of the few studies that explore machine-based Soft ALife ruleset learning and system identification for reaction-diffusion dynamics without any prior knowledge of the underlying physics. Moreover, we provide comprehensive findings from experiments investigating the potential effects of using noisy and sparse observed datasets on learning emergent dynamics. Additionally, we successfully identify the structure and parameters of the underlying partial differential equations (PDEs) representing these dynamics. Experimental results demonstrate that the learned models are able to predict the emergent dynamics with good accuracy (74%) and exhibit quite robust performance when subjected to Gaussian noise and temporal sparsity.
【8】Identifying Key Features for Establishing Sustainable Agro-Tourism Centre: A Data Driven Approach
标题：确定建立可持续农业旅游中心的关键特征：数据驱动方法
链接：https://arxiv.org/abs/2509.09214
摘要：农业旅游是一种战略性经济模式，旨在通过使农民等当地社区的收入来源多样化，促进农村发展，同时促进土著文化遗产和传统农业做法的保护。作为旅游业中一个非常蓬勃发展的子领域，有必要详细研究农业旅游的发展战略。目前的研究确定了农业旅游业增长和加强的重要指标。研究分两个阶段进行：通过全面的文献审查确定重要指标，第二阶段采用最先进的技术确定农业旅游业增长的重要指标。这些指标也被称为特征，应用机器学习模型进行特征选择，并观察到最小绝对收缩和选择算子（LASSO）方法与机器学习分类器（如逻辑回归（LR），决策树（DT），随机森林（RF）树和极端梯度提升（XGBOOST）模型）相结合，用于表明农业旅游的增长。结果表明，在LASSO方法中，LR模型在70-30%的训练测试数据中给出了98%的最高分类准确率，其次是RF，准确率为95%。同样，在80-20%的训练测试数据中，LR保持了99%的最高准确率，而DT和XGBoost则以97%的准确率紧随其后。
摘要：Agro-tourism serves as a strategic economic model designed to facilitate rural development by diversifying income streams for local communities like farmers while promoting the conservation of indigenous cultural heritage and traditional agricultural practices. As a very booming subdomain of tourism, there is a need to study the strategies for the growth of Agro-tourism in detail. The current study has identified the important indicators for the growth and enhancement of agro-tourism. The study is conducted in two phases: identification of the important indicators through a comprehensive literature review and in the second phase state-of-the-art techniques were used to identify the important indicators for the growth of agro-tourism. The indicators are also called features synonymously, the machine learning models for feature selection were applied and it was observed that the Least Absolute Shrinkage and Selection Operator (LASSO) method combined with, the machine Learning Classifiers such as Logistic Regression (LR), Decision Trees (DT), Random Forest (RF) Tree, and Extreme Gradient Boosting (XGBOOST) models were used to suggest the growth of the agro-tourism. The results show that with the LASSO method, LR model gives the highest classification accuracy of 98% in 70-30% train-test data followed by RF with 95% accuracy. Similarly, in the 80-20% train-test data LR maintains the highest accuracy at 99%, while DT and XGBoost follow with 97% accuracy.
【9】Clip Your Sequences Fairly: Enforcing Length Fairness for Sequence-Level RL
标题：公平地剪辑您的序列：强制序列级RL的长度公平
链接：https://arxiv.org/abs/2509.09177
摘要：我们提出了FSPO（公平序列策略优化），这是一种用于LLM的序列级强化学习方法，它直接在重要性采样（IS）权重空间中执行长度公平裁剪。我们重新审视了序列级RL方法，并确定了PPO/GRPO风格的裁剪移植到序列时的不匹配：固定的裁剪范围系统地重新加权短响应与长响应，扭曲了有效的目标。从理论上讲，我们通过长度重新加权误差（LRE）形式化长度公平性，并证明了小LRE产生一个方向余弦保证之间的裁剪和真正的更新。FSPO引入了一个简单的，高斯动机的补救措施：我们剪辑的序列对数IS比与一个波段，适用于KL校正漂移项和规模为$\sqrt{L}$。从经验上讲，FSPO可以跨长度箱调整剪辑速率，稳定训练，并在多个评估数据集上优于所有基线。
摘要：We propose FSPO (Fair Sequence Policy Optimization), a sequence-level reinforcement learning method for LLMs that enforces length-fair clipping directly in the importance-sampling (IS) weight space. We revisit sequence-level RL methods and identify a mismatch when PPO/GRPO-style clipping is transplanted to sequences: a fixed clip range systematically reweights short vs. long responses, distorting the effective objective. Theoretically, we formalize length fairness via a Length Reweighting Error (LRE) and prove that small LRE yields a directional cosine guarantee between the clipped and true updates. FSPO introduces a simple, Gaussian-motivated remedy: we clip the sequence log-IS ratio with a band that applies a KL-corrected drift term and scales as $\sqrt{L}$. Empirically, FSPO flattens clip rates across length bins, stabilizes training, and outperforms all baselines across multiple evaluation datasets.
【10】HISPASpoof: A New Dataset For Spanish Speech Forensics
标题：HISPaspoof：西班牙语语音取证的新数据集
链接：https://arxiv.org/abs/2509.09155
备注：8 pages, 1 figure, 10 tables, being submitted to ICASSP 2026 (IEEE International Conference on Acoustics, Speech, and Signal Processing 2026)
摘要：Zero-shot语音克隆（VC）和文本到语音（TTS）方法发展迅速，能够生成高度逼真的合成语音，并引起了人们对它们滥用的严重关注。虽然已经为英语和中文开发了许多检测器，但全世界超过6亿人使用的西班牙语在语音取证中仍然代表不足。为了解决这一差距，我们引入了HISPASpoof，这是第一个为合成语音检测和归因而设计的大规模西班牙语数据集。它包括来自公共语料库的六种口音的真实语音和由六个zero-shot TTS系统生成的合成语音。我们评估了五种有代表性的方法，表明在英语上训练的检测器无法推广到西班牙语，而在HISPASpoof上训练则大大提高了检测能力。我们还评估了HISPASpoof的合成语音归因性能，即，识别合成语音的生成方法。因此，HISPASpoof为推进西班牙语的可靠和包容性语音取证提供了一个关键基准。
摘要：Zero-shot Voice Cloning (VC) and Text-to-Speech (TTS) methods have advanced rapidly, enabling the generation of highly realistic synthetic speech and raising serious concerns about their misuse. While numerous detectors have been developed for English and Chinese, Spanish-spoken by over 600 million people worldwide-remains underrepresented in speech forensics. To address this gap, we introduce HISPASpoof, the first large-scale Spanish dataset designed for synthetic speech detection and attribution. It includes real speech from public corpora across six accents and synthetic speech generated with six zero-shot TTS systems. We evaluate five representative methods, showing that detectors trained on English fail to generalize to Spanish, while training on HISPASpoof substantially improves detection. We also evaluate synthetic speech attribution performance on HISPASpoof, i.e., identifying the generation method of synthetic speech. HISPASpoof thus provides a critical benchmark for advancing reliable and inclusive speech forensics in Spanish.
【11】STRIDE: Scalable and Interpretable XAI via Subset-Free Functional Decomposition
标题：WRIDE：通过无子集功能分解可扩展和可解释的XAI
链接：https://arxiv.org/abs/2509.09070
备注：10 pages, 2 figures
摘要：大多数可解释AI（XAI）框架面临两个实际限制：对特征子集进行推理的指数成本和将效果总结为单个标量值的表达能力降低。我们提出了STRIDE，一个可扩展的框架，旨在减轻这两个问题的框架解释作为一个子集枚举自由，正交功能分解的再生核希尔伯特空间（RKHS）。STRIDE不是只关注标量属性，而是通过基于递归核中心过程的解析投影方案来计算函数分量f_S（x_S），避免了显式子集枚举。在我们研究的表格设置中，该方法是模型不可知的，提供了局部和全局视图，并且在所述假设下得到了正交性和L^2收敛的理论结果的支持。在我们环境中的公共表格基准测试中，我们观察到加速范围从0.6倍（在小数据集上比TreeSHAP慢）到9.7倍（加利福尼亚州），在10个数据集上的中位数约为3.0倍，同时保持高保真度（R^2在0.81和0.999之间）和大多数数据集上的实质性排名一致。总的来说，STRIDE补充标量归因方法，提供了一个结构化的功能的角度来看，使新的诊断，如“组件手术”，定量测量特定的相互作用在我们的实验范围内的影响。
摘要：Most explainable AI (XAI) frameworks face two practical limitations: the exponential cost of reasoning over feature subsets and the reduced expressiveness of summarizing effects as single scalar values. We present STRIDE, a scalable framework that aims to mitigate both issues by framing explanation as a subset-enumeration-free, orthogonal functional decomposition in a Reproducing Kernel Hilbert Space (RKHS). Rather than focusing only on scalar attributions, STRIDE computes functional components f_S(x_S) via an analytical projection scheme based on a recursive kernel-centering procedure, avoiding explicit subset enumeration. In the tabular setups we study, the approach is model-agnostic, provides both local and global views, and is supported by theoretical results on orthogonality and L^2 convergence under stated assumptions. On public tabular benchmarks in our environment, we observed speedups ranging from 0.6 times (slower than TreeSHAP on a small dataset) to 9.7 times (California), with a median approximate 3.0 times across 10 datasets, while maintaining high fidelity (R^2 between 0.81 and 0.999) and substantial rank agreement on most datasets. Overall, STRIDE complements scalar attribution methods by offering a structured functional perspective, enabling novel diagnostics like 'component surgery' to quantitatively measure the impact of specific interactions within our experimental scope.
【12】MoWE : A Mixture of Weather Experts
标题：MOWE：天气专家的混合体
链接：https://arxiv.org/abs/2509.09052
摘要：数据驱动的天气模型最近取得了最先进的性能，但近年来进展停滞不前。本文介绍了混合专家（MoWE）的方法作为一种新的范式，以克服这些局限性，而不是通过创建一个新的预测，但通过优化组合现有模型的输出。MoWE模型的训练使用的计算资源明显低于单个专家。我们的模型采用了基于Vision Transformer的门控网络，该网络动态学习在每个网格点对多个“专家”模型的贡献进行加权，并以预测提前期为条件。这种方法创建了一个综合的确定性预测，比任何单个组件的均方根误差（RMSE）更准确。我们的结果证明了这种方法的有效性，在2天的预测范围内，RMSE比性能最好的人工智能天气模型低10%，显著优于单个专家以及专家之间的简单平均值。这项工作提出了一种计算效率高、可扩展的策略，通过充分利用领先的高质量预报模型，推动数据驱动天气预报的发展。
摘要：Data-driven weather models have recently achieved state-of-the-art performance, yet progress has plateaued in recent years. This paper introduces a Mixture of Experts (MoWE) approach as a novel paradigm to overcome these limitations, not by creating a new forecaster, but by optimally combining the outputs of existing models. The MoWE model is trained with significantly lower computational resources than the individual experts. Our model employs a Vision Transformer-based gating network that dynamically learns to weight the contributions of multiple "expert" models at each grid point, conditioned on forecast lead time. This approach creates a synthesized deterministic forecast that is more accurate than any individual component in terms of Root Mean Squared Error (RMSE). Our results demonstrate the effectiveness of this method, achieving up to a 10% lower RMSE than the best-performing AI weather model on a 2-day forecast horizon, significantly outperforming individual experts as well as a simple average across experts. This work presents a computationally efficient and scalable strategy to push the state of the art in data-driven weather prediction by making the most out of leading high-quality forecast models.
【13】Fast attention mechanisms: a tale of parallelism
标题：快速注意力机制：并行的故事
链接：https://arxiv.org/abs/2509.09001
摘要：Transformers具有模拟大规模并行计算（MPC）算法的代表能力，但其时间复杂度为二次方，严重限制了其可扩展性。我们引入了一个有效的注意机制，称为近似最近邻注意（ANNA）次二次时间复杂度。我们证明了ANNA变换器（1）保留了先前为标准注意力建立的表达能力，与MPC算法的能力相匹配，（2）可以解决关键的推理任务，如Match 2和$k$-hop，具有接近最优的深度。使用MPC框架，我们进一步证明了恒定深度的ANNA变换器可以模拟恒定深度的低秩Transformers，从而提供了一种统一的方式来推理广泛的一类有效的注意力近似。
摘要：Transformers have the representational capacity to simulate Massively Parallel Computation (MPC) algorithms, but they suffer from quadratic time complexity, which severely limits their scalability. We introduce an efficient attention mechanism called Approximate Nearest Neighbor Attention (ANNA) with sub-quadratic time complexity. We prove that ANNA-transformers (1) retain the expressive power previously established for standard attention in terms of matching the capabilities of MPC algorithms, and (2) can solve key reasoning tasks such as Match2 and $k$-hop with near-optimal depth. Using the MPC framework, we further prove that constant-depth ANNA-transformers can simulate constant-depth low-rank transformers, thereby providing a unified way to reason about a broad class of efficient attention approximations.
【14】Safe and Certifiable AI Systems: Concepts, Challenges, and Lessons Learned
标题：安全且可认证的人工智能系统：概念、挑战和经验教训
链接：https://arxiv.org/abs/2509.08852
备注：63 pages, 27 figures
摘要：人工智能在安全关键型应用中的应用越来越多，但证明人工智能系统安全、合法和社会可接受的实用方案仍然很少。本白皮书介绍了T\“UV AUXIA可信AI框架，这是一种用于评估和认证机器学习系统的端到端审计目录和方法。审计目录自2019年以来一直在与科学合作伙伴的持续合作中不断发展。基于三大支柱-安全软件开发，功能要求以及道德和数据隐私-该目录将欧盟人工智能法案的高级义务转化为具体的，可测试的标准。其功能可信度的核心概念将统计定义的应用程序域与基于风险的最低性能要求和独立采样数据的统计测试相结合，为真实环境中的模型质量提供透明和可重现的证据。我们提供了我们评估的功能需求的概述，这些需求面向AI系统的生命周期。此外，我们还分享了从审计目录的实际应用中吸取的一些经验教训，强调了我们遇到的常见陷阱，例如数据泄漏场景，不充分的域定义，忽视偏见或缺乏分布漂移控制。我们进一步讨论了认证人工智能系统的关键方面，例如鲁棒性，算法公平性或认证后要求，概述了我们目前的结论和未来研究的路线图。总的来说，通过将技术最佳实践与新兴的欧洲标准相结合，该方法为监管机构、提供商和用户提供了一个实用的路线图，以实现合法、功能可靠和可认证的人工智能系统。
摘要 ：There is an increasing adoption of artificial intelligence in safety-critical applications, yet practical schemes for certifying that AI systems are safe, lawful and socially acceptable remain scarce. This white paper presents the T\"UV AUSTRIA Trusted AI framework an end-to-end audit catalog and methodology for assessing and certifying machine learning systems. The audit catalog has been in continuous development since 2019 in an ongoing collaboration with scientific partners. Building on three pillars - Secure Software Development, Functional Requirements, and Ethics & Data Privacy - the catalog translates the high-level obligations of the EU AI Act into specific, testable criteria. Its core concept of functional trustworthiness couples a statistically defined application domain with risk-based minimum performance requirements and statistical testing on independently sampled data, providing transparent and reproducible evidence of model quality in real-world settings. We provide an overview of the functional requirements that we assess, which are oriented on the lifecycle of an AI system. In addition, we share some lessons learned from the practical application of the audit catalog, highlighting common pitfalls we encountered, such as data leakage scenarios, inadequate domain definitions, neglect of biases, or a lack of distribution drift controls. We further discuss key aspects of certifying AI systems, such as robustness, algorithmic fairness, or post-certification requirements, outlining both our current conclusions and a roadmap for future research. In general, by aligning technical best practices with emerging European standards, the approach offers regulators, providers, and users a practical roadmap for legally compliant, functionally trustworthy, and certifiable AI systems.
【15】Low-degree lower bounds via almost orthonormal bases
标题：通过几乎垂直基的低级下界
链接：https://arxiv.org/abs/2509.09353
摘要：低次多项式已经成为一个强大的范例，为各种高维统计模型提供统计-计算差距的证据[Wein 25]。对于检测问题-目标是测试种植分布$\mathbb {P}'$与具有独立分量的零分布$\mathbb{P}$-标准方法是使用$\mathbb{L}^2（\mathbb{P}）$-正交多项式族来限制优势。但是，这种方法在估计任务或更复杂的测试问题中会失效，其中$\mathbb{P}$具有一些植入结构，因此没有简单的$\mathbb{L}^2（\mathbb{P}）$-正交多项式族可用。为了应对这一挑战，已经提出了几种技术解决方案[SW 22，SW 25]，尽管它们的实现可能很微妙。在这项工作中，我们提出了一个更直接的证明策略。专注于随机图形模型，我们构建了一个基础的多项式，几乎是正交下$\mathbb{P}$，正是在这些制度的统计-计算差距出现。这种几乎正交的基础不仅产生了一个直接的路线，建立低程度的下限，但也允许我们明确地确定多项式，优化低程度的标准。这反过来又为最优多项式时间算法的设计提供了见解。我们说明了我们的方法的有效性，通过恢复已知的低程度的下界，并建立新的问题，如隐藏的子集团，随机块模型和序列化模型。
摘要：Low-degree polynomials have emerged as a powerful paradigm for providing evidence of statistical--computational gaps across a variety of high-dimensional statistical models [Wein25]. For detection problems -- where the goal is to test a planted distribution $\mathbb{P}'$ against a null distribution $\mathbb{P}$ with independent components -- the standard approach is to bound the advantage using an $\mathbb{L}^2(\mathbb{P})$-orthonormal family of polynomials. However, this method breaks down for estimation tasks or more complex testing problems where $\mathbb{P}$ has some planted structures, so that no simple $\mathbb{L}^2(\mathbb{P})$-orthogonal polynomial family is available. To address this challenge, several technical workarounds have been proposed [SW22,SW25], though their implementation can be delicate. In this work, we propose a more direct proof strategy. Focusing on random graph models, we construct a basis of polynomials that is almost orthonormal under $\mathbb{P}$, in precisely those regimes where statistical--computational gaps arise. This almost orthonormal basis not only yields a direct route to establishing low-degree lower bounds, but also allows us to explicitly identify the polynomials that optimize the low-degree criterion. This, in turn, provides insights into the design of optimal polynomial-time algorithms. We illustrate the effectiveness of our approach by recovering known low-degree lower bounds, and establishing new ones for problems such as hidden subcliques, stochastic block models, and seriation models.
【16】Scalable extensions to given-data Sobol' index estimators
标题：给定数据Sobol指数估计量的可扩展
链接：https://arxiv.org/abs/2509.09078
摘要：基于方差的敏感性分析的给定数据方法显著地提高了计算昂贵的模型和具有许多输入的模型的Sobol指数计算的可行性。然而，现有的方法的局限性仍然排除了他们的应用程序的模型具有非常大的数量的输入。在这项工作中，我们提出了实际的扩展现有的给定数据Sobol的指数方法，它允许基于方差的灵敏度分析，以有效地执行大型模型，如神经网络，其中有$>10^4$参数化的输入。对于这种规模的模型，将所有输入-输出评估同时保存在内存中（如现有方法所要求的）可能很快变得不切实际。这些扩展还支持具有许多重复值的非标准输入分布，这些值不适合于现有给定数据方法所采用的等概率分区。 我们的扩展包括一个一般定义的给定数据Sobol的指数估计与任意分区，流算法处理输入输出样本的批次，和一个启发式过滤出的小指数是无法区分的零指数，由于统计噪声。我们发现，在现有的给定数据的方法中采用的等概率分区可以引入显着的偏差到Sobol的指数估计，即使在大样本量，并提供数值分析，证明为什么会发生这种情况。我们还表明，我们的流算法可以实现相当的准确性和运行时间与较低的内存需求，相对于目前的方法，一次处理所有样本。我们展示了我们在神经网络建模中的两个应用问题上的新进展。
摘要：Given-data methods for variance-based sensitivity analysis have significantly advanced the feasibility of Sobol' index computation for computationally expensive models and models with many inputs. However, the limitations of existing methods still preclude their application to models with an extremely large number of inputs. In this work, we present practical extensions to the existing given-data Sobol' index method, which allow variance-based sensitivity analysis to be efficiently performed on large models such as neural networks, which have $>10^4$ parameterizable inputs. For models of this size, holding all input-output evaluations simultaneously in memory -- as required by existing methods -- can quickly become impractical. These extensions also support nonstandard input distributions with many repeated values, which are not amenable to equiprobable partitions employed by existing given-data methods. Our extensions include a general definition of the given-data Sobol' index estimator with arbitrary partition, a streaming algorithm to process input-output samples in batches, and a heuristic to filter out small indices that are indistinguishable from zero indices due to statistical noise. We show that the equiprobable partition employed in existing given-data methods can introduce significant bias into Sobol' index estimates even at large sample sizes and provide numerical analyses that demonstrate why this can occur. We also show that our streaming algorithm can achieve comparable accuracy and runtimes with lower memory requirements, relative to current methods which process all samples at once. We demonstrate our novel developments on two application problems in neural network modeling.
【17】Generative quantum advantage for classical and quantum problems
标题：经典和量子问题的生成量子优势
链接：https://arxiv.org/abs/2509.09033
摘要：最近在生成机器学习方面的突破，由大量的计算资源提供动力，已经展示了前所未有的类人能力。虽然超越经典的量子实验可以从经典的难以处理的分布中生成样本，但它们的复杂性阻碍了所有有效学习的努力。这一挑战阻碍了生成量子优势的展示：量子计算机学习和生成所需输出的能力远远优于经典计算机。我们通过引入生成量子模型来解决这一挑战，这些模型很难用经典方法模拟，可有效训练，没有贫瘠的高原或增殖的局部极小值，并且可以学习生成经典计算机无法达到的分布。使用68 $-量子比特超导量子处理器，我们在两种情况下展示了这些能力：学习经典的棘手的概率分布和学习量子电路加速物理模拟。我们的研究结果表明，学习和采样都可以在超越经典的制度下有效地进行，为量子增强的生成模型提供了新的可能性，具有可证明的优势。
摘要 ：Recent breakthroughs in generative machine learning, powered by massive computational resources, have demonstrated unprecedented human-like capabilities. While beyond-classical quantum experiments can generate samples from classically intractable distributions, their complexity has thwarted all efforts toward efficient learning. This challenge has hindered demonstrations of generative quantum advantage: the ability of quantum computers to learn and generate desired outputs substantially better than classical computers. We resolve this challenge by introducing families of generative quantum models that are hard to simulate classically, are efficiently trainable, exhibit no barren plateaus or proliferating local minima, and can learn to generate distributions beyond the reach of classical computers. Using a $68$-qubit superconducting quantum processor, we demonstrate these capabilities in two scenarios: learning classically intractable probability distributions and learning quantum circuits for accelerated physical simulation. Our results establish that both learning and sampling can be performed efficiently in the beyond-classical regime, opening new possibilities for quantum-enhanced generative models with provable advantage.
【18】Physics-informed waveform inversion using pretrained wavefield neural operators
标题：使用预先训练的波场神经运算符进行基于物理的波形倒置
链接：https://arxiv.org/abs/2509.08967
摘要：全波形反演（FWI）是重建高分辨率地下模型的关键，但考虑到有限的数据，它经常受到阻碍，其零空间导致低分辨率模型，更重要的是，其计算成本，特别是如果需要实时应用。最近尝试使用学习的波场神经算子来加速FWI已经显示出效率和可微性的前景，但是通常遭受噪声和不稳定的反演性能。为了解决这些限制，我们引入了一种新的物理信息FWI框架，以提高反演的准确性，同时保持基于神经算子的FWI的效率。我们在FWI的损失函数中加入了一个物理约束项，从而提高了反演速度模型的质量，而不是仅仅依靠L2范数目标函数通过自动微分，导致噪声模型重建。具体来说，从初始模型开始模拟波场，然后评估损失，结果波场遵守物理定律（波动方程）并与记录的数据相匹配，我们实现了噪声和伪影的减少。使用OpenFWI和逆掩断层模型的数值实验表明，我们的方法的优越性能，提供更干净，更准确的地下速度比香草的方法。考虑到与FWI相比该方法的效率，这一进步代表了FWI在实时地下监测的实际应用中向前迈出的重要一步。
摘要：Full waveform inversion (FWI) is crucial for reconstructing high-resolution subsurface models, but it is often hindered, considering the limited data, by its null space resulting in low-resolution models, and more importantly, by its computational cost, especially if needed for real-time applications. Recent attempts to accelerate FWI using learned wavefield neural operators have shown promise in efficiency and differentiability, but typically suffer from noisy and unstable inversion performance. To address these limitations, we introduce a novel physics-informed FWI framework to enhance the inversion in accuracy while maintaining the efficiency of neural operator-based FWI. Instead of relying only on the L2 norm objective function via automatic differentiation, resulting in noisy model reconstruction, we integrate a physics constraint term in the loss function of FWI, improving the quality of the inverted velocity models. Specifically, starting with an initial model to simulate wavefields and then evaluating the loss over how much the resulting wavefield obeys the physical laws (wave equation) and matches the recorded data, we achieve a reduction in noise and artifacts. Numerical experiments using the OpenFWI and Overthrust models demonstrate our method's superior performance, offering cleaner and more accurate subsurface velocity than vanilla approaches. Considering the efficiency of the approach compared to FWI, this advancement represents a significant step forward in the practical application of FWI for real-time subsurface monitoring.
【19】Deploying AI for Signal Processing education: Selected challenges and intriguing opportunities
标题：部署人工智能用于信号处理教育：选定的挑战和有趣的机会
链接：https://arxiv.org/abs/2509.08950
备注：Accepted to the IEEE Signal Processing Magazine Special Issue on Artificial Intelligence for Education: A Signal Processing Perspective
摘要：近年来出现的强大的人工智能（AI）工具-包括大型语言模型，自动编码助手以及先进的图像和语音生成技术-是人类巨大成就的结果。这些突破反映了对多个技术学科的掌握和对重大技术挑战的解决。然而，一些最深刻的挑战可能仍然摆在面前。这些挑战不纯粹是技术性的，而是涉及以真正改善全球人类状况的方式公平和负责任地使用人工智能。本文探讨了与这一愿景相一致的一个有前途的应用：使用人工智能工具来促进和加强教育，特别关注信号处理（SP）。它提出了两个相互关联的观点：识别和解决技术限制，并在实践中应用人工智能工具来改善教育体验。在教育环境中使用人工智能时出现的几个核心技术问题，包括如何确保公平性和包容性，处理幻觉输出，以及实现资源的有效利用。这些和其他考虑因素--如透明度、可解释性和可信度--通过开发一本沉浸式、结构化和可靠的“智能教科书”来说明。“这篇文章为研究人员和教育工作者提供了一个资源，以促进人工智能在工程教育中的作用。
摘要：Powerful artificial intelligence (AI) tools that have emerged in recent years -- including large language models, automated coding assistants, and advanced image and speech generation technologies -- are the result of monumental human achievements. These breakthroughs reflect mastery across multiple technical disciplines and the resolution of significant technological challenges. However, some of the most profound challenges may still lie ahead. These challenges are not purely technical but pertain to the fair and responsible use of AI in ways that genuinely improve the global human condition. This article explores one promising application aligned with that vision: the use of AI tools to facilitate and enhance education, with a specific focus on signal processing (SP). It presents two interrelated perspectives: identifying and addressing technical limitations, and applying AI tools in practice to improve educational experiences. Primers are provided on several core technical issues that arise when using AI in educational settings, including how to ensure fairness and inclusivity, handle hallucinated outputs, and achieve efficient use of resources. These and other considerations -- such as transparency, explainability, and trustworthiness -- are illustrated through the development of an immersive, structured, and reliable "smart textbook." The article serves as a resource for researchers and educators seeking to advance AI's role in engineering education.
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/186662
本文地址：http://www.python88.com/topic/186662