2026-11-16 | CS.LG机器学习 | 共 78 篇
[机构]信息由AI分析生成,可能存在错误,仅供参考,以论文实际显示为准
快速导航
1. 深度学习架构与训练方法 5 篇
2. 表示学习、自监督与对比学习 1 篇
3. 强化学习与序列决策 7 篇
4. 生成模型与概率建模 5 篇
5. 优化、泛化与理论分析 6 篇
6. 高效学习、压缩与部署 2 篇
7. 联邦学习、隐私与安全 2 篇
8. 鲁棒性、不确定性与可信学习 4 篇
9. 图学习与结构化数据 2 篇
10. 迁移、元学习与持续学习 1 篇
11. 数据集、基准与评测 3 篇
12. 机器学习应用 6 篇
13. 其他/综合机器学习 34 篇
1. 深度学习架构与训练方法 | 5 篇
1. Do Mixture-of-Experts Routers Benefit from Ensembling?
混合专家模型的路由模块是否从集成中受益?
AI 总结:该研究探究混合专家模型的路由模块是否可通过集成提升性能,提出联合训练的路由模块集成方法,经多任务实验发现集成有轻微益处但被计算成本抵消。
链接:https://arxiv.org/abs/2611.17472
机构:University of Groningen(格罗宁根大学)
作者:Viktor Veselý, Sebastian Jitaru
英文摘要:Ensembles of neural networks have repeatedly been shown to outperform single networks. Ensemble theory attributes this gain to the accuracy of the individual members and the diversity among them. Mixture-of-experts models already combine many experts, but a single router decides how the experts are weighted for each input. Motivated by ensemble theory, we apply ensembling to the routing step: an ensemble of routers, trained jointly with the experts, proposes the expert weights. We systematically evaluate this approach using underparameterized networks on two image-classification and two tabular-regression tasks. We analyse each experiment with a performance-diversity decomposition of the router ensemble, which, to our knowledge, has not previously been developed for routers. We report four findings. First, more routers lower the validation loss. Second, training routers to explicitly maximize expert diversity improves the mean performance on three of the four tasks. Third, explicitly maximizing router diversity has no effect on performance. Fourth, combining router weights with the arithmetic mean works better than combining them with the geometric mean. Routing benefits mildly from ensembling, but this benefit is offset by the computational cost of training additional routers.
2. Fuse-All MoE Inference Kernel with Load Balancing on TPUs
在TPU上实现负载均衡的Fuse-All MoE推理内核
AI 总结:该研究针对MoE在TPU推理中的效率瓶颈,提出Fuse-All MoE内核,通过融合计算通信与负载均衡优化,使EP16预填运行时间降至1.09倍、EP8TP2解码延迟降21.3%,系统吞吐量提升34.5%。
链接:https://arxiv.org/abs/2611.17857
机构:Meta; Meta SuperIntelligence Lab(元平台超级智能实验室)
作者:Rupeng Liu, Bangsheng Tang, Zongwei Zhou, Chengji Yao, Yejin Lee
英文摘要:Mixture-of-Experts (MoE) architectures activate only a subset of experts for each token, allowing large language models (LLMs) to scale parameter capacity without a proportional increase in computation per token. However, intermediate data movement and uneven expert loads limit the efficiency of MoE inference on TPUs. To address these bottlenecks, we introduce Fuse-All MoE, a TPU kernel design that jointly optimizes expert computation, output communication, and load balancing. The kernel fuses token collection, expert projections, gated activation, and output writes, retaining expert computation intermediates on chip. Fixed token-slot destinations allow scheduling and expert placement to change while preserving routing semantics. In prefill-decode (PD) disaggregated serving, Fuse-All MoE balances EP16 prefill workloads through scheduling and expert redistribution, while symmetric EP8TP2 shares active expert computation between the two TensorCore devices within each chip during decode. Our experiments show that Fuse-All MoE reduces kernel runtime for a measured skewed EP16 prefill workload from 2.3x to 1.09x the same fixed reference time for a balanced workload. Across 32-512 decode tokens, symmetric EP8TP2 reduces kernel latency by up to 21.3% relative to fused EP16. With accompanying serving stack optimizations, the integrated system improves serving throughput by up to 34.5% over the Megablox EP16 baseline.
3. From Local Prediction Error to Final Outputs: A Theory of Expert Sharing in Multi-Step Reasoning
从局部预测误差到最终输出:多步推理中的专家共享理论
AI 总结:该研究探讨MoE模型多步推理中专家共享的局部收益能否保留至最终输出,推导相关准则与误差界,通过实验验证局部-最终风险反转,明确专家共享的有效场景与归因证据要求。
链接:https://arxiv.org/abs/2611.17879
机构:Nanyang Technological University(南洋理工大学); KTH Royal Institute of Technology(KTH皇家理工学院); Beijing Institute of Technology(北京理工大学)
作者:Tiantong Wang, Zhiren Gong, Yixin Wang, Tiantong Wu, Wei Yang Bryan Lim
英文摘要: Mixture-of-experts (MoE) models can share experts across layers or computational steps, pooling training information from different contexts. This can reduce local prediction error, but multi-step systems are ultimately evaluated by their final outputs. We study when these local gains survive composition. In specified linear regression models, we derive exact sharing and merging criteria by balancing variance savings against bias from sharing across roles with different target behavior. Under a common fixed linear propagation map, we characterize expected squared final-output risk, retaining error directions and correlations. We construct cases where sharing lowers average local error yet increases final-output error. Within this setting, we also identify when orthogonal full pooling with isotropic noise preserves every local improvement at the final output. For general routed computations, we derive conditional end-to-end error bounds that account for distribution shifts, errors in surrounding components, and changes in expert selection. Separately, we show that correct predictions and route labels alone do not establish that individual experts implement the attributed operations. Controlled experiments realize a strict local-to-final risk reversal. In low-data symbolic settings, trained Transformers exhibit statistically supported teacher-forced one-step gains without statistically resolved free-running final-output gains. Separate intervention tests distinguish successful multi-layer actions from single-expert attribution and generalization to unseen transitions. Together, these results distinguish when sharing improves local estimation, when those gains survive to the final output, and what evidence is needed to attribute reusable operations to individual experts.
4. Learning nonlinear interactions and cross-feature couplings with product-unit residual networks
用乘积单元残差网络学习非线性交互与跨特征耦合
AI 总结:该研究提出复值乘积单元残差网络(CV-PURe),显式建模跨特征耦合,在多个基准数据集上相比MLP显著降低预测误差,提升交互恢复能力,且在扰动输入与有限监督下表现稳定。
链接:https://arxiv.org/abs/2611.18074
机构:University of Applied Sciences Koblenz(科布伦茨应用科学大学); Technical University of Munich(慕尼黑工业大学)
作者:Ziyuan Li, Uwe Jaekel, Babette Dellen
英文摘要:Understanding nonlinear feature interactions is crucial in science and engineering, yet standard multilayer perceptrons (MLPs) often capture such interactions only implicitly, leading to entangled representations that can impair robustness and interpretability. We investigate complex-valued product-unit residual networks (CV-PURe) that integrate multiplicative product units with residual connections to explicitly model cross-feature couplings while stabilizing optimization. We conduct a systematic evaluation on an interaction-driven synthetic benchmark and real-world datasets and evaluate prediction together with input-level interaction recovery under a reproducible protocol. Across five data splits and five training seeds, CV-PURe achieves the lowest mean RMSE on four of six scientific benchmarks, reducing Friedman error by 53.9% relative to MLP. Its Friedman interaction maps assign 60.7% of total strength to the known interacting pair, compared with 31.0% for MLP. On a synthetic task containing third- and fourth-order products and 20 distractors, CV-PURe reduces RMSE from 0.1376 to 0.0797 relative to a complex-valued MLP and recovers all nine true pairwise projections in every training/sampling repetition. Bike Sharing experiments connect improved prediction to the contribution of temporal, calendar, and seasonal context through paired ablations of both PURe variants. Parkinsons Telemonitoring extends the context analysis to repeated measurements. Noise and learning-curve evaluations demonstrate sustained predictive gains under perturbed inputs and limited supervision, while inference measurements quantify computational cost. This article extends our ICCS 2026 paper, Modeling Nonlinear Feature Interactions with Product-Unit Residual Networks (doi: https://doi.org/10.1007/978-3-032-29921-5_6 ).
5. Emulating physics-based XCO2 retrievals across OCO-2 viewing modes with compact neural networks
用紧凑神经网络模拟OCO-2观测模式下基于物理的XCO2反演
AI 总结:本研究用奇异值分解压缩OCO-2光谱,训练紧凑多层感知机预测全物理反演与先验值的差值,在多观测模式测试中误差低于基准模型,可高效模拟跨模式的全物理反演。
链接:https://arxiv.org/abs/2611.18333
作者:Xianlei San, Chengxing Zhai, Hui Su, Kuai Dai, Shuangchen Du
英文摘要:Operational full-physics retrieval of the column-averaged dry-air mole fraction of carbon dioxide from satellite spectra is computationally demanding. We use singular value decomposition to compress spectra from the Orbiting Carbon Observatory-2 separately by band. Compact multilayer perceptrons use the resulting spectral scores, prior information, and viewing geometry to predict the difference between the full-physics retrieval and its operational prior. Adding the predicted difference to the prior yields an estimate of the retrieved mole fraction. The models were trained on 2015-2019 observations and validated on 2020 observations. In 2021-2025 tests, the mean annual root-mean-square errors relative to the Atmospheric Carbon Dioxide Observations from Space retrieval product were 0.89, 1.35, and 1.43 parts per million for ocean glint, land glint, and nadir observations, respectively. On East Asian nadir observations screened using the published criteria for the spectral Transformer, our model yielded a lower mean annual error than reported for that model in 2020-2022. These results show that compact neural networks using compressed spectra can efficiently emulate the full-physics retrieval across multiple viewing modes and years.
2. 表示学习、自监督与对比学习 | 1 篇
6. LightTAR: Light and Fast Target-Aware Representations for Multimodal Tabular Learning
LightTAR:面向多模态表格学习的轻量快速目标感知表示
AI 总结:LightTAR是一种适配预测任务的轻量目标感知降维方法,通过正则化PLS提取目标感知特征增强PCA表示,在21种表格模型及几乎所有MulTaBench数据集上提升预测性能且运行时间增加少,可直接集成到现有编码流程。
链接:https://arxiv.org/abs/2611.17600
机构:Technion – Israel Institute of Technology(以色列理工学院)
作者:Eilam Shapira, Alan Arazi, Shoham Grunblat, Roi Reichart
英文摘要:Multimodal tabular learning involves classification and regression on tables combining structured numerical and categorical features with unstructured text and images. These unstructured fields are commonly represented by pretrained encoder embeddings reduced with principal component analysis (PCA). This reduction prioritizes input variance but may overlook information relevant to predicting the target. We introduce LightTAR, a simple, inexpensive method that adapts dimensionality reduction to the prediction task. LightTAR augments the standard PCA representation with a few target-aware features extracted jointly from the final and an intermediate encoder layer using regularized partial least squares (PLS). We evaluate LightTAR with 21 tabular models, including tree ensembles, neural networks, and tabular foundation models. LightTAR improves average predictive performance for all models and, averaged across models, improves prediction on almost every MulTaBench dataset. These gains come with a small increase in total runtime relative to PCA representations. LightTAR integrates directly into existing encoding pipelines, improving tabular learners' predictive performance without modifying the encoder or the learner.
3. 强化学习与序列决策 | 7 篇
7. Improved Regret via Variance-Aware Policy Optimization in Adversarial MDPs
对抗MDP中基于方差感知策略优化的改进遗憾值
AI 总结:针对未知动态全信息奖励的回合制对抗MDP,提出基于方差感知策略优化的VOPO算法,通过稳定性匹配奖励分析将遗憾值主导项改进为$\tilde O(\boldsymbol{\sqrt{H^3SAK}})$,缩小了与下界的差距。
链接:https://arxiv.org/abs/2611.17469
机构:Tel Aviv University(特拉维夫大学); Google Research(谷歌研究)
作者:Ofir Schlisselberg, Alon Cohen, Yishay Mansour
英文摘要:We study episodic adversarial MDPs with unknown dynamics and full-information rewards and achieve regret with leading term $\widetilde O(\sqrt{H^3SAK})$. Here $H$ is the horizon, $S$ the total number of states across decision layers, $A$ the number of actions, and $K$ the number of episodes. This improves the two incomparable prior leading terms by factors $\sqrt{S/H}$ and $\sqrt{H^3}$, leaving a factor $\sqrt H$ to the lower-bound scale. We give a reduction from unknown to known dynamics for \emph{downstream-dependent} algorithms, whose policy at step $h$ is computed only from information at steps $h+1$ and onward. This reduces the remaining leading-order gap to finding a downstream-dependent known-dynamics algorithm with $\widetilde O(H\sqrt K)$ regret, which would yield the tight $\widetilde O(H\sqrt{SAK})$ leading term for unknown dynamics. We instantiate the reduction with VOPO, a policy optimization (PO) algorithm. Its improved guarantees follow from a variance-aware analysis enabled by a novel bonus, which we call the Stability-Matching Bonus (SMB). VOPO achieves $\widetilde O(\sqrt{H^3K})$ regret under known dynamics with full information; its $\sqrt H$ gap to the target $H\sqrt K$ rate is inherited by our unknown-dynamics guarantee. We also show that with known dynamics and trajectory bandit feedback, VOPO achieves $\widetilde O(\sqrt{H^2SAK})$ regret. Both known-dynamics guarantees improve the corresponding state-of-the-art PO bounds by a factor $\sqrt H$. A matching lower bound establishes that the full-information rate is tight in one parameter regime.
8. Offline KL-Regularized Reinforcement Learning with Stochastic Transitions
带随机转移的离线KL正则化强化学习
AI 总结:本文研究带随机转移的离线KL正则化强化学习,推导样本复杂度下界,提出悲观软值迭代方法,证明其在参考数据下的有效性,指出插件估计器在小温度参考数据下的失效问题。
链接:https://arxiv.org/abs/2611.17603
机构:Columbia University(哥伦比亚大学)
作者:Andrew Liu
英文摘要:KL-regularized reinforcement learning is the objective behind RL fine-tuning of language models, and its data are often collected by the reference policy itself. However, beyond bandits and deterministic transitions, little is known about how much offline data it needs. In this work, we study finite discounted Markov decision processes with unknown stochastic transitions, $K$ state-action pairs and effective horizon $H$. For data that cover the regularized optimum with concentrability $C\geq 4$, every estimator needs $\Omega(KCH^3/(\epsilon\max\{\epsilon,\beta\}))$ samples on some instances when $\epsilon$ is small, where $\beta$ is the temperature. Under a fixed design, pessimistic soft value iteration with a variance-aware penalty attains this rate with high probability, up to logarithmic factors, when $\beta\geq 1.4H$. When the data come from the reference policy itself, we show that it covers the optimum up to a power law whose exponent grows as $H/\beta$; in the same temperature range, this power law alone gives the estimator a sample complexity polynomial in $1/\epsilon$, with no coverage assumption. For $\beta\geq H$ the power can also increase the sample size needed by a factor polynomial in $1/\epsilon$. Finally, the plug-in estimator, which is minimax optimal with a generative model, can fail on reference data at small temperatures when many actions are rarely seen, while the pessimistic estimator does not.
9. Joint World Action Models through Differentiable Trajectory Optimization
通过可微轨迹优化的联合世界动作模型
AI 总结:本研究提出WATO方法,通过联合优化动作与状态训练WAM,在7个视觉控制环境中较基线大幅提升成功率,且部署时速度更快、评估次数更少。
链接:https://arxiv.org/abs/2611.17626
机构:UC Berkeley(加州大学伯克利分校)
作者:Mintae Kim, Koushil Sreenath
英文摘要:Joint world action models (WAMs) generate future actions and states together, modeling world-action trajectories rather than actions alone. However, trajectory imitation does not ensure that these trajectories are task-effective or consistent with dynamics. We present \textbf{world action trajectory optimization (WATO)}, which optimizes generated actions and future states jointly for control. WATO uses both as references in a dynamics-constrained trajectory optimization problem and differentiates the task loss through the optimized trajectory to train the generator. This makes generated trajectories task-aware and dynamics-consistent while using trajectory optimization only during training. At deployment, WATO directly generates candidate trajectories and ranks them with a world model, without iterative trajectory optimization. Across $7$ visual control environments, WATO improves average success from $79.9\%$ for the imitation joint WAM to $91.7\%$, outperforming strong model-based, goal-conditioned RL, and generative control baselines. Compared with cross-entropy method (CEM), WATO is on average $11.5\times$ faster and uses $600.5\times$ fewer world model evaluations at deployment.
10. TIDE: Reclaiming Lost Performance In On-Policy Reinforcement Learning
TIDE:恢复同策略强化学习中损失的性能
AI 总结:TIDE是一种保留同策略RL训练语义的系统,通过动态重新利用rollout GPU和迁移rollout提升资源利用率,实现最高1.36倍加速,达最优吞吐量97%,泛化性强。
链接:https://arxiv.org/abs/2611.17924
机构:University of Washington(华盛顿大学); Brown University(布朗大学); UC Berkeley(加州大学伯克利分校); New York University(纽约大学)
作者:Mathew Jacob, Morgan Borjigin-Wang, Kan Zhu, Po Hao Chen, Yi Pan, Andy Ruan, Nayani Modugula, Ethan Lavi, Luis Ceze, Malte Schwarzkopf, Akshay Narayan, Deepti Raghavan, Stephanie Wang
英文摘要: Synchronous, colocated RL post-training of large language models (LLMs) today suffers from severe under-utilization due to long-tail rollouts. Inference engines fall idle waiting for long-tail rollouts or decode at low, inefficient batch sizes. To address this, we present TIDE, an RL training system that preserves on-policy training semantics while recovering resource utilization. TIDE does so by two complementary techniques: (1) dynamically repurposing rollout GPUs for training while long-tail rollouts complete and (2) dynamically migrating rollouts between inference engines to boost decoding throughput. TIDE automatically determines the right time to repurpose rollout resources through an adaptive migration policy, obtaining performance improvements that generalize across multiple applications and hardware configurations without requiring bespoke configuration. In our evaluation, TIDE provides end-to-end speedups of up to 1.36x over colocated systems, outperforming all evaluated on-policy baselines and achieving up to 97% of optimal throughput.
11. RL$^{\mathrm{RT}}$: On-Device Reinforcement Learning Runtime
RL$^{\mathrm{RT}}$:设备端强化学习运行时
AI 总结:研究针对设备端强化学习中执行体停滞或策略漂移问题,提出RL$^{\mathrm{RT}}$运行时,通过可调耦合参数等技术,在Jetson板上使1680万参数策略的截止期限缺失率降至1%以下。
链接:https://arxiv.org/abs/2611.18035
机构:Nanyang Technological University(南洋理工大学)
作者:Zexin Li, Xinwei Gao, Arvind Easwaran
英文摘要:On-device reinforcement learning runs a periodic actor and a learner on one embedded GPU shared with other workloads. Because the learner produces the actor's weights, existing designs stall the actor or let its policy drift. We present RL$^{\mathrm{RT}}$, an on-device runtime that makes this coupling a tunable parameter: a refresh bound limits actor releases between refreshes, and a GPU permit with slack-aware admission prioritises the actor and fills spare time with training atop any base scheduler. Under the real refresh cost on two Jetson boards, RL$^{\mathrm{RT}}$ keeps a 16.8 M-parameter policy's deadline misses below 1%, against 85 to 100% without it.
12. Enrichment-Oriented Virtual Screening of Perovskite Solar Cells through Reinforcement Learning
面向富集的钙钛矿太阳能电池虚拟筛选的强化学习方法
AI 总结:本研究针对钙钛矿太阳能电池实验优化的组合多样性问题,提出代理引导强化学习框架,通过TabPFN指导配方生成,在虚拟筛选中富集高性能候选,使PPO、RPPO的邻域支持命中率较基线提升显著。
链接:https://arxiv.org/abs/2611.18043
机构:Hong Kong Quantum AI Lab Limited(香港量子人工智能实验室有限公司); The University of Hong Kong(香港大学); The Hong Kong Polytechnic University(香港理工大学); MattVerse Limited(MattVerse有限公司); QuantumFabless Limited(QuantumFabless有限公司); Lixin Technology (Shenzhen) Co. Ltd.(立信科技(深圳)有限公司)
作者:Yezeyuan Zheng, Ziyang Hu, Maojun Sun. Ruijian Han, Jian Huang, Guanhua Chen, Jie Liu
英文摘要:Experimental optimization of perovskite solar cells is constrained by combinatorial diversity in absorber compositions, device layers, and processing, which makes virtual screening attractive for prioritizing recipes before fabrication. We develop a surrogate-guided reinforcement-learning framework that casts recipe generation as virtual screening, enriching candidate shortlists near high-performing experimental neighbors. A frozen Tabular Prior-data Fitted Network (TabPFN) guides recipe generation, while a reference pool of 890 measured devices enables neighborhood-based assessment. Five-fold evaluation on 1,846 devices shows top-ten selection raises mean power conversion efficiency (PCE) from 19.68\% to 23.74\%. Three learned policies are compared with six baselines under 3,000 surrogate evaluations per run. In top-100 shortlists, Proximal policy optimization (PPO) and recurrent PPO (RPPO) achieve neighborhood-supported hit rates of 23\% and 24\% (7.9- and 8.3-fold Pure Random's 2.9\%), versus 10\% (3.4-fold) for the baselines with the highest supported hit rate (L-SHADE and Ax BO, tied) at $K = 100$. Gains coexist with weak-support fractions. Of 9,000 recipes, 65.4\% match a composition family at similarity 0.80, falling to 11.7\% at 0.90. Results support enrichment-oriented prioritization but not experimental performance, seed robustness, or matched-budget advantage.
13. On numerical issues of divergences between nearly equal distributions
关于近似相等分布间散度的数值问题
AI 总结:本文发现分类分布间的标准散度(含KL散度等)在分布近似相等时存在数值问题,提出稳定重写方案并经测试验证,可用于知识蒸馏等优化场景。
链接:https://arxiv.org/abs/2611.18511
机构:Reflection AI(反射人工智能公司)
作者:Brandon Amos
英文摘要:Barron et al. (2026) recently identified numerical issues in the softmax and soft cross-entropy loss. We show that similar issues are present in standard divergence operations between categorical distributions. This includes the forward and reverse Kullback-Leibler (KL) divergence and generalized Jensen-Shannon divergence (JSD), as well as Monte Carlo KL estimates and entropy. When the distributions are nearly equal, rounding and cancellation issues affect the forward and gradient computations. These issues can affect settings using divergences in optimization objectives, such as knowledge distillation, reinforcement learning, and proximal methods. We propose numerically stable reformulations and provide example implementations for each setting, validated by property-based tests.
4. 生成模型与概率建模 | 5 篇
14. Identifying Latent Neural Dynamics with Recognition-Parametrised Gaussian Process Dynamical Systems
用识别参数化高斯过程动力学系统识别潜在神经动力学
AI 总结:本文提出RP-GPdyn模型,通过非参数高斯过程转移函数和RPM框架规避生成相关问题,可从合成与实验数据中揭示行为相关的潜在变量和动力学。
链接:https://arxiv.org/abs/2611.17487
机构:Gatsby Computational Neuroscience Unit(盖茨比计算神经科学单元); University College London(伦敦大学学院)
作者:Arielle Rosinski, Qianqian Feng, Lior Fox, Maneesh Sahani
英文摘要: Neural circuits are densely interconnected systems, and many neural computations are thought to be mediated by the dynamical evolution of activity within these recurrent networks, a hypothesis often referred to as "computation through dynamics". Under this view, understanding computation within real neural populations depends on building models of the dynamical rules governing the temporal evolution of recorded high-dimensional neural activity. Most commonly, such models depend on explicit generative parameterisations of (i) the (nonlinear) intrinsic dynamical flow field and stochasticity, (ii) the (nonlinear) mapping from dynamical state to neuronal activity, and (iii) the variability of individual neural responses given that dynamical state. Misspecification of any of these components can bias estimates of dynamics and latent trajectories. In this paper, we circumvent generation-related issues by introducing the Recognition-Parametrised Gaussian Process dynamics (RP-GPdyn) model. RP-GPdyn models the dynamical flow field using a nonparametric Gaussian Process-defined transition function and models the relationship of dynamics to neural activity implicitly using the Recognition-Parametrised Model (RPM) framework. We show that this generation-free approach uncovers meaningful, behaviourally relevant latent variables and dynamics from both synthetic and experimental datasets.
15. A Synthetic Benchmark for Target-Centric Causal Discovery in Industrial Processes
面向工业过程中以目标为中心的因果发现的合成基准
AI 总结:针对工业过程因果发现基准稀缺且难度固定的问题,提出一种围绕目标构建的两级结构因果模型合成基准,评估八种方法并分析其在难度叠加时的性能变化。
链接:https://arxiv.org/abs/2611.17556
机构:Svelaro GmbH(斯韦拉罗有限公司)
作者:Angelo Ziletti
英文摘要:Causal discovery promises to find which recorded variables drive a process target such as product quality, yield or energy use. Process data with known causes are rare, and in existing benchmarks the difficulty of identifying the causes of a target is either fixed by the recorded data or set for the whole graph. We present a synthetic benchmark for target-centric causal discovery in industrial processes. Its generator is a two-level structural causal model inspired by batch production, assembled from components that each model one phenomenon of process data, such as a control loop or a delayed effect. The graph is built around the target: without sensor error, every non-cause can be distinguished from the direct causes by conditioning on them or by time order. Each component is set independently, so the difficulty can be varied one condition at a time. We evaluate eight methods, from association measures to effect estimation, with an error analysis by the role of the selected candidate; all degrade as the difficulties combine, each in a way consistent with its assumptions.
16. Classifier-Guided Latent Diffusion for Small-Molecule Generation
分类器引导的潜在扩散模型用于小分子生成
AI 总结:本研究提出基于ChemBERTa的分类器引导潜在扩散框架,实现小分子的属性可控生成,在血脑屏障通透性等药物相关终点上生成有效新颖分子。
链接:https://arxiv.org/abs/2611.17650
机构:School of Computer Science(温莎大学计算机科学学院); University of Windsor
作者:Ali Forooghi, Luis Rueda, Alioune Ngom
英文摘要:Diffusion models have emerged as a promising class of generative models for molecular design because of their ability to learn complex chemical distributions and support conditional or guided generation. In this work, we investigate a latent diffusion pipeline for property-guided small-molecule generation. The proposed framework represents canonicalized SMILES strings using a frozen ChemBERTa encoder, trains a Transformer-based decoder to reconstruct SELFIES strings from molecular latent embeddings, and learns an unconditional denoising diffusion model in the ChemBERTa latent space. To enable property-directed generation, a differentiable latent property predictor is used to guide the diffusion sampling process. Generated SELFIES strings are converted to SMILES, validated using RDKit, and evaluated using molecular validity, uniqueness, novelty, and predicted property scores. We study guidance toward two drug-relevant binary endpoints: blood--brain barrier permeability and inhibition of human $\beta$-secretase 1. The results suggest that latent diffusion over pretrained molecular embeddings can generate chemically valid and novel molecules while enabling controllable steering toward desired molecular properties.
17. Analyzing Learning-Dynamics Across Loss and Prediction Choices for Diffusion Models
分析扩散模型中损失与预测选择之间的学习动态
AI 总结:本研究针对扩散模型中三种预测目标与三种训练损失的九种组合,分析了预测选择、损失空间及线性瓶颈对去噪精度和样本质量的影响,揭示了压缩场景下预测选择的关键作用。
链接:https://arxiv.org/abs/2611.17967
机构:POSTECH(浦项科技大学)
作者:Dongwoo Kim
英文摘要:Denoising generative models predict clean data ($x$), noise ($\epsilon$), or velocity ($v$), while training losses can be measured in any of these spaces. Although the resulting nine combinations are algebraically related, they can yield substantially different denoising accuracy and sample quality. We disentangle the effects of prediction and loss spaces. For a fixed prediction target, we show that changing the loss space is exactly equivalent to timestep reweighting and provide a heuristic analysis of how this reweighting affects generation quality. We then show that a rank-$m$ linear bottleneck compressing a $D$-dimensional noisy input imposes an irreducible squared-error floor of $D-m$ on noise and velocity prediction, whereas clean-data prediction can exploit low-dimensional data structure. Combining this bound with prediction-dependent error conversion yields distinct necessary conditions on bottleneck capacity. Experiments with U-Net and JiT across CIFAR-10, Imagenette, and ImageNet-256 support these theoretical predictions. Under compression, prediction choice strongly affects both denoising accuracy and sample quality, with noise-prediction errors closely matching the theoretical lower bound. Our results provide a quantitative understanding of how architectural bottlenecks interact with prediction and loss choices in denoising generative models.
18. Sample-efficient prediction of high-entropy alloy strength through outcome-aware robust sequential learning
通过结果感知的鲁棒序列学习实现高熵合金强度的样本高效预测
AI 总结:本研究提出ROSE-HEA框架,通过结果感知鲁棒序列学习,以更少样本实现高熵合金极限抗拉强度的高效预测,性能优于多种对比方法。
链接:https://arxiv.org/abs/2611.18462
机构:West Virginia University(西弗吉尼亚大学); University of South Carolina(南卡罗来纳大学)
作者:Ahmed Shoyeb Raihan, Md Habibor Rahman, Ashish Nimbarte, Imtiaz Ahmed
英文摘要: Accurate prediction of high-entropy alloy (HEA) strength can guide composition and processing decisions; however, obtaining tensile-test data for HEAs can be costly and experimentally demanding. This study proposes Robust Outcome-aware Sequential Experimentation for High-Entropy Alloys (ROSE-HEA), a sample-efficient framework for predicting ultimate tensile strength (UTS) from alloy composition and processing conditions. Its acquisition policy anticipates how possible UTS outcomes update predictions and the support for complementary Gaussian process (GP) descriptions. It then reassesses the worst-case expected predictive risk remaining across a reference domain to select informative candidates. A retrospective evaluation on 501 HEA records compares ROSE-HEA with expected-improvement (EI) and upper-confidence-bound (UCB) Bayesian optimization (BO), random GP sampling, and eight conventional regressors across 30 matched runs with shared initial observations and test conditions. Starting from 25 initial observations and acquiring 100 additional responses, ROSE-HEA achieves the lowest mean root-mean-square error (RMSE), at 152.84 MPa, and the highest mean R^2, at 0.7443. Mean RMSE is reduced by 6.16% and 6.37% relative to EI and UCB, respectively. The selected observations improve prediction across six regressor families and provide broader design-space coverage. ROSE-HEA also surpasses the strongest conventional regressor's mean predictive performance using 125 rather than 185 observations, corresponding to 32.4% fewer training observations. These findings demonstrate the potential of outcome-aware robust sequential learning to improve UTS prediction in HEAs under constrained training budgets.
5. 优化、泛化与理论分析 | 6 篇
19. Classification with Large-Step Gradient Descent: Unifying Self-Stabilization and Convergence Rates
大步长梯度下降分类:统一自稳定与收敛速率
AI 总结:本研究将统一几何视角扩展到可分线性分类的指数尾损失,确定曲率定义的参考子空间,推导涵盖不稳定与稳定区域的迭代显式边界,揭示大步长的瞬态隐含偏差。
链接:https://arxiv.org/abs/2611.17459
机构:University of Pennsylvania(宾夕法尼亚大学)
作者:Salma Tarmoun, Lachlan Ewen MacDonald, Konstantinos Emmanouilidis, Ziqing Xu, René Vidal
英文摘要:Neural networks are often trained with gradient descent (GD) using step sizes that exceed classical stability thresholds, a regime where standard convergence theory no longer applies. Despite exhibiting non-monotonic loss and oscillatory dynamics, this regime frequently leads to faster convergence and better generalization. Existing theoretical perspectives offer complementary but incomplete insights: one identifies a self-stabilization mechanism that drives GD toward flat regions but does not yield convergence rates; another derives rigorous rates for specific losses but does not explain the underlying stabilization mechanism; and a third unifies these views for overparameterized least squares, but relies on the existence of a minimizer manifold, which is absent in classification settings. In this work, we extend this unified geometric perspective to exponential-tail losses, including logistic and cross-entropy losses in separable linear classification, where the loss infimum is not attained at any finite parameter. We identify a curvature-defined reference subspace that replaces the role of the minimizer manifold, yielding a coupled dynamical system in which orthogonal oscillations are damped by parallel progress along directions of decreasing sharpness. Under regularity conditions, which we verify for logistic and multiclass cross-entropy losses on symmetric data models, we derive explicit bounds for the iterates, not just the loss, covering both the unstable and stable regimes, and revealing a three-phase damping structure in the latter. Our analysis further uncovers a transient implicit bias induced by large step sizes: although GD converges asymptotically to the max-margin direction, large steps can leave persistent orthogonal residuals and, in certain geometries, amplify them, affecting finite-time alignment with the max-margin direction.
20. Adversarially Batched Online Learning
对抗式批量在线学习
AI 总结:该研究提出对抗式批量在线学习模型,针对四类经典问题分析其复杂度与悔界,证明无批量感知学习器可通过自适应加倍技巧达到上界,且下界对有批量感知学习器仍成立。
链接:https://arxiv.org/abs/2611.17500
机构:University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)
作者:Mingda Qiao, Kerui Wu
英文摘要:We introduce adversarially batched online learning, where the learner may update its decision rule only at a restricted set of time steps. Equivalently, the time horizon is partitioned into batches, within which the learner must use a fixed policy. We study this model for four canonical problems: stochastic bandits, online convex optimization, prediction with expert advice, and adversarial bandits. For stochastic bandits, we identify a universal complexity measure based on relative batch growth and establish both gap-dependent and gap-independent regret bounds. We show that the multiplicative penalty relative to the standard gap-dependent complexity can grow superlinearly in batch hardness. For the remaining three, we show that the optimal regret is tightly characterized by the 2-norm of the batch-length sequence. The upper bound is achieved by a batch-oblivious learner who does not know the batch structure, via a generic adaptive doubling trick tailored to this complexity measure. In contrast, the lower bound holds even for batch-aware learners.
21. Complex Schrödinger Bridges
复薛定谔桥
AI 总结:针对扩散桥优化空间庞大的问题,本文提出复薛定谔桥(CSB)及图像到图像CSB(I²CSB),将其应用于量子电动力学模拟,验证了复值扩散的优势。
链接:https://arxiv.org/abs/2611.17746
机构:Department of Computing(计算机系); Imperial College London(帝国理工学院)
作者:Dong-Sig Han, Tolga Birdal
英文摘要:Diffusion bridges have emerged as versatile frameworks for facilitating transformations between arbitrary data distributions. However, these approaches are hindered by an immense optimization space and its underlying high-order structures. This paper explores a variant of diffusion bridges for solving real-world problems in complex vector spaces governed by scaling and rotation laws, such as Hamiltonian structures. To address this, we introduce conformal optimal transport (COT), a complex-valued transportation framework designed for physical systems with geometric and dissipative dynamics under a geometric lifting. Building on this, we propose a new class of dynamical diffusion bridges, called complex Schrödinger bridges (CSBs), whose derived algorithms can handle diffusion-based tasks using a conformal geometric prior. For scalability, we propose image-to-image CSB (I$^2$CSB), a tractable diffusion-bridge technique with an analytic spiral posterior. Finally, we implement a physics-informed CSB algorithm within simulations of quantum electrodynamics, mimicking the logical behavior of quantum logic gates. Our extensive results validate the underlying theory while highlighting advantages of complex-valued diffusion.
22. ParetoM$^3$: Learning on the Pareto Set under Preference Guidance via Min-Max-Min Optimization
ParetoM$^3$:基于偏好引导的帕累托集学习的极小-极大-极小优化方法
AI 总结:针对偏好引导的多目标优化问题,提出基于罚函数的极小-极大-极小公式及单循环一阶算法ParetoM,可高效求得近似弱帕累托最优解,兼具理论收敛性与实际性能。
链接:https://arxiv.org/abs/2611.18252
机构:The Chinese University of Hong Kong(香港中文大学); Shun Hing Institute of Advanced Engineering(信兴高等工程研究院)
作者:Pei Tang, Songtao Lu
英文摘要:Learning across multiple inherently conflicting objectives requires selecting desirable trade-offs from the Pareto set. In this work, we study preference-guided multi-objective optimization, where a predefined preference function is minimized over the weak Pareto set of multiple nonconvex objectives. Leveraging a merit function that vanishes on the weak Pareto set, we propose a penalty-based min-max-min formulation, termed the M$^3$ problem, which unifies preference optimization and the enforcement of weak Pareto optimality in a single objective. We further develop ParetoM$^3$, a single-loop first-order algorithm for computing stationary solutions of the resulting M$^3$ problem. Under a local Kurdyka-Lojasiewicz assumption, we prove that ParetoM$^3$ finds an $\epsilon$-stationary point of the M$^3$ problem that is also approximately weakly Pareto optimal for the original multi-objective problem when the penalty parameter is sufficiently large, with explicit non-asymptotic convergence rates. We also show that this stationarity notion recovers existing optimality criteria, including approximate preference stationarity and approximate Karush-Kuhn-Tucker conditions, under the same assumptions used in prior works. Experiments on a synthetic benchmark, image classification, regression, and math reasoning demonstrate that ParetoM$^3$ reliably attains preferred weak Pareto optimal solutions while achieving strong practical performance. Code is available at this https URL.
23. Deep Neural Networks Training Efficiency: Does Grokking Modify its Dynamics?
深度神经网络训练效率:Grokking是否会改变其动态特性?
AI 总结:本研究以单位能量准确率衡量训练效率,通过模运算、MNIST场景及不同精度的神经网络模型,结合Orthograd测试,发现Grokking未实质性改变训练效率动态特性。
链接:https://arxiv.org/abs/2611.18396
机构:Technological University Dublin(都柏林理工大学); Trinity College Dublin(都柏林圣三一大学)
作者:Eduardo Cueto-Mendoza, John D. Kelleher
英文摘要:We study whether grokking, the delayed emergence of out-of-distribution generalization after apparent overfitting, alters training efficiency in deep neural networks, where efficiency is measured as accuracy per unit energy. Using two canonical settings, modular arithmetic and MNIST, we analyze two neural network models under 16-, 32-, and 64-bit precision and use Orthograd to test whether grokking produces noticeable deviations from the typically decreasing dynamics of training efficiency. We consider both short training runs of up to 500 epochs and long training runs of up to 20,000 epochs, and in both cases identify grokking as a sharp improvement in test accuracy after a sustained train-test gap. In the short-horizon experiments, applying Orthograd at progressively stronger levels during early training does not induce grokking, and efficiency remains smoothly decreasing. In the long-horizon experiments, Orthograd induces grokking, but the efficiency curves remain approximately monotonic and show no appreciable local increase at the grokking transition. These results suggest that, in our setting, grokking does not materially alter overall training-efficiency dynamics.
24. WeightBench: Evaluating Language Models as Weight-Space Programmers
WeightBench:评估语言模型作为权重空间程序员的性能
AI 总结:本文提出WEIGHTBENCH基准,在42项权重空间编程任务上评估LLMs,发现前沿智能体可读写小型网络但无法修补或无数据压缩语言模型,还给出了多款模型的宏观得分。
链接:https://arxiv.org/abs/2611.18553
机构:The University of Southern Mississippi(南密西西比大学)
作者:Aayush Marasini, Barsat Khadka, Nick Rahimi
英文摘要:Recent work shows that large language models (LLMs) can operate directly on the parameters of other neural networks. They can read what a network was trained to do, fix a network that fails, and write working networks from scratch, all without gradient descent. This capability has been termed Weight-Space Programming (WSP). Exploring this new paradigm systematically requires a robust benchmark. We introduce WEIGHTBENCH, a benchmark that evaluates LLMs of increasing capability on 42 WSP tasks across five tracks: reading, fixing and writing weights, recognizing edits that are impossible, and data-free compression. The networks whose weights the LLMs read and edit range from 2K-parameter control policies to 7B-parameter language models. Experimental benchmark results show that frontier agents can already read small networks and write working control policies without ever running them, but cannot yet patch language models, compress them without data, or tell an impossible edit from a hard one. On all 42 tasks, Claude Opus 5.5 reaches a macro score of 0.535 (Sonnet 5.5 0.466, Haiku 5.5 0.402, DeepSeek v4-flash 0.215); on the 38 tasks it was run on, GPT-6.1-sol reaches 0.568 against Opus's 0.546. Code, the task registry, our OS-level sandbox harness, and the live leaderboard are publicly available at this https URL.
6. 高效学习、压缩与部署 | 2 篇
25. Antidistillation is Cheap: Lightweight Distillation-Resistance via Stylistic Corruption
抗蒸馏成本低廉:通过风格污染实现轻量级抗蒸馏
AI 总结:本研究提出轻量级抗蒸馏防御框架,通过向教师模型激活注入风格引导向量破坏学生蒸馏学习,开销可忽略且保留文本自然性,可抵御黑盒API下的序列级蒸馏攻击。
链接:https://arxiv.org/abs/2611.17772
机构:College of Computing and Data Science(计算与数据科学学院); Nanyang Technological University(南洋理工大学)
作者:Anh Tu Ngo, Anupam Chattopadhyay
英文摘要: Knowledge distillation (KD) is a highly effective paradigm for transferring capabilities from large language models (LLMs) to smaller, more specialized student models. In commercial deployment where frontier models are restricted behind black-box APIs, sequence-level distillation remains a potent vector for competitors to clone proprietary capabilities at a fraction of the development cost. Existing defenses mostly rely on surrogate models to manipulate next-token sampling, which increases computational overhead and real-time inference latency. In this work, we propose a lightweight defense that dynamically injects style-steering vectors into the teacher model's activations upon malicious queries. This framework offers exceptional flexibility, allowing hosts to customize target defensive styles and dynamically blend them to maximize stylistic variance. Crucially, this inference-time intervention preserves semantic utility and fluency during malicious queries, misleading adversaries into believing that they are extracting pristine teacher outputs, while standard consumers continue to receive original, unmodified responses. Our experiments demonstrate that this framework successfully disrupts student learning, achieving substantial anti-distillation performance while incurring negligible overhead and preserving text naturalness. Our code is available at this https URL.
26. Neural Classifiers as Error-Correcting Codes
作为纠错码的神经分类器
AI 总结:本文将监督深度分类表征为香农意义下纠错码的解码过程,揭示了神经分类器与纠错码的对应关系,为损失函数、决策边界稳定性等提供几何基础,并拓展至自监督编码器。
链接:https://arxiv.org/abs/2611.18239
机构:St. Petersburg State University(圣彼得堡国立大学); Braude College(布劳德学院)
作者:Sergey Salishev, Anton Makarov, Oleg Granichin, Renata Avros, Zeev Volkovich
英文摘要:A unified framework is proposed that characterizes supervised deep classification as the decoding of error-correcting codes in the Shannon sense. Cross-entropy optimization is shown to align softmax classifiers with maximum-likelihood decoding, where logits map to Hamming distances to class-specific codewords. This correspondence explains the emergence of standard divergence objectives (e.g., Kullback-Leibler, Jeffreys) and provides a geometric basis for the stability of decision boundaries. Furthermore, the geometries of Neural Collapse and LeJEPA are identified as optimal constellations for decoding under isotropic noise. Unlike classical Error-Correcting Output Codes, deep networks are shown to learn effective codebooks in the feature space implicitly. This insight is leveraged to derive novel criteria for lossless quantization, improved knowledge distillation, and architectural regularization based on code redundancy. Finally, this perspective is extended to self-supervised encoders, offering a cohesive explanation for the geometry of latent representations in modern neural models.
7. 联邦学习、隐私与安全 | 2 篇
27. Federated Physics-Informed Thermal Field Prediction Across Unseen Geometries in Distributed Additive Manufacturing
分布式增材制造中跨未知几何的联邦物理信息热场预测
AI 总结:本文提出Fed-PIGANO联邦框架,在不共享零件几何的前提下聚合各站点的PI-GANO模型,在金属AM热场预测中精度接近集中式模型,优于仅本地训练,可实现跨未知几何的高效热预测。
链接:https://arxiv.org/abs/2611.17794
机构:Virginia Tech(弗吉尼亚理工大学)
作者:Amirul Islam Saimon, Zhenyu (James) Kong
英文摘要:In additive manufacturing (AM), each change in part geometry requires a new thermal simulation, which makes design evaluation over many candidates costly. Geometry-aware models reduce this cost by predicting thermal fields on unseen parts with a single learned model, but they assume that diverse geometries are available centrally. This assumption is restrictive when each manufacturing site holds only a limited set of proprietary part designs that it cannot share. We propose Fed-PIGANO, a federated framework that trains physics-informed geometry-aware neural operator (PI-GANO) models at individual sites and aggregates their geometry encoders and prediction networks without sharing part geometries. We evaluate the framework on a 2D steady-state thermal benchmark for metal AM, with geometries from five polygonal families distributed across three sites under four scenarios that range from identical to strongly different family compositions. Over seven replications, Fed-PIGANO achieves mean relative L2 errors of 1.83% to 2.04% across all 12 scenario-site cases, compared with up to 20.46% for local-only training, and consistently yields lower PDE residuals. Its prediction accuracy is comparable to that of a centralized model trained on the pooled geometries of all sites. These results demonstrate that federated learning lets manufacturing sites benefit from each other's geometries without sharing them, enabling rapid thermal prediction on new part designs for tasks such as shape optimization, inverse design, and uncertainty quantification.
28. Differentially Private Federated Class-Incremental Learning for EEG Mental State Classification
用于脑电信号(EEG)心理状态分类的差分隐私联邦类增量学习
AI 总结:针对小型客户端联邦的脑电心理状态分类,提出FedEEG结合突触智能与自适应FedProx,引入头范围客户端级DP,在减少灾难性遗忘的同时实现高效隐私保护。
链接:https://arxiv.org/abs/2611.17944
作者:Baran Can Gül, Ali Gülümser, Nasser Jazdi, Michael Weyrich
英文摘要:Federated learning (FL) under differential privacy (DP) is typically evaluated on large client cohorts, where subsampling and cross-client averaging amplify privacy and smooth injected noise. Personal biosignal applications such as wearable EEG instead involve small federations of a handful of subjects, a regime whose interaction with formal client-level DP is largely uncharacterized. We study differentially private federated class-incremental learning in this small-cohort regime, combining a public EEG dataset with a custom four-channel MUSE 2 recording set into a K=5-client federation, and give a masked per-class training protocol that avoids degenerate gradients and missing negative supervision under class-incremental streaming. We propose FedEEG, combining Synaptic-Intelligence consolidation with a lagged adaptive FedProx term, and show it reduces catastrophic forgetting relative to FedAvg, FedProx, and a federated Learning-without-Forgetting baseline; on-device balanced-batch replay reduces mean forgetting by a further 56.7%. A class-scoping diagnosis yields $50.5\%\pm3.6\%$ accuracy with 6 seeds and 2.02 times chance. We also introduce head-scoped client-level DP, which protects the classification head and alone reduces the achievable $\varepsilon$ by 200 times at a matched round budget; combined with fewer communication rounds it reaches $\varepsilon\!\approx\!10.4$ with utility not statistically distinguishable from non-private training.
8. 鲁棒性、不确定性与可信学习 | 4 篇
29. Alignment with Reflect-Reasoning: Learning How To Follow Principles
与反思推理对齐:学习如何遵循原则
AI 总结:本文提出Reflect-Reasoning训练方法,教会模型针对对齐原则推理,在五款模型上优于系统提示等策略,可泛化至医疗、金融领域,减少原则违规且安全鲁棒,无需额外微调。
链接:https://arxiv.org/abs/2611.17398
机构:Duke University(杜克大学)
作者:Henry Bell, Caroline Zhang, Dhaval Potdar, Mohammed Mobasserul Haque, Brandon Fain
英文摘要:The appropriate governing norms and principles for the alignment of Large Language Models (LLMs) often depend on cultural context and deployment application. However, most alignment techniques focus on training models to conform to human preferences or constitutional principles specified at training time and subsequently fixed. In practice, many deployers rely on system prompting to implement contextual norms and guardrails at inference time. Prior work has shown that post-generation reflective reasoning with critique and revision can improve conformance compared to simple system prompting, but such methods are limited to the reasoning abilities inherent in the trained model. We introduce Reflect-Reasoning, a training method that teaches models how to reason about alignment to principles, rather than simply which principles to follow. Across five models, Reflect-Reasoning consistently outperforms both system prompting and explicit prompting strategies for in-context reflective reasoning. These improvements extend and generalize to entirely out-of-distribution domains of medical and financial principles. We additionally demonstrate that Reflect-Reasoning reduces the occurrence of rare but serious principle violations. Finally, we show that Reflect-Reasoning does not erode the safety engineering of a model and is robust against jailbreaking attempts using adversarial constitutions. Overall, our results demonstrate that Reflect-Reasoning is a scalable method for training constitutional alignment as a generalizable reasoning capability, enabling models to adapt to novel principles and produce transparent reasoning traces without additional fine-tuning.
30. Generative Design with Real-time Physics Explainability: Towards Product Definition in the Age of AI
结合实时物理可解释性的生成式设计:AI时代的产品定义
AI 总结:本文将可逆神经网络与生成式物理模拟结合,提出带不确定性量化的生成式设计框架,开发翼型、燃烧室设计交互环境,解决生成式设计幻觉问题,为AI时代产品定义提供方案。
链接:https://arxiv.org/abs/2611.17560
作者:M. de Campos, C. Drygala, E. Ross, A. Bruce, M. Bohon, H. Gottschalk
英文摘要:In this article, we explore opportunities from using generative AI in mechanical engineering. On the one hand, generative methods based on invertible neural networks have been recently proposed for the solution of inverse design problems, allowing to infer design parameters from performance labels. On the other hand, generative AI models have shown that they can act as real time capable surrogates for physics based simulations. Here we suggest that these two streams should be combined in a unified framework, where INN are used to control the design process from the customer requirements perspective and the generative simulation of the systems physics adds a layer of explainability, why the proposed design fulfils the requirements. As generative design is prone to hallucinations, we propose uncertainty quantification to fend off physically infeasible requests. Finally, validation with classical tools is a requirement for generative design process. To demonstrate the capabilities of our novel generative design paradigm, we develop two interactive environments, one for airfoil design based on simulator data and one for the combustor design space exploration based on measured data.
31. Representational Geometry as a Diagnostic for Adversarial Robustness
表征几何作为对抗鲁棒性的诊断依据
AI 总结:本研究以MNIST上的MLP为对象,用M-PHATE分析对抗训练的表征几何,发现其会改变网络表征结构,且鲁棒准确率与表征稳定性排序相反,为模型鲁棒性审计提供新诊断依据。
链接:https://arxiv.org/abs/2611.17684
机构:California State University, Northridge(加州州立大学北岭分校); University of California San Diego(加利福尼亚大学圣地亚哥分校); Halıcıoğlu Data Science Institute(哈利乔卢数据科学研究所)
作者:Brandon Ismalej, Alex Cloninger, Gal Mishne
英文摘要:Adversarial training is a common technique for making neural networks more robust to small, intentionally crafted input perturbations, and robustness is commonly measured through accuracy under attack. By exploring inter-network representations across different adversarial training objectives, we can analyze whether multiple networks organize their latent representations similarly. We study Multilayer Perceptrons trained on MNIST under three adversarial training regimes and compare the resulting population training dynamics and geometry to those of a vanilla network. We use M-PHATE to embed data samples across training epochs and examine how the geometry of the data changes during training under adversarial objectives. On penultimate-layer representations we measure displacement between clean and perturbed points, distributional distance through maximum mean discrepancy, and nearest-neighbor recovery. Our visualizations and quantitative analyses show that adversarial training leads to structural changes in how networks organize internal data representations, and robust accuracy and representational stability can rank the same defenses in opposite ways. These findings support a discussion of re-evaluating how practitioners approach the auditing of model robustness by treating latent representations and their training trajectories as diagnostic artifacts across sets of networks.
32. Black-Box Uncertainty Quantification for Large Language Models via Ensemble-of-Ensembles
基于集成集成的大语言模型黑盒不确定性量化
AI 总结:该研究提出两级集成的黑盒方法,通过分解偶然与认知不确定性,在问答基准和指令调优LLM上实现与白盒基线相当的性能,可区分提示歧义与模型知识缺口。
链接:https://arxiv.org/abs/2611.18453
机构:Rensselaer Polytechnic Institute(伦斯勒理工学院); Lirio; IBM Software Innovation Lab(IBM软件创新实验室); IBM Research(IBM研究院)
作者:Wang Ma, Debarun Bhattacharjya, Junkyu Lee, Nhan H Pham, Harsha Kokel, Qiang Ji
英文摘要: Reliable use of large language models (LLMs) requires uncertainty estimates that separate ambiguity intrinsic to a prompt from genuine knowledge gaps. Bayesian and deep-ensemble methods deliver this aleatoric/epistemic decomposition in principle, but are computationally prohibitive at LLM scale and require white-box access. Existing black-box methods, in contrast, summarize to a single scalar that cannot make the distinction. We introduce a two-level ensemble that bridges this gap. Stochastic decoding of a fixed prompt forms the inner ensemble; meaning-preserving semantic perturbations of the prompt form the outer ensemble. Variability is measured in a continuous embedding space, and the law of total covariance gives an exact within-/between-perturbation decomposition to estimate aleatoric and epistemic uncertainty (AU/EU); it requires only black-box sampling access. On top of this estimator, we contribute three theoretical results that ground the framework: (i) a finite-sample bias identity for nested Monte Carlo with a closed-form bias-corrected epistemic estimator; (ii) a Bayesian bridge bounding the gap between perturbation-population AU/EU and Bayesian targets; and (iii) a separation result identifying a class of failure modes that any consistency-only black-box method provably misses while perturbation-based EU detects. Across five short QA benchmarks and four instruction-tuned LLMs spanning two families and two scales, our estimator is competitive with strong white-box baselines, and at a matched generation budget it matches leading black-box methods on error ranking while decomposing AU and EU; controlled paired interventions show that AU and EU respond selectively to distinct, actionable sources of failure: prompt ambiguity and model knowledge gaps; and a long-form pilot on the NQ long-answer split shows the framework extends to claim-level factuality without retraining.
9. 图学习与结构化数据 | 2 篇
33. ERGo: Energy-Efficient Hybrid Graph Neural Network Training on Processing-In-Memory Architectures
ERGo:存算一体架构上的高能效混合图神经网络训练
AI 总结:ERGo是一种混合GNN训练框架,可在PIM及异构NVM-SRAM架构上切换训练阶段,减少片外访问与NVM写操作,实现最高3.15倍加速、10.5倍能效提升及33倍NVM寿命延长。
链接:https://arxiv.org/abs/2611.17478
作者:Pratyush Dhingra, Chibuike E. Ugwu, Janardhan Rao Doppa, Partha Pratim Pande
英文摘要:Processing-in-memory (PIM) has been proposed as an alternative computing paradigm for training Deep Neural Networks, including Graph Neural Networks (GNNs). Despite these advancements, training GNN workloads on PIM devices necessitates off-chip memory access. This off-chip access is expensive in terms of performance and energy, thereby impacting the overall energy efficiency of the training process on PIM platforms. In this paper, we propose a novel hybrid training framework called ERGo that automatically switches from a full-parameter phase to a parameter-efficient phase during the training process with negligible loss in predictive accuracy. The parameter-efficient phase employs low-rank representations of GNN weights, effectively reducing the number of trainable parameters. This helps in reducing the off-chip access during the end-to-end training process on PIM architectures, leading to notable improvements in both performance and energy efficiency. ERGo outperforms the conventional full-parameter GNN training on a PIM-based platform by up to 3.15x in speedup and enhances energy efficiency by 10.5x. Furthermore, ERGo offers additional advantages when utilized on heterogeneous architectures incorporating non-volatile memory (NVM) and static random-access memory (SRAM). Training on the heterogeneous NVM-SRAM architecture typically utilizes NVM for the forward-pass and SRAM for the backward-pass. However, NVM cells suffer from low device endurance and repeated write operations due to weight updates can lead to poor lifetime. ERGo improves the lifetime of NVM devices by freezing the weights and preventing weight updates in the parameter-efficient phase. Experimental results demonstrate that ERGo improves the lifetime of heterogeneous NVM-SRAM architecture by up to 33x in comparison to full-parameter implementation.
34. Quantum Graph Neural Networks: Architectures, Trainability, and Applications
量子图神经网络:架构、可训练性与应用
AI 总结:本综述系统梳理量子图神经网络(QGNNs)的架构、可训练性等,提出统一形式体系,对比五大架构家族,发现对称性是最充分的归纳偏置但证据薄弱,明确开放挑战与研究议程。
链接:https://arxiv.org/abs/2611.17886
机构:School of Computer Engineering, Iran University of Science and Technology(伊朗科技大学计算机工程学院); Faculty of Information and Communications Technology, Malek Ashtar University of Technology(马利克·阿什塔尔科技大学信息与通信技术学院)
作者:Zeinab Sharifi, Hossein Shirazi
英文摘要:Quantum graph neural networks (QGNNs) apply parametrized quantum circuits to graph-structured data, with the aim of overcoming limits of classical graph neural networks in scalability, expressivity, and long-range information flow. Since the first Hamiltonian-based model in 2019, the field has produced many architectures, applications, and claims, but the evidence behind them has not been assessed systematically. This survey introduces a unified formalism that describes every QGNN as an encoder, a graph-conditioned circuit, observables, and an optional classical head, together with a circuit-level condition for permutation equivariance and a resource model for comparing costs. We organize the literature into five architecture families (convolutional, equivariant, message-passing and recurrent, Hamiltonian, and hybrid) and compare them by qubit cost, symmetry, scalability, and evidence. We then review symmetry and geometric inductive biases (permutation, rotation, and Lorentz), the results on expressivity, trainability, noise, and scalability, and applications in high-energy physics, chemistry, finance, healthcare, earth observation, and transportation. An audit of datasets and evaluation practices leads to a minimum reporting protocol. Our main finding is that the design space is rich and symmetry is the best-supported inductive bias, whereas the evidence remains thin: results are mostly simulated, on small graphs, at parity with classical models or with fewer parameters, and no advantage has yet been established on tasks over classical graph data. We identify five open challenges and a research agenda covering provable advantage, equivariant and geometric designs, fault-tolerant implementations, and shared benchmarks. The coverage extends through 2026 and emphasizes recent work.
10. 迁移、元学习与持续学习 | 1 篇
35. Direction or Magnitude? Learning Scalars over Task-Calibrated Directions
方向还是幅度?学习任务校准方向上的标量
AI 总结:该研究提出参数高效微调方法SCALAR,通过学习任务校准方向上的标量,在性能与LoRA相当的情况下,大幅减少可训练参数、降低峰值训练内存并提升吞吐量,适配多种任务。
链接:https://arxiv.org/abs/2611.17784
机构:National University of Defense Technology(国防科技大学); OPPO AI-Center(OPPO AI中心)
作者:Ziqing Wen, Xiaohui Song, Jiahuan Wang, Ping Luo, Junlin Zeng, Dongsheng Li, Kele Xu, Tao Sun
英文摘要: Parameter-efficient fine-tuning (PEFT) aims to preserve adaptation quality while reducing training costs. We propose SCALAR, which achieves performance comparable to LoRA with substantially fewer trainable parameters, lower peak training memory, and higher throughput. SCALAR constructs a fixed input basis from task activations and assigns a random output dictionary to each input direction. Fine-tuning learns only layer-specific scalar coefficients, reducing gradient and optimizer-state storage. Grouped computation aggregates output atoms before applying the adapter to token activations, while dictionary sharing across compatible layers reduces fixed-basis storage. Experiments on commonsense reasoning, mathematical reasoning, code generation, and knowledge evaluation after instruction tuning demonstrate effective adaptation at small trainable budgets. On commonsense reasoning, SCALAR achieves accuracy comparable to LoRA with about 4% of its trainable parameters. System measurements on Qwen2.5-7B show 20% lower peak training memory and 6% higher throughput than LoRA. The combination of adaptation quality, a compact trainable state, and training efficiency makes SCALAR a promising approach to resource-constrained fine-tuning.
11. 数据集、基准与评测 | 3 篇
36. Unfinished-Bench: Measuring Rule Violations by Persistent Agents in Realistic Work Environments
Unfinished-Bench:测量现实工作环境中持久智能体的规则违反情况
AI 总结:Unfinished-Bench基准针对现实工作环境中持久智能体的规则违反问题,通过97个场景实验发现,持久性会显著提升内部文档规则的违反率,凸显需评估该风险。
链接:https://arxiv.org/abs/2611.17460
机构:NAVER AI Lab(NAVER AI实验室)
作者:Seunghyun Lee, Jaehui Hwang, Dongyoon Han, Sangdoo Yun
英文摘要:AI agents are increasingly equipped with persistence toward task completion to run delegated work autonomously for long periods, under many unstated constraints from internal documents and other people's authority. When completion requires violating a rule, the agent must decide alone, yet benchmarks of instruction-rule conflicts state the rule in the prompt or keep it hidden and do not evaluate persistence. We present Unfinished-Bench, a benchmark that gives models persistence in autonomous runs without a user, in realistic work environments with embedded rules. In each of its 97 scenarios across 7 organizations and 7 risk categories, the goal and the rule cannot both hold. We find that persistence raised violations of a rule in an internal document from 32.2% to 43.6%, five times the 8.5% for the same rule stated by the user. Of the document-rule violations, 98.3% occurred after the rule was displayed, and in 89% of a judged sample the agent first wrote down the rule. Violations of rules placed in the environment without user oversight can lead to serious incidents, so persistence-driven risks need to be evaluated. Benchmark documentation: this https URL
37. DeltaVisionX: A Low-Cost Vision-Guided Automation System Using YOLOv11 and PLC-Based Actuation
DeltaVisionX:一种使用YOLOv11和基于PLC的执行机构的低成本视觉引导自动化系统
AI 总结:该研究提出DeltaVisionX系统,通过YOLOv11与台达DVP-SE PLC的编码器同步集成,实现低成本工业物体分拣,精度0.97、帧率100ms、吞吐量80个/分钟,可降低劳动力依赖并提升制造效率。
链接:https://arxiv.org/abs/2611.17959
作者:Lara Sobh (AUST), Marc Nahhas (AUST), Francisco Katach El Halabi (AUST), Michel Owayjan (AUST, IREENA, Nantes Univ), Fadi Elias Sleiman
英文摘要:This paper presents DeltaVisionX, a low-cost industrial automation system that integrates real-time computer vision with PLC-based actuation for object classification and sorting. The system uses the YOLOv11 (You Only Look Once) deep learning model to detect objects on an operating conveyor belt and communicates detection results to a Delta DVP-SE PLC, which actuates pneumatic pistons for sorting. A custom dataset was created, labeled, and augmented to train the YOLOv11 model, achieving a mean average precision of 0.97 with real-time inference of 100 ms per frame. Encoder-based tracking ensures reliable synchronization between detection and actuation, supporting a throughput of 80 objects per minute. Results show that affordable, locally developed automation can reduce labor dependency and improve manufacturing efficiency. The novelty of the proposed system lies in its encodersynchronized vision-PLC integration rather than in the detection model itself. Future work includes integrating a highspeed Delta robot with EtherCAT-based servo control for advanced pick-and-place operations.
38. MarathonTS: a benchmark of long synthetic time series from window assembly and long-series generators
MarathonTS:基于窗口组装与长序列生成器的合成长时序基准测试
AI 总结:本研究提出首个统一对比窗口组装与长序列生成器两类方法的MarathonTS基准,通过多维度评估发现窗口选择比接缝处理更重要,无方法能如真实序列般训练下游模型,相关成果公开以保障可复现。
链接:https://arxiv.org/abs/2611.18190
作者:Ilyas Varshavskiy, Sergey Shulgin, Shuhrat Khalilbekov, Bonu Boboeva, Azizjon Azimi
英文摘要:Many applications of synthetic time series require a series that is much longer than the windows on which a generative model is trained. Such a series can be assembled from a pool of short generated windows, which requires deciding which windows are taken, in what order, and how their seams are processed, or it can be produced directly by a long-series generator. This study presents MarathonTS, to our knowledge the first open benchmark that compares both families under one protocol. Every method produces a series of the same length on 9 open hourly datasets with 10 seeds. The series is evaluated by its fidelity to the real data (83 metrics in 12 groups, against three real references: train, validation and an out-of-time split), by its utility (models are trained on the synthetic series only and tested on real data, TSTR against TRTR, in 14 classification and regression tasks), by its memorisation of the training data and by its computational cost. The statistical analysis is carried out as a separate stage that reads the published tables and gives the rankings of every method in every slice, the answers to the research questions with tests and uncertainty, and the results of a pre-specified confirmatory family. In the main run, the methods differ in both confirmatory cells; the choice of windows matters more than the processing of their seams, which does not improve the series, and no method trains the downstream models as well as the real series. The top tier of the leaderboard is reproduced on other hardware, whereas the exact places within it are not. For the reproducibility of the study, the code, the data hashes and all results are publicly available (links below).
12. 机器学习应用 | 6 篇
39. Logically Consistent Accurate Forecasts
逻辑一致的准确预测
AI 总结:该研究针对大语言模型智能体预测系统的逻辑一致性缺陷,提出微调监督语言模型的方法,在ForecastBench上使检索增强型GPT-5.1的Brier分数提升9.3%,结构不一致性降低82%-90%,实现一致性与准确性的协同提升。
链接:https://arxiv.org/abs/2611.17735
机构:Bridgewater AIA Labs(桥水AIA实验室); Massachusetts Institute of Technology(麻省理工学院)
作者:Kate Yuan, Rohan Alur, Manish Raghavan, Devavrat Shah
英文摘要:Agentic forecasting systems based on large language models (LLMs) are now competitive with expert human forecasters, but these systems still suffer from a critical limitation: the inability to produce forecasts that are logically consistent. For example, forecasts for related events often fail to satisfy the axioms of probability, which in turn implies that related forecasts cannot simultaneously be correct and undermines their utility for decision makers. Enforcing consistency is not trivial -- naive approaches (e.g., projection onto the set of consistent forecasts) can degrade accuracy. We argue that the key to overcoming the apparent tradeoff between consistency and accuracy lies in the reasoning which supports each forecast. We finetune a supervisory language model that leverages this reasoning to jointly reconcile inconsistencies while improving the accuracy of related forecasts. On ForecastBench, our method improves the Brier score of a retrieval-augmented GPT-5.1 forecaster by 9.3% while reducing measures of structural inconsistency by 82-90%. We interrogate our method via a comprehensive series of baselines and ablations, and find that no alternative method matches our gains in consistency and accuracy simultaneously.
40. Process Mining-Enabled Federated Anomaly Detection for the Industrial IoT
面向工业物联网的流程挖掘驱动联邦异常检测
AI 总结:针对工业物联网中联邦异常检测面临的非IID数据导致误报率升高的问题,提出流程挖掘方法动态加权本地模型,实验显示其F1分数和误报率表现优于基线方法。
链接:https://arxiv.org/abs/2611.17869
机构:DIETI University of Naples Federico II(那不勒斯费德里科二世大学 DIETI 学院); IMT School for Advanced Studies Lucca(卢卡高等研究院); DIMAI University of Florence(佛罗伦萨大学 DIMAI 学院); Interfaculty Initiative in Information Studies The University of Tokyo(东京大学信息学跨学科研究院)
作者:Francesco Vitale, Salvatore Bramante, Francesco Flammini, Hangli Ge
英文摘要:While federated anomaly detection enables the integration of local data insights across diverse nodes to reduce false positives, it inherently struggles with non-IID data. In practice, industrial IoT plants often operate under varying conditions and experience diverse environmental phenomena, resulting in significant heterogeneity in the monitored time series. In such settings, standard federated learning approaches fail to perform nuanced aggregation that accounts for these cross-node differences, ultimately leading to increased false positive rates. In this paper, we propose a process mining approach to evaluate the similarity of local node data against a reference provided by a global node. The global node utilizes these similarity metrics to dynamically weight local models during aggregation, producing personalized updates distributed across the network. We evaluate our approach using industrial IoT time-series data collected from manufacturing plants operating under distinct conditions. Experimental results demonstrate that our process mining-enabled federated anomaly detection pipeline achieves superior performance, yielding a 46.52% and 11.99% relative improvement in F1-score compared to isolated local training baselines and standard FedAvg, respectively, alongside a 51.24% relative reduction in false positives over standard federated aggregation.
41. When Copying Is Hard to Beat: A Negative Result in Clinical Assessment Forecasting
当复制难以击败:临床评估预测中的负面结果
AI 总结:该研究发现,在次日临床评估预测中,所评估模型未展现出优于强持续性基线的一致优势,凸显了文档流程等因素对评估预测结论的影响。
链接:https://arxiv.org/abs/2611.18142
机构:Heidelberg University(海德堡大学); Interdisciplinary Center for Scientific Computing (IWR)(跨学科科学计算中心(IWR)); University Medicine Mannheim, Heidelberg University(海德堡大学曼海姆医学院)
作者:Marius Fracarolli, Stefan Riezler
英文摘要:We report a negative result in next-day clinical assessment forecasting: the evaluated models show no consistent advantage over strong persistence-based baselines. Clinicians can view the previous day's questionnaire answers, a plausible source of documentation persistence. Predicting 45 items on 29,715 ICU day-pairs with patient-disjoint splits, a physiology-informed gated model improves item-macro-F1 over a one-line clinical rule by +0.0019 [+0.0006,+0.0031], while losing accuracy. No macro-F1 advantage is established when the physiology window ends at the previous form's reference time (+0.0001 [-0.0006,+0.0008]), or when scoring excludes the 68.5% of cells derived from parent answers; combining both changes yields a small disadvantage. Four checkpoints across three families underperform persistence, and a fine-tuned one differs from it on only two cells. A categorical read-out raises changed-cell accuracy eightfold, but a state-only read-out scores higher overall than forecast-only decoding and matches a transition matrix. This negative result highlights how the documentation process, input cutoff, observation mask and decoding rule shape conclusions about forecasting recorded assessments.
42. Which Model, For Which Variable? Per-Variable Forecast Combination in Sparse ICU Time Series
哪种模型对应哪个变量?稀疏ICU时间序列的逐变量预测组合
AI 总结:该研究针对稀疏ICU时间序列,提出逐变量预测组合方法,在5个ICU数据库上较最优单一模型降低均方误差,增益集中于稀疏数据区域,且模型排序随数据库规模变化。
链接:https://arxiv.org/abs/2611.18149
机构:Heidelberg University(海德堡大学); Helmholtz Information & Data Science School for Health, Karlsruhe/Heidelberg, Germany(亥姆霍兹健康信息与数据科学学院(卡尔斯鲁厄/海德堡,德国)); Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University(海德堡大学跨学科科学计算中心)
作者:Marius Fracarolli, Stefan Riezler
英文摘要: Clinical forecasting papers typically report a single best architecture. We show that on multivariate ICU physiology this question conceals variable-specific differences: no architecture is best on every variable, and which model wins changes from variable to variable. Across five ICU databases (MIMIC-III, MIMIC-IV, eICU, HiRID, and UMM (University Medicine Mannheim), a German single-center ICU) we forecast 94 channels over a 24-hour horizon with a pool of 14 models, and combine them with weights fitted per variable. On test, the combination beats the best single model on all five databases by 6.1-11.0% mean squared error (mean 8.7%). The gain is concentrated where clinical data is thinnest: the sparsest third of channels improves by 11.9% and laboratory values by 7.5%, against 3.1% for the densest third. Rank-based harmonic weighting of the best five models per variable, with no fitted weights at all, recovers about four-fifths of the gain. Extending the pool afterwards with a per-channel gradient-boosted tree, ARIMA and ETS makes the tree the validation-selected best single model on all five databases; per-variable combination still improves on it by 2.9-5.9% (significant on four of five), while equal weighting of the same members does not. As on univariate benchmarks, learned combination beats simple averaging - but only once the weights are constrained. We also report which model to prefer when, and show that the ordering changes with database size.
43. f-Divergence Self-Play for Tabular Anomaly Detection via Large Language Models
基于大语言模型的表格异常检测的f-散度自博弈方法
AI 总结:提出DiSPaT自博弈微调框架,基于f-散度最小化,通过交替优化生成伪异常并训练判别器,使模型分布对齐真实正常数据,在多基准上优于各类现有表格异常检测方法。
链接:https://arxiv.org/abs/2611.18370
机构:Hanoi University of Science and Technology(河内科技大学); Deakin University(迪肯大学); Monash University(莫纳什大学)
作者:Hoang Tran Vuong, Linh Ngo Van, Dang Nguyen, Thin Nguyen, Phuoc Nguyen, Mehrtash Harandi, Trung Le
英文摘要:Anomaly detection in tabular data poses significant challenges due to heterogeneous feature types-mixing numerical, categorical, and textual attributes, which complicate learning meaningful representations of normality. Recent work has applied large language models (LLMs) to this problem by serializing table rows as text sequences, yet these approaches rely on one-shot supervised fine-tuning that offers limited signal to tighten the model's description of normality. We propose DiSPaT, a self-play fine-tuning framework that strengthens the model's understanding of normal data. Building on the theoretical foundation of f-divergence minimization, we derive a tight approximation connecting our training objective to reducing the distributional gap between real normal data and model-generated samples. DiSPaT operates through an alternating optimization: at each iteration, the current policy generates synthetic samples that serve as pseudo-anomalies, while a critic discriminator learns to distinguish these from real normal samples; this signal drives policy updates that progressively align the model distribution with the true normal-data distribution. Extensive experiments on diverse benchmarks demonstrate that DiSPaT consistently outperforms prior LLM-based methods, deep learning approaches, and classical unsupervised detectors for tabular anomaly detection.
44. Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEs
Fuse-PINN:结合有限元方法与物理信息神经网络实现非线性偏微分方程的大规模并行模拟
AI 总结:本研究提出Fuse-PINN框架,结合有限元方法与物理信息神经网络,实现非线性偏微分方程在GPU高性能计算系统上的大规模并行模拟,在磁约束聚变相关模型上验证了近乎完美的扩展性。
链接:https://arxiv.org/abs/2611.18409
机构:UKAEA, CCFE, Culham Science Centre(英国原子能管理局,聚变能源中心,卡勒姆科学中心); IRMA, Univ. Strasbourg, France(法国斯特拉斯堡大学数学与计算机科学研究所); INRIA Nancy-Grand Est, Strasbourg, France(法国国家信息与自动化研究所南锡-大东部分部)
作者:Stanislas Pamela, Nicolas Pailliez, Emmanuel Franck, Victor Michel-Dansac, Laurent Navoret, Vignesh Gopakumar
英文摘要:Research in the domain of Physics-Informed Neural Networks applied to PDE modelling has advanced significantly in recent years, providing a wide ecosystem of novel methods. However, one frequent limitation is the inability of PINNs to scale out on High-Performance Computing architectures to address more ambitious challenges, particularly non-linear physics models with turbulent dynamics in large spatial domains. Typical studies restrain demonstrations to toy models with simple physics equations, few variables, and rarely any complex non-linear dynamics evolved over long timescales. Part of the AI community has even adopted the idea that "PINNs don't scale". This work proves otherwise. We present a mathematically robust formulation of Finite-Element-Method for Neural Networks (FEM-NN) implemented into a comprehensive, modular framework: Fuse-PINN. This formulation provides the basis for a sclable parallelisation of Physics-Informed Neural Networks on GPU-based HPC systems. Furthermore, an Energy Natural Gradient Descent optimiser is implemented to allow high-precision convergence. Fuse-PINN is demonstrated on physics models relevant to Magnetic Confinement Fusion, including non-linear convective models with fine-scale dynamics. Near-perfect scaling is achieved on multi-GPU runs with increasing problem size.
13. 其他/综合机器学习 | 34 篇
45. WETW: Learning Pair-Specific Weighted Euclidean Distances for Efficient DTW Search
WETW:学习针对特定对的加权欧氏距离以实现高效的DTW搜索
AI 总结:该研究针对DTW搜索速度慢的问题,提出WETW学习特定对的加权欧氏距离,结合WESEE编码器与过滤-验证流水线WETW-FV,在8个数据集上比最快精确方法快11.4倍,48K点序列上快40倍,召回率表现优异。
链接:https://arxiv.org/abs/2611.17412
机构:Université Paris Cité(巴黎城市大学); Harvard University(哈佛大学); FORTH-ICS(FORTH-ICS研究所)
作者:Christos Panourgias, Qitong Wang, George Tzagkarakis, Themis Palpanas
英文摘要: Dynamic Time Warping (DTW) is the standard distance for similarity search over time series that are misaligned in time, but its cost is quadratic in the series length and lower bounds often prune few candidates, so search over large collections of long series is slow. Learned approximations embed the series to make comparisons cheap, yet compare every pair with the same fixed rule, usually the Euclidean distance, although DTW aligns each pair differently. We observe that, once a pair is aligned, DTW is a Euclidean distance over coordinates selected for that pair. Building on this view, we propose Weighted Euclidean Time Warping (WETW), a learned distance that adapts the comparison of fixed-length embeddings to each pair. A small symmetric network predicts one weight per embedding di- mension and pair without computing an alignment, which halves the error of the best static distance on the same embeddings. The embeddings come from the Weighted Euclidean SEries Encoder (WESEE), whose multi-scale Temporal Feature Extractor keeps the timing information that global pooling removes and raises recall@1 from 0.90 to 0.95, although WETW works with any encoder. We also show that fitting DTW distances is not enough for search, as regression alone misorders the closest neighbours, and that ranking regularization raises recall@1 from 0.79 to 0.95. Our filter-and-verify pipeline, WETW-FV, uses WETW to build a shortlist and exact DTW to check it, so the search is approximate but every returned distance is exact. Over eight datasets, WETW-FV is 11.4x faster than the fastest exact method among the UCR Suite, lower bounds and MESSI-DTW, at a mean recall@10 of 0.93, while the best learned baseline reaches 0.59 at the same speed. On 48K-point series, WETW- FV remains 40x faster than the UCR Suite at a recall@10 of 0.91.
46. Diffusion Tree Sampling for Inference Time Adaptation of Crystal Generative Models
用于晶体生成模型推理时自适应的扩散树采样
AI 总结:该研究提出扩散树采样(DTS)方法,在不修改晶体生成模型的前提下,通过蒙特卡洛树搜索实现推理时自适应,可提升晶体稳定性、生成稀有空间群晶体及多目标帕累托前沿样本。
链接:https://arxiv.org/abs/2611.17462
机构:McGill University(麦吉尔大学); Mila - Quebec Artificial Intelligence Institute(米拉 - 魁北克人工智能研究所)
作者:Daniel T. Levy, Vineet Jain, Tara Akhound-Sadegh, Sékou-Oumar Kaba, Siamak Ravanbakhsh
英文摘要:Diffusion-based generative models have become strong priors over plausible crystal structures, but turning that prior into promising candidates requires steering toward several conflicting properties at once. Fine-tuning is expensive and produces a new model for every new objective, while differentiable guidance is not applicable to many real-world tasks. We instead adapt these generative models at inference time using Diffusion Tree Sampling (DTS), a Monte Carlo tree search procedure over the denoising trajectory. We make two technical contributions on top of DTS that are particularly relevant for AI-for-science applications. First, we show how to use existing property-conditional generative models (e.g., models fine-tuned for classifier-free guidance) as guided proposals inside DTS, without distorting the target distribution. Second, we extend DTS to multi-objective sampling, so that a single search produces samples spanning an entire Pareto front. We instantiate both adaptations on de novo crystal generation: improving the stability of crystals generated by different models, using pretrained conditional models to generate crystals belonging to rare space groups or with high bulk modulus, and generating crystals along a Pareto front of high dielectric constant and high bandgap materials. Across these tasks, DTS-based inference-time adaptation successfully improves model outputs without modifying the models themselves.
47. Availability-Aware Historical Feedback Learning for Electric Arc Furnace Temperature and Chemical Composition Prediction
面向电弧炉温度与化学成分预测的可用性感知历史反馈学习
AI 总结:本研究提出可用性感知历史反馈学习框架,结合工业数据特征,经时间验证评估算法,可降低电弧炉终点温度与化学成分预测的均方根误差,证实历史结果可用性的重要性。
链接:https://arxiv.org/abs/2611.17463
机构:West Virginia University(西弗吉尼亚大学)
作者:Ahmed Shoyeb Raihan, Farzana Islam, Ashish Nimbarte, Imtiaz Ahmed
英文摘要:Electric arc furnace (EAF) steelmaking plays an increasingly important role in recycled and lower-carbon steel production. However, variability in charged materials, energy input, and operating conditions makes accurate prediction of molten steel temperature and final chemical composition challenging. Intermittent or delayed measurements limit the information available for timely prediction. This study develops an availability-aware historical-feedback learning framework for predicting EAF endpoint temperature and the final concentrations of twelve chemical elements. Eight industrial data sources are integrated into three progressively enriched predictor representations comprising 19 static, 39 temporal, and 47 history-informed features. Historical outcomes are incorporated only when eligible under an assumed 60-minute measurement-release delay. Using 19,738 temperature heats and 3,341 chemistry heats, twelve tuned regression algorithms are evaluated through chronological forward validation. The proposed historical-feedback representation reduces root mean squared error (RMSE) in 147 of 156 matched algorithm-target comparisons. For temperature prediction, ExtraTrees achieves an RMSE of 12.290 degrees C, representing a 5.54 percent reduction compared with its temporal-only counterpart. Historical-feature ablation and feedback-delay sensitivity analyses demonstrate the importance of recent outcome information and its availability. In a separate retrospective later-period evaluation, lightweight adaptive residual correction reduces temperature RMSE from 12.502 to 12.275 degrees C without retraining the underlying model. Exploratory deep learning comparisons and target-specific feature-attribution analyses provide additional insights into predictive behavior. The results establish historical outcome availability and sequential feedback as important considerations for EAF endpoint prediction.
48. SURFACE: Preference Distribution Matching on Pareto Fronts via Scalarization Steering
SURFACE:通过标量化引导的帕累托前沿偏好分布匹配
AI 总结:SURFACE通过自适应更新标量化权重匹配帕累托前沿的期望偏好分布,实现了偏好分布不匹配的线性收敛,在多基准测试中较基线提升了目标质量平衡与前沿覆盖度。
链接:https://arxiv.org/abs/2611.17484
机构:University of Rochester(罗切斯特大学); IBM Research(IBM研究院)
作者:Liuyuan Jiang, Prasanna Sattigeri, Lisha Chen
英文摘要:Constructing a finite Pareto representation requires allocating a limited number of solutions across the Pareto front (PF). A desired preference distribution specifies this allocation by assigning more solutions to some PF regions and fewer to others. Scalarization generates Pareto solutions by varying objective weights and solving single-objective problems. However, a distribution of scalarization weights generally does not translate into the same distribution of Pareto solutions along the PF, because the weight-to-solution map is nonlinear and unknown in this http URL account for this distortion, we introduce SURFACE (Scalarization Updates for Redistributing Finite Approximations with Chart Estimation}), which adaptively updates scalarization weights to match a desired PF distribution. SURFACE estimates how each region of the weight grid corresponds to an area of the PF from the current scalarized solutions, then redistributes the weights accordingly. The method supports parallel, warm-started, inexact optimization with standard single-objective solvers. Theoretically, we establish that, under the stated regularity conditions, SURFACE achieves linear convergence of the preference distribution mismatch to a finite-resolution error floor of $\mathcal{O}(N^{-2/(M-1)})$, where $N$ is the number of adaptive weights and $M$ is the number of objectives. Empirically, experiments across multiple benchmarks demonstrate improved target-mass balance and PF coverage compared with established baselines.
49. PF-Exec: Large-Scale UAV Relay Load Balancing with an Anchored Potential Direction Decider and a Per-Dimension Gain-Learning Executor
PF-Exec:基于锚定势方向决策器与逐维度增益学习执行器的大规模无人机中继负载均衡
AI 总结:该研究针对大规模无人机中继负载均衡问题,提出PF-Exec双层架构,含锚定势方向决策器与逐维度增益学习执行器,经多场景评估,其公平性、负载性能及鲁棒性优于多数对比方法。
链接:https://arxiv.org/abs/2611.17492
机构:University of Sussex(萨塞克斯大学); Shanghai Shuyuan Information Technology Co., Ltd.(上海书院信息技术有限公司); Zhejiang Gongshang University(浙江工商大学)
作者:Liheng Zeng, Hanzhang Jia, Yiran Li, Yi Gao, Bo Ma
英文摘要:Relay load balancing in large-scale UAV networks requires joint decisions on association, bandwidth, power and hovering position, while the dimension grows with the number of UAVs and each UAV sees only its local state. This paper splits the decision into two layers. An anchored potential direction decider emits a closed-form target at every instant and returns its direction only. A gain-learning executor maps a local observation into a positive gain per dimension, composes gain and target, and clips the action against the physical single-step bound; the two layers form PF-Exec. The unit gain is the default start, so the executor reduces to the pure potential policy before training. The load is first-order homogeneous in bandwidth, making the bandwidth target closed form, and the position target is the demand-weighted centroid of the served users. The system uses a two-hop access and millimetre-wave backhaul link with soft association, a 3GPP UMa-AV channel with two shadowing layers, an OU-type social-force crowd and a quadrotor physical layer. Evaluation spans all fleet sizes, two crowd scenarios, independent seeds, the published baselines in their own settings and a degraded-information line. In the highest-pressure burst setting the fixed-step comparison breaks down on part of the seeds, losing fairness and mean load at once, while PF-Exec holds fairness near one. Among the ten comparison methods only the greedy heuristic survives that setting; its load variance stays far higher. Under stale global state and position noise the fairness index stays high at both largest-scale scenarios. Flight energy is nearly identical between the learned and the fixed-step executor, and three constants are fixed once across all settings. The convergence properties of both layers, from the truncated gain iteration to the perturbed tracking bound, are proved in the companion analysis.
50. Beyond a Single Sign: BiTE for Branch-Preserving Binary Threshold Expansion
超越单一符号:用于分支保留的二值阈值扩展的BiTE
AI 总结:针对二值神经网络单一符号激活表示能力不足的问题,提出BiTE方法,通过保留多阈值的二值响应提升表示能力,在BinaryViT等模型上实现了准确率提升且参数规模优势明显。
链接:https://arxiv.org/abs/2611.17576
机构:Ruhr University Bochum(鲁尔大学波鸿分校)
作者:Siddharth Gupta, Mikail Yayla, Akash Kumar
英文摘要:Binary neural networks (BNNs) reduce model storage and replace many arithmetic operations with efficient bitwise computations, but the single-sign activation limits their representational capacity. Each preactivation direction is compared with one threshold and reduced to one of two values, discarding variation within each sign region. We propose \textbf{BiTE} (Branch-Preserving Binary Threshold Expansion), which evaluates each feature direction against $K$ ordered thresholds and retains the resulting binary responses as separate inputs to the following learned operator. BiTE can distinguish up to $K+1$ ordered activation states while allowing the following operator to learn a separate transformation for each threshold response. It also enables a controllable trade-off between the number of independently constructed feature directions and the number of ordered responses extracted from each direction. On BinaryViT, BiTE improves mean final-epoch Top-1 accuracy from $74.60\pm0.30\%$ to $75.83\pm0.15\%$ on CIFAR-10 and from $42.80\pm0.46\%$ to $44.07\pm0.32\%$ on CIFAR-100, with nearly unchanged trainable parameter counts. A matched uniform-collapse control reaches $75.33\pm0.15\%$ on CIFAR-10, supporting the value of retaining the threshold responses separately relative to the evaluated scalar collapse. Binary VGG-16 experiments further show a favorable observed parameter--accuracy trade-off, including a configuration that achieves $0.64$ percentage points higher mean accuracy with $21.8\%$ fewer parameters than conventional width scaling. Overall, these results support branch-preserving threshold expansion as an effective way to improve binary representations and the observed parameter--accuracy trade-off.
51. Fair and Efficient Distributed EV Charging Coordination Using Threshold Cryptography and Machine Learning
基于门限密码学与机器学习的公平高效分布式电动汽车充电协调
AI 总结:该研究针对分布式EV充电协调中的拜占庭攻击问题,提出结合门限密码学与机器学习的防御框架,可高效检测攻击并维持优化收敛,大幅降低攻击带来的成本与负载影响。
链接:https://arxiv.org/abs/2611.17577
机构:Texas A&M University(德克萨斯农工大学); Tennessee Tech University(田纳西理工大学); Hamad Bin Khalifa University(哈马德本哈利法大学); FAMU-FSU College of Engineering(佛罗里达农工大学-佛罗里达州立大学工程学院)
作者:Md. Mainul Islam, Muhammad Ismail, Hasan Kurban, Abdulrahman Takiddin, Erchin Serpedin
英文摘要:Distributed coordination of electric vehicle (EV) charging with the alternating direction method of multipliers (ADMM) keeps EV constraints private but assumes that every participant follows the algorithm. This assumption fails in practice, where a biased operator or a man-in-the-middle (MITM) attacker can send inconsistent signals to different EVs, and compromised EVs can deviate from their prescribed updates. We first prove that attacks by such arbitrarily malicious, i.e., Byzantine, participants do not prevent convergence and therefore remain undetected, and derive the most damaging attack in closed form. We then propose a framework that combines a threshold-signed broadcast with upload recomputation, which detects every deviation without false alarms at linear instead of quadratic communication cost. To keep the optimization running, each affected EV recovers locally with a certified, fleet-aware machine learning price forecast, and we prove that the optimization remains convergent with a recovery cost bounded by the shape of the forecast error. Simulation results with real-world load, price, and charging data show that a biased operator raises the annual cost of disadvantaged EVs by 132.7% and lowers that of advantaged EVs by 49.3% without changing the aggregate load, whereas the defense limits all cost changes to 2.6%. An external MITM attacker raises the cost of its victims by 57.6%, the peak load by 5.8%, and the grid cost by 15.8%, whereas the defense keeps them within 1.1%, 0.2%, and 0.3% of benign operation. With up to 70% of the EVs attacked, the recovery converges in at least 97.8% of the runs.
52. Neural Simulation-Based Inference for Computational Cognitive Models: A Tutorial
面向计算认知模型的基于神经模拟的推理:教程
AI 总结:本教程针对认知建模中似然计算不可行的问题,介绍基于神经网络的模拟推理(neural SBI)的工作流程与实践建议,助力认知科学家突破技术限制、拓展理论研究范围。
链接:https://arxiv.org/abs/2611.17608
机构:University of California, Berkeley(加州大学伯克利分校); Helen Wills Neuroscience Institute, University of California, Berkeley(加州大学伯克利分校海伦·威尔斯神经科学研究所)
作者:Ti-Fen Pan, Yi Cheng, Anne GE Collins
英文摘要:Computational cognitive modeling is an increasingly essential methodology to elucidate the mechanisms underlying human and animal cognition. By fitting models to empirical data, researchers can perform parameter estimation, model comparison, and model-based neural analyses to assess competing theories, quantify individual differences, and investigate neural representations. Typically, fitting these models relies on likelihood-dependent methods (e.g., Maximum likelihood estimation or hierarchical Bayesian methods). However, for many reasonable cognitive models, computing the likelihood is computationally intractable, in which case these methods become inadequate. This substantially limits the range of theories that researchers can investigate. Simulation-based inference with neural networks (neural SBI) has emerged as a powerful toolkit to overcome this hurdle. By training deep neural networks on datasets generated through model simulations, neural SBI learns the relation between observable data and cognitive models. This approach enables all the applications of standard modeling while bypassing the likelihood computation, without constraints on empirical data size. Despite its successful adoption across diverse scientific fields, neural SBI remains underutilized in cognitive modeling, partly due to a lack of accessible, domain-tailored guidance. This tutorial addresses this gap by providing a clear workflow for applying neural SBI to cognitive models. We also provide practical use cases and recommendations for reducing the computational and simulation burden, facilitating efficient implementation in real-world research settings. By lowering the technical barriers to neural SBI, this tutorial aims to empower cognitive scientists to investigate richer theory spaces and ultimately propel scientific discovery.
53. A mesh-free deep energy method for phase-field modeling of thermally driven brittle fracture
用于热驱动脆性断裂相场建模的无网格深度能量方法
AI 总结:该研究提出一种基于多分辨率神经表示的无网格深度能量方法,用于热驱动脆性断裂相场建模,可预测裂纹形核、扩展等,结果优于有限元计算,无需预先设置裂纹相关要素。
链接:https://arxiv.org/abs/2611.17630
机构:University of New South Wales(新南威尔士大学); Central Queensland University(中央昆士兰大学); Bauhaus-Universität Weimar(魏玛包豪斯大学)
作者:Han Zhang, Mehrisadat Makki Alamdari, Babak Shahbodagh, Mohammad Vahab, Cosmin Anitescu, Timon Rabczuk, Elena Atroshchenko
英文摘要:Phase-field simulation of thermally driven fracture requires resolving localized crack bands whose paths are unknown in advance and thermal boundary layers whose thickness evolves during the transient. Neural energy-based computations of thermal fracture have so far started from defects placed in advance. This paper proposes a mesh-free deep energy method based on multiresolution neural representations that predicts spontaneous crack nucleation, crack spacing, and selective crack propagation and arrest under transient thermal loading. Two networks, each with its own multiresolution encoding, represent the displacement and phase fields and the transient temperature, and the mechanical energy and the incremental functional of the backward Euler heat equation are estimated on integration points redrawn at every iteration. Restricting irreversibility to the crack set, carrying the optimizer state across load steps and decaying the learning rates within each step help prevent spurious damage accumulation. On two notched plates the initiation peak loads agree closely with an independent finite element reference. On a quenched glass strip under an analytical temperature field the crack path changes from straight to oscillatory and then to branched, with an oscillation threshold close to the linear stability prediction. Under a prescribed boundary temperature a quenched ceramic slab forms a crack array of the type observed in experiment, with a spacing close to that of a published benchmark. On the slab and a quenched annulus the arrays are denser than those of a finite element computation on the same material field. No crack paths, nucleation sites or crack-adapted meshes are prescribed.
54. Pattern-Based Matrix Analysis Under Permutations
排列下基于模式的矩阵分析
AI 总结:本文针对仅经行列排列后才具结构简洁性的矩阵,引入模式距离与模式加低秩分解,推导交替算法,在合成与真实矩阵任务上验证了通用算法可恢复不同矩阵结构的优势。
链接:https://arxiv.org/abs/2611.17674
作者:Andrei Ermakov
英文摘要:Low-rank approximation captures one important notion of matrix simplicity: a matrix is simple if it is well described by a low-dimensional linear model. This paper studies a complementary notion. We consider matrices that become structurally simple only after permuting rows and columns, so that their mass concentrates in a prescribed geometric pattern such as a band, block-diagonal, arrowhead, or related form. We introduce a pattern distance that measures how close a matrix is to a given pattern after optimal reordering, giving a common framework for structural problems such as latent ordering, community detection, and bandwidth minimization. The problem is NP-hard in general; we derive an alternating algorithm based on Linear Assignment subproblems. We further introduce a pattern-plus-low-rank decomposition that combines permutation-structured fitting with a low-rank residual, whose permutation step is pattern fitting on the residual; its gains across pattern families persist at a matched parameter budget and are substantially reduced under a density-matched random-mask control. We evaluate the framework on synthetic recovery tasks, real correlation and graph adjacency matrices, and transformer attention heads, showing that a single universal algorithm recovers qualitatively different forms of matrix structure.
55. Electrocardiographic Imaging via Posterior Sampling under Operator Discrepancy
算子差异下的后验采样心电图成像
AI 总结:针对心电图成像中前向算子存在结构性差异的问题,提出OpDis-PS扩散后验采样器,建模信号依赖的算子差异并修正前向算子,在两种差异场景下的重建精度优于经典方法和学习型预测器。
链接:https://arxiv.org/abs/2611.17851
机构:Center for Artificial Intelligence and Robotics(人工智能与机器人中心); Technical University of Applied Sciences(应用技术大学); Würzburg-Schweinfurt(维尔茨堡-施韦因富特)
作者:Ricarda Buttmann, Andreas M. Lehrmann
英文摘要: Electrocardiographic imaging (ECGI) reconstructs heart-surface potentials from body-surface potentials, an ill-posed inverse problem. Diffusion posterior samplers combine a learned prior with an explicit forward operator that they assume to be accurate. In ECGI this operator is only an estimate, because the body changes with respiration and posture, and body composition such as subcutaneous fat is rarely known for an individual patient. The resulting operator discrepancy is structured and depends on the heart signal. We introduce OpDis-PS, a diffusion posterior sampler that models this discrepancy instead of treating it as signal-independent noise. OpDis-PS learns how the discrepancy depends on the signal, folds this into a corrected forward operator, and reconstructs with a fixed prior across all operator conditions. We study two realistic sources of discrepancy, changing lung conductivity and an added subcutaneous-fat layer. Across both, OpDis-PS reconstructs more accurately than classical regularization and learned predictors, with its largest gains on held-out cardiac pathologies.
56. Disentangling Forgetting from Utility: Lightweight LLM Unlearning via Orthogonal Null-Space Projection
分离遗忘与效用:基于正交零空间投影的轻量级大语言模型遗忘技术
AI 总结:该研究提出UUE框架,通过正交零空间投影实现轻量级LLM遗忘,在TOFU和WMDP基准上效果优于现有方法,兼顾遗忘效率与模型通用效用。
链接:https://arxiv.org/abs/2611.17864
机构:Zhejiang University(浙江大学); University of Illinois Chicago(伊利诺伊大学芝加哥分校); Zhejiang Tailong Commercial Bank(浙江泰隆商业银行)
作者:Xiuyuan Wang, Weiming Liu, Zongxin Yang, Fan Wang, Liemiao Jin, Rubin Qin, Wei Chen, Bin Shi, Chaochao Chen, Xiaolin Zheng
英文摘要:Large Language Models (LLMs) pose significant security risks by retaining private or hazardous information, creating an urgent need for unlearning techniques that excise specific knowledge without compromising general utility. However, prevailing fine-tuning-based unlearning methods struggle to achieve this balance, often suffering from computational inefficiency and unintended utility degradation due to the entangled nature of knowledge within model parameters. To disentangle forgetting from utility, we propose UUE, a theoretically grounded framework that reformulates unlearning as controllable model editing. First, UUE projects parameter updates into the orthogonal left null space of retained knowledge representations, strictly ensuring that the editing process causes minimal interference to the model's general capabilities. Second, distinct from targeted mapping, we introduce a convex untargeted objective that derives a closed-form analytical solution to effectively disrupt undesired knowledge by pushing forget-set embeddings toward their antipodal points. We implement UUE via lightweight, pluggable adapters (including a low-rank variant, UUE-L), enabling efficient deployment without modifying the frozen backbone. Extensive experiments on TOFU and WMDP benchmarks demonstrate that UUE and UUE-L achieve superior unlearning efficacy, significantly outperforming existing methods.
57. Protection-Oriented Assessment of Machine Learning-Based Fault Detection in Power Systems
面向保护的电力系统中基于机器学习的故障检测评估
AI 总结:该研究针对电力系统保护场景,在PROTECT-90数据集上评估三种ML故障检测器与序电流参考,发现其AUC-ROC超0.999但拒动率存在差异,明确了故障电阻等关联因素。
链接:https://arxiv.org/abs/2611.17872
机构:Friedrich-Alexander-Universität Erlangen-Nürnberg(埃尔兰根-纽伦堡弗里德里希-亚历山大大学); Ostbayerische Technische Hochschule Amberg-Weiden(东巴伐利亚应用科学大学安贝格-魏登校区)
作者:Julian Oelhaf, Georg Kordowich, Changhun Kim, Christian Bergler, Andreas Maier, Johann Jäger, Siming Bayer
英文摘要:Machine learning (ML)-based fault detectors are increasingly proposed for power system protection, yet aggregate metrics can obscure the consequences of false and missed trips. We present a protection-oriented assessment of three ML detectors and a sequence-current reference on PROTECT-90, comprising 9,022 simulated fault episodes on a 90 kV double-circuit line. The assessment combines five window conditions, causal window-end labelling, episode-grouped cross-validation, and operating-point selection under a fixed security budget. It reports security, dependability, detection timing, decision margins, and episode-level nuisance assertions. Gradient-boosted trees, a convolutional neural network, and logistic regression achieve AUC-ROC values above 0.999, yet at a security budget of $10^{-3}$ their developed-fault missed-trip rates range from 0.007% to 1.99%. Post-clearing false-trip rates of approximately 0.12-0.16% per window coexist with nuisance assertions in 11.3-19.1% of episodes. Among the analysed physical descriptors, missed trips are most consistently associated with higher fault resistance within the sampled range. An analytical current proxy suggests a fault-current gradient only partly reproduced by waveform-derived current (rank correlation 0.62). No single topology state or faulted phase consistently dominates within the sampled domain. Because PROTECT-90 contains fault episodes only, security is assessed on pre-fault and post-clearing windows rather than independent non-fault disturbances.
58. Delayed Effects of Temporary Weight Decay in Muon Pretraining
μ子预训练中临时权重衰减的延迟效应
AI 总结:该研究针对Muon预训练的仅解码器Transformer,发现临时权重衰减会产生延迟效应,需在最终训练预算下评估,其特定调度方案在跨参数规模迁移时表现出复杂的性能变化。
链接:https://arxiv.org/abs/2611.17876
机构:Meta; Mila-Quebec AI Institute(米拉-魁北克人工智能研究所); Université de Montréal(蒙特利尔大学); Samsung SAIL Montreal(三星北美研发中心蒙特利尔人工智能实验室)
作者:Md Rifat Arefin, Ravid Shwartz-Ziv, Ernie Chang, Chinnadhurai Sankar, Rylan Conway, Aristide Baratin, Irina Rish, Adithya Sagar, Patrick Huber
英文摘要:A temporary optimization intervention can increase validation loss when it ends yet reduce it at the final training budget. We demonstrate this with temporary weight decay in Muon-trained decoder-only Transformers with 162M, 405M, 1.4B, and 3.4B parameters. For models up to 1.4B parameters, moving a fixed-duration decay window from early to late training reverses its final effect. At 162M, changing window duration alters final loss even at approximately matched total shrinkage. Most strikingly, a schedule selected at 162M and transferred without retuning to 1.4B is 0.26 nats worse than no decay when removed, overtakes it only after 73% of training, and ultimately finishes 0.028 nats better while also outperforming the best sampled constant-decay baseline. Early decay leaves a persistent weight-norm deficit, which keeps relative steps larger after the intervention ends. An approximate norm-dynamics recurrence captures the slow convergence of these relative steps, and fixed-norm replays of the measured trajectories reproduce the performance ordering and a similar loss difference. At 162M and 405M, norm-reset experiments show that smaller weight norms at the end of the decay window explain most of the final loss improvement. A separate Gram intervention exhibits related post-removal norm and relative-step dynamics. These results show that temporary optimization schedules can have delayed effects long after removal and should therefore be evaluated at the intended final training budget, not only at removal.
59. Reasoning Models Confabulate to Defend Injected Beliefs About Their Own Requests
推理模型会编造理由为自身被注入的关于请求的信念辩护
AI 总结:该研究发现,激活编辑可覆盖推理模型对自身请求的信念,使其编造理由为被注入的错误主题辩护,破坏了思维链监控的有效性。
链接:https://arxiv.org/abs/2611.17958
作者:Yang Ou
英文摘要:Chain-of-thought (CoT) monitoring and self-report are proposed as levers for AI oversight, on the assumption that a model's account of what it is doing is anchored to what it was asked. We show this anchor can be cut. An activation edit invisible in the prompt text, the injected forming-trace of an off-topic concept, overwrites a reasoning model's belief about its own request: across six models spanning scale, architecture, and recipe, the injected topic becomes the task it reasons about, reports back, and answers: the forced quote-back returns the injected topic in 47 of 48 model-concept cells, and on the four models with clean final haiku the injected answer follows in 99% of generations. Warnings barely move it: even one naming the true topic yields under 5% true-topic answers. Handed the truth in clean tokens, the model confabulates a story about the user ("maybe they got confused and corrected themselves") and answers with the injection anyway, its behavior and chain-of-thought corrupted together: a concrete limit on CoT monitorability. Opening the model up offers no reprieve: it attends to the true request even harder after edits, yet that attention is causally inert, and the injected content rides intact task circuits, so attention maps and circuit attributions read as on-task too; the same edit redirects the request's language and format, not only its topic. What the injection reaches is the model's reference to its own input; what it elicits is its defense of it.
60. When Does Oversampling Help? A Decision Framework for Imbalanced Data Streams Under Label Delay and Concept Drift
过采样何时有用?标签延迟与概念漂移下不平衡数据流的决策框架
AI 总结:该研究针对带标签延迟与概念漂移的不平衡数据流,构建决策框架判断过采样是否优于重新评估,经实验发现过采样仅在少数真实场景有边际贡献,方法选择需随数据流特征动态调整。
链接:https://arxiv.org/abs/2611.17981
机构:The British University in Dubai(迪拜英国大学); Cairo University(开罗大学)
作者:Ahmed Awad, Anirudh Sengar
英文摘要:For imbalanced data streams with delayed labels, is it worth adding a streaming oversampler, or does continuous re-evaluation of earlier predictions already recover the cost of the delay? We address this through an extensive experimental comparison of streaming oversampling and continuous re-evaluation under joint class imbalance, concept drift, and label delay. Streaming oversamplers are typically evaluated under the test-then-train assumption of immediate labels; their behaviour under these conditions, assessed through re-evaluation, has not been systematically studied. We close this gap with a decision framework that predicts when oversampling adds value over re-evaluation, organised around three axes: drift density, minority-class learnability, and delay relative to the refinement window, and operationalised as a competition between a recovery channel (re-evaluation) and a minority-coverage channel (oversampling). Evaluating $15$ classifiers on $6$ synthetic and $6$ real streams, we find: re-evaluation recovers delay-induced loss on drift-active streams but is silent on stationary ones; oversampling's marginal contribution over re-evaluation is statistically detectable in only one real-data configuration; and cost--performance Pareto recommendations from synthetic streams do not transfer to real data, where fronts partition by drift regime. Method selection should therefore be conditioned on the stream's profile and re-estimated as it evolves, not inherited from synthetic benchmarks.
61. RiverScan: Learning to Accumulate on River Networks
RiverScan:面向河流网络的累积学习
AI 总结:本研究针对大型流域径流预测问题,提出基于面积加权选择性状态空间递归的RiverScan空间算子,在多瑙河流域608个站点的实验中,其预测性能优于多种基线模型,为水文建模提供了有效归纳偏置。
链接:https://arxiv.org/abs/2611.18005
机构:Central China Institute of Artificial Intelligence(华中人工智能研究院); University of Waterloo(滑铁卢大学)
作者:He Zhu, Zhiyi Gao, Youhuan Yang, Han Quan, Ming Li
英文摘要:Accurate runoff prediction across large river basins requires models to capture heterogeneous local hydrological responses and their accumulation downstream. River-network connectivity provides a natural structure for this task, but using it effectively requires learning how to combine contributions from subcatchments of different sizes. We frame this challenge as learning to accumulate and introduce RiverScan, a spatial operator based on area-weighted selective state-space recurrence. RiverScan recursively combines local temporal representations with accumulated upstream states in topological order. Contributing-area fractions account for subcatchment size, while learned retention controls how upstream information persists downstream. Experiments on 608 stations in the Danube basin show that RiverScan outperforms the evaluated temporal and graph baselines in overall predictive performance. Structural controls and ablations demonstrate that composing heterogeneous subcatchment representations in a manner aligned with hydrological accumulation substantially improves runoff prediction, with the benefits of correct topology growing along the river-network hierarchy. These findings establish physically structured accumulation as an effective inductive bias for hydrological modeling and motivate finer-grained, fully distributed AI-based hydrological models.
62. Sample-Efficient Control of Magnetoconvective Flows via Differentiable Simulation
基于可微模拟的磁对流样本高效控制
AI 总结:本研究针对磁流体动力学(MHD)流动控制的未探索问题,提出新型可微GPU加速MHD求解器φ-PICT,集成至FluidGym后可提升传热超25%、逆设计精度达黑箱方法的10³倍,且公开可用。
链接:https://arxiv.org/abs/2611.18008
机构:TU Dortmund University(多特蒙德工业大学); Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔机器学习与人工智能研究所); TU Ilmenau(伊尔默瑙工业大学); TU Munich(慕尼黑工业大学); Munich Center for Machine Learning(慕尼黑机器学习中心); Paderborn University(帕德博恩大学)
作者:Jannis Becktepe, Dmitry Krasnov, Nils Thuerey, Jörg Schumacher, Sebastian Peitz
英文摘要: Magnetohydrodynamic (MHD) fluid flows are central to demanding engineering applications, most prominently fusion blanket cooling, where flow control is a promising tool to optimize key properties such as heat transfer. While active flow control (AFC) has recently advanced through machine learning, its application to MHD flows remains largely unexplored. In this work, we present $\phi$-PICT, a novel differentiable GPU-accelerated MHD solver targeted at AFC. We validate $\phi$-PICT against MHD benchmarks and demonstrate its high computational efficiency. Integrated into FluidGym, $\phi$-PICT enables sample-efficient gradient-based algorithms to improve heat transfer by $>25$% and allows optimizers to achieve $10^3\times$ higher accuracy in inverse design than black-box methods. $\phi$-PICT is publicly available at this https URL.
63. Conflict, Feasibility, Faithfulness, Displacement: Four Quantities That Come Apart in Federated Dual-Cone Aggregation
冲突、可行性、忠实性、位移:联邦双锥聚合中分离的四个量
AI 总结:该研究针对联邦双锥聚合,发现FedFV等多目标梯度聚合器视为一体的冲突、可行性等四个量发生分离,提出的UPGrad在CIFAR-10等数据集上的增益受参与度、数据划分等因素影响,明确了联邦学习评估应报告的内容。
链接:https://arxiv.org/abs/2611.18014
机构:Warsaw University of Technology(华沙理工大学); Warsaw University of Life Sciences(华沙生命科学大学); Cardinal Stefan Wyszyński University(枢机主教斯特凡·维申斯基大学)
作者:Grzegorz Gwardys, Karol Wojciechowski, Mateusz Gwardys, Bartosz {Ś}widerski
英文摘要:FedFV, FedGH and FedMGDA+ aggregate client updates with multi-objective gradient aggregators to remove conflict between them. We examine this rationale with UPGrad, which increases no client's loss to first order, in a comparison that changes only the direction of FedAvg's update. Four quantities the rationale treats as one -- conflict between client updates, feasibility of their weighted mean, faithfulness of the transmitted updates to the clients' gradients, and displacement of the update -- come apart. Under Dirichlet partitioning UPGrad improves CIFAR-10 accuracy by +0.78 pp (14/15 seeds, p < 0.001), only with full participation; on Oxford-IIIT Pet its +0.52 pp gain vanishes (+0.07 pp) once the data our protocol left unused are kept. Varying only the Dirichlet concentration, the gain grows with heterogeneity, yet the split with the most conflict shows none. Uniform client weights, blind to conflict, match the CIFAR-10 gain and exceed the Pets gain; a matched random rotation does neither. No fairness effect survives multiplicity correction, and on CIFAR-10 the guarantee does not reach the clients' gradients. We state what evaluations should report.
64. Deep Latents, Long Memory: Latent persistence explains temporal correlations in transformer activations
深度潜变量与长记忆:潜变量持续性解释Transformer激活中的时间相关性
AI 总结:本研究针对LLM隐藏层抽象程度难以定量验证的问题,提出以潜变量持续性解释Transformer激活的时间相关性,通过合成与真实文本实验验证了深层潜特征持续性更强的结论。
链接:https://arxiv.org/abs/2611.18089
机构:Simplex(辛普莱克斯); SISSA(国际高等研究学院)
作者:Francesco Cagnetta, Santiago Acevedo
英文摘要:The hidden layers of Large Language Models (LLMs) are believed to encode representations of the data whose abstraction increases with depth. However, in the absence of an operational notion of abstraction, this statement is hard to test quantitatively. Here, we propose an alternative view, building on the principle that the correlations of a sequence reflect the structure of the process that generated it. We define the autocorrelation function of a layer as the average dot product between its activations at two context positions separated by a lag. Latent variables encoded persistently along the context create slowly decaying tails in the autocorrelation, and we find these tails to grow across layers in both synthetic and natural data. In synthetic data with controlled hierarchical latent structure, this growth stems from the encoding of abstract latent variables, which govern long stretches of the input. Indeed, the persistence of latent codes predicts the qualitative structure of autocorrelations and accounts for most of the empirical measures. In real text, we take sparse-autoencoder features as proxies for latent variables, and find that their persistence correlates strongly with the magnitude of autocorrelations across datasets and LLMs. In particular, the persistence time increases with depth, as do autocorrelations, implying that deeper latent features persist for longer context spans. We complement this analysis by explicitly ablating the persistent sparse-autoencoder features and observing a consequent decrease in the autocorrelations.
65. Efficient Poincaré Convolutions through Patch-Statistics Factorization
基于Patch-Statistics分解的高效庞加莱卷积
AI 总结:该研究提出通过Patch-Statistics分解实现高效庞加莱卷积,无需将图像块映射到庞加莱球,可提升训练速度、降低内存,且不影响模型性能。
链接:https://arxiv.org/abs/2611.18125
机构:Department of Computer Science(计算机科学系)
作者:Lukáš Jochymek, Markéta Vašinková, Petr Gajdoš
英文摘要:Published implementations of the Poincaré convolution in Hyperbolic Neural Networks++ (HNN++) map every overlapping image patch to the Poincaré ball before evaluating its score. We show that the clipped score depends on each patch only through two statistics, its squared norm and its inner products with the filters, which a native convolution and a single-channel box filter compute directly. The factorized layer therefore evaluates the specified score exactly, without constructing ball-valued patches, and its single-precision outputs and gradients agree with double-precision evaluations at least as closely as those of the explicit reference. On an RTX A6000 under two versions of JAX, complete training updates of a Poincaré U-Net and a Poincaré ResNet-20 are 1.5 to 1.8 times faster than the faster of two explicit implementations that map patches to the ball (1.2 to 1.4 times against an explicit implementation that skips this mapping); on a V100, the gain over the gather-based one persists as the ResNet-20 is widened eightfold. In 15 paired training runs per task, updates are 2.0 and 1.8 times faster than a reference that follows the published execution order, with no consistent change in final segmentation or classification quality, and peak memory falls by 38 to 55% in a U-Net scaling study. Replacing the convolutions of the official PyTorch Hyperbolic U-Net makes its training step 1.4 times faster with half the memory. Evaluating an existing layer from its patch statistics thus makes Poincaré convolutional networks cheaper to train in the tested models and software stacks.
66. STAMP: Manufacturing-Informed Generative Design and Shape Optimization of Sheet Panels
STAMP:面向板材的制造感知生成设计与形状优化
AI 总结:STAMP将制造条件嵌入板材形状表示,结合边界条件扩散与预测器梯度优化,在汽车引擎盖内板实验中,小训练集即可生成多样布局,且变形优化效果优于随机选择。
链接:https://arxiv.org/abs/2611.18144
机构:Korea Advanced Institute of Science and Technology(韩国科学技术院); Narnia Labs(纳尼亚实验室)
作者:Jihoon Kim, Jun Hyeok Song, Wonho Ha, Namwoo Kang
英文摘要:Generative design of formed sheet panels must preserve geometric manufacturing conditions while exploring layouts and improving performance. STAMP embeds these conditions directly in the shape representation. Each panel is described by its material layout and a reference surface with one height at each occupied position in a plane perpendicular to the drawing direction. Nominal thickness is prescribed along the normal. The representation allows curved surfaces, ribs, and openings. It excludes reference-surface undercuts and keeps nominal thickness fixed without manufacturing penalty terms. Because these conditions belong to the representation, every generated and optimized panel satisfies them regardless of training-set size. Boundary-conditioned diffusion generates alternative layouts, and predictor gradients guide a surface optimization that retains outlines, openings, and designated fixed regions. We demonstrate STAMP on automotive hood inner panels using CarHoods10k. With a comparable number of stored values, depth maps reconstruct surfaces more accurately than point-cloud and voxel baselines. From only five training designs, one of three training runs yields novel and varied layouts. A generator trained on 500 designs, 6.5% of the training set, already reaches the layout variety of the full-data model. Across 11 held-out design families, predictor-based selection among existing dataset designs yields an average gap of 0.18 mm to the best available FEA deformation, versus an expected 1.59 mm for random selection. It does better than random selection in all 11 families. At a 10% depth-change bound, a network not used in the search predicts an average deformation reduction of 24.8% for six generated and existing panels, with a 3.2% average mass increase computed from geometry. Engineers can thus explore and optimize panels within this manufacturing-informed design space.
67. On the Limits of Sufficient Explanations
充分解释的局限性
AI 总结:该研究形式化刻画了结构化数据分类器充分解释的存在条件,扩展分析至多种充分性变体,设计统计量界定任务最大可实现充分性,评估发现多数数据集无法实现完全充分性,为评判解释器提供任务级参考。
链接:https://arxiv.org/abs/2611.18163
机构:TU Wien(维也纳技术大学); Leipzig University(莱比锡大学); Max Planck Institute for Mathematics in the Sciences(马克斯·普朗克数理科学研究所); Santa Fe Institute(圣达菲研究所)
作者:Klaus Weinbauer, Peter F. Stadler, Thomas Gärtner, Sagar Malhotra
英文摘要:We formally characterize the conditions under which sufficient explanations exist for classifiers on structured data such as graphs and strings. We focus on post-hoc explainers that select parts of the input as sufficient explanations. An explanation is sufficient if the selected part alone ensures the predicted label. Sufficient explanations have been widely adopted across data modalities, including graphs, strings, and images. However, a unified formal analysis of sufficient explanations remains missing. We bridge this gap with four main contributions: (i) We define a general explanation formalism consisting of an instance space, a classifier, and a select relation. The select relation specifies which potential sub-instances or feature subsets can be selected as explanations from each instance; (ii) We show that the existence of sufficient explainers is fully characterized by the interplay between the classifier and the select relation; (iii) We extend this analysis to practically relevant variants of sufficiency, including probabilistic sufficiency and deletion sufficiency; (iv) Based on the formal analysis, we devise statistics that bound the maximum achievable sufficiency for a given task. We evaluate these statistics on language, protein, and molecular classification datasets and find that full sufficiency is unattainable on most of them. Since these bounds hold for every explainer, they provide a task-level reference against which any explainer's sufficiency can be judged in absolute terms.
68. T2ST: Data-Efficient Spatio-Temporal Foundation Models via Temporal Data and Knowledge Transfer
T2ST:通过时间数据与知识迁移实现数据高效的时空基础模型
AI 总结:提出T2ST框架,用10%时空数据结合辅助时间序列与时间序列基础模型知识迁移,提升STFMs在多数据集上的预测性能,建立数据高效训练新范式。
链接:https://arxiv.org/abs/2611.18199
作者:Yue Xu, Kaiyun Wei, Wenying Duan, Zichen Xu, Shuai Ma, Xiaoxi He
英文摘要:Spatio-temporal foundation models (STFMs) require large-scale training corpora, yet synchronized observations and spatial metadata are costly to acquire and curate, limiting the availability of suitable data. By contrast, time-series data are abundant and easier to collect. Since observations at each location form a time series, this motivates a natural question: can abundant time-series data enhance STFMs when spatio-temporal observations are scarce? To bridge this gap, we propose T2ST, a data-efficient training framework that augments limited spatio-temporal observations with selected auxiliary time series and transfers knowledge from a frozen time-series foundation model. Our key insight is that temporal pattern learning can benefit from abundant external time series, while spatial dependency learning remains grounded in real spatio-temporal observations. Guided by this insight, T2ST retrieves matched sequences to reinforce sparsely observed temporal patterns and selects reliable complementary sequences to broaden temporal coverage. Temporal relation distillation aligns relationships among historical patches, while multi-scale prediction distillation transfers forecasting behavior at fine and coarse temporal resolutions, enabling knowledge transfer across heterogeneous architectures. Using only 10\% of the original spatio-temporal data, T2ST enables STFMs to achieve overall forecasting performance competitive with or superior to their full-data counterparts across six long-term and twelve short-term forecasting datasets. These results establish a new paradigm for data-efficient training of spatio-temporal foundation models. Code is available at this https URL.
69. NeoResearch: Literature- and Experience-Guided Autonomous Time Series Model Discovery
NeoResearch:基于文献与经验引导的自主时间序列模型发现
AI 总结:提出NeoResearch框架,利用LLMs作为研究者,通过双循环工作流、文献挖掘与分层经验记忆,在十个数据集上实现轻量级领域特定预测模型的自主发现,性能具竞争力。
链接:https://arxiv.org/abs/2611.18235
机构:University of Science and Technology of China(中国科学技术大学)
作者:Ze Guo, Mingyue Cheng, Xiaoyu Tao, Shuo Yu, Shangtong Ye
英文摘要: Developing effective forecasting models for diverse time-series domains requires substantial expert knowledge, evidence from scientific literature on the web, and iterative experimentation. However, translating this knowledge and research experience into model designs requires preserving source context and testing applicability under task-specific assumptions. In this paper, we propose NeoResearch, a literature- and experience-guided autonomous research framework that leverages large language models (LLMs) as researchers to discover lightweight, domain-specific forecasting models. Specifically, NeoResearch establishes an expert-inspired dual-loop research workflow, coupling hypothesis-driven architecture exploration with iterative training and hyperparameter optimization through experimental feedback. To enable knowledge-grounded discovery, the agent autonomously mines scientific literature from the Web, extracting modeling mechanisms, empirical evidence, and applicability conditions to formulate task-grounded, testable architecture hypotheses. Furthermore, a hierarchical experience memory links literature findings to experimental outcomes and consolidates conditional lessons, guiding architecture discovery and training optimization while supporting reuse across forecasting tasks. Experiments on ten datasets show competitive performance and support dual loops, literature extraction, and memory reuse. Our code is available.
70. Small Is Not Dead: Distance-Aware Cluster Revival for e-means
小并非无用:面向e-means的距离感知聚类复兴机制
AI 总结:针对e-means算法的死聚类复兴机制仅考虑聚类大小的缺陷,提出距离感知的改进条件,在不增加运行时间的情况下,提升含小型孤立组数据集的聚类性能,保留原算法优势。
链接:https://arxiv.org/abs/2611.18238
机构:Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所)
作者:Eyal Weiss
英文摘要:e-means (Bessa et al., 2026) is a recent mini-batch k-means algorithm, now part of the FAISS library, that reaches the error of Lloyd's algorithm about an order of magnitude faster on large embedding datasets. Every five mini-batches, it removes every cluster whose running point count falls below a tenth of the average and reuses its centre to split a large cluster. In the authors' ablation, removing this mechanism, called dead-cluster revival, raises the error more than removing any other component added to the moving-average update. The rule, however, considers only cluster size: it cannot distinguish a cluster that is small because it is redundant from one that covers a rare, isolated group of points, and on data with such groups it repeatedly removes centres whose removal is costly. We add a second condition, based on the distance between centres: a small cluster is removed only if its centre is close to another centre, relative to a running estimate of the mean squared error. When a centre equals the mean of its points, this squared distance is an upper bound on the average increase in squared error, per point of the cluster, caused by removing the centre. The condition costs one nearest-centre search for the small clusters every five mini-batches and adds no measurable running time. On the e-means paper's embedding benchmarks, it never prevents a removal, so the results are identical to those of FAISS. On datasets with small isolated groups not used during development, it reduces the test error after two epochs by roughly 10% to 80% relative to count-based revival, and it preserves the advantage of k-means++ initialization; on the other evaluation datasets, it stays within about 1% of the better of revival enabled and disabled. We also report two failure modes that the analysis predicts. This is a CPU proof of concept; GPU implementations are left to future work.
71. Right Token, Right Time: From Per-Token Gating to Trajectory-Aware Activation Steering
正确的 token,正确的时机:从逐 token 门控到轨迹感知的激活引导
AI 总结:该研究提出两种轨迹感知的激活引导门控机制 CFP 和 CLABS,将引导转化为逐 token 分配问题,在固定预算下实现大语言模型的行为控制,同时提升生成质量。
链接:https://arxiv.org/abs/2611.18274
机构:The Vanguard Group, Inc.(先锋集团); University of Toronto(多伦多大学)
作者:Nima Eshraghi, Lovedeep Gondara, Sagarika Suresh, Xiaotong Xu, Jithin Pradeep, Fanny Chevalier
英文摘要:Activation steering via sparse autoencoders (SAEs) enables behavioral control of large language models without task-specific fine-tuning. Yet, standard methods apply the steering signal at every generated token, displacing representations from the distribution the model was trained on and eroding generation quality. We show that \emph{when} along a generation the intervention is applied is a decisive axis of control. We cast steering as a per-token allocation problem under a fixed budget of steerable tokens, so that methods differ only in which tokens they select, making allocation the sole variable. Within this framework we introduce two gates. The first, Contrastive Feature Projection (CFP), is memoryless and selects the tokens least aligned with the target behavior through a sparse, interpretable feature projection. The second, Closed-Loop Adaptive Bernoulli Steering (CLABS), is trajectory aware. It treats allocation as closed-loop feedback control, tracking the alignment a generation has accumulated so far and spending budget where the trajectory falls behind. On a linear steering-response model we derive an explicit gain region that guarantees closed-loop stability of CLABS and show that its integral term reduces the steady-state tracking offset. Empirically, CFP and CLABS achieve the largest behavioral shift among budgeted gates at matched budgets, with CLABS strongest under the tight budgets where allocation matters most, while best preserving fluency.
72. Clean Tickets, Wrong Orders: Catching Silent Errors with a Language Model in Your Browser Tab
干净的票据,错误的订单:在浏览器标签页中用语言模型捕获静默错误
AI 总结:本文提出在浏览器中运行的0.8B参数语言模型,可捕获订单转换中的静默错误,在1357个PIZZA测试订单上精确匹配率达0.882,且订单数据不离开设备。
链接:https://arxiv.org/abs/2611.18284
机构:ITMO University(ITMO大学)
作者:Umar Ahmed, Maxim Dunaev, Mohammad Nour Al Awad, Sergey Ivanov, Ivan Khodnenko
英文摘要:A small language model that turns a typed order into structure can fail in two ways. It can print something broken, which any system rejects. Or it can print a clean, well formed order that nobody placed. Our companion work calls the second kind a silent error, and it is the dangerous one. We present a web demo in which a fine-tuned 0.8B parameter model runs entirely inside the visitor's browser tab, through this http URL compiled to WebAssembly. No order text leaves the device. The page parses orders as the visitor types, scores every ticket with the PIZZA benchmark's own matcher ported to TypeScript, refuses anything off the menu with "?" so the model can face the open web, and lets visitors hunt for silent errors or try to cause one. Run in the browser on all 1,357 PIZZA test orders, the deployed model writes the same output as the server evaluation for 99.0% of them and reaches the same exact match (0.882); we also report its latency on 3 consumer laptops. Demo: this https URL
73. DECODE: Decomposable Environments for COntrolled Sequential-Decision Evaluation
DECODE:用于受控序贯决策评估的可分解环境
AI 总结:DECODE是用于序贯决策系统评估的基准,通过消费者信贷催收生成的环境开展受控实验,验证规划时域、输入更改等对求解器得分的影响,可测试求解器性能假设。
链接:https://arxiv.org/abs/2611.18367
机构:Alpha Synthesis Labs(阿尔法合成实验室)
作者:Diego Silva Prado, Bruno Caldas de Souza, Tiago Amaral Penteado de Jesus, Ricardo Guimarães Herrmann, Cristiano Breuel, Cristiano Bevitori Maffia De Oliveira
英文摘要:When a sequential decision system falls short of an optimum, its score does not reveal which modifications would improve its decisions. DECODE is a benchmark for testing such modifications through controlled experiments on planning and available information. Its consumer-credit collections generator provides five partially observed environments that share known dynamics matrices and vary a memory parameter and process noise. The experiments change selected inputs or planning rules while keeping the rest of the solver fixed. Each comparison specifies the solver's state inputs, response inputs and planning horizon. On the deterministic base environment, which was selected for a large gap between six-month and one-month planning with the hidden state, extending planning from one to six months increases the scores of two gradient-boosted solvers by 15 to 17 percentage points of the exact optimum, computed with the hidden state and borrower traits. Even at this horizon, the best graded solver, whose repayment response is fitted on logs, remains 15.6 points below that optimum. In a specified intervention sequence, three changes to its state inputs and their evaluation during search lower its score by 6.3 points, and replacing its fitted repayment model with the true response, evaluated with hidden borrower traits, then raises it by 15.6, a net recovery of nine of those points. Because the intermediate effects are conditional on the repayment model and the order of the changes, they do not uniquely assign the gap to separate causes. Within these limits, DECODE makes hypotheses about solver performance testable through specified interventions under known dynamics and explicit information conditions.
74. Where Tree Ensembles Decide: Structural Local Explanation with Decision Predicate Graphs
树集成模型的决策依据:基于决策谓词图的结构化局部解释
AI 总结:针对树集成模型预测解释的缺陷,提出局部决策谓词图方法,可定位关键决策阈值,在错误预测和故障阈值识别上效果优于对比方法,补充了现有解释技术。
链接:https://arxiv.org/abs/2611.18382
机构:University of Trieste(的里雅斯特大学); University College Cork(科克大学学院)
作者:Sylvio Barbon Junior, Luca Longo
英文摘要:Tree ensembles are among the most accurate models for tabular data, yet the computation behind a single prediction is spread over hundreds of decision rules. Feature attributions and counterfactuals explain such predictions through the influence of features or a change of the input, leaving open which of the thresholds applied by the trees a prediction responds to, while structural explanations compress these rules and lose the trees behind them. To address this gap, we propose a local Decision Predicate Graph (local DPG), which gathers the rules executed for a sample into a verifiable record of the computation, with a class support that reproduces every explained prediction. From these rules we select the critical predicate, the executed predicate whose crossing is estimated to move the model most strongly toward a chosen class, which offers the user a concrete threshold and the trees that share it, without an external explainer. Across 16 datasets and four ensemble families, it separates differently predicted neighbours better than random and nearest-threshold predicates. A single crossing recovers the true class in 46-69% of wrong predictions, against 29-50% when the same rule is applied to the feature ranked first by TreeSHAP, a measure close to the selection criterion, and on planted faults it finds the faulty threshold in 46-71% of the resulting errors, against 6-21% at random. Although training-free edits of these predicates did not reduce the error on unseen data, the critical predicate complements attributions and counterfactuals by naming where a prediction can be changed.
75. WeatherDreamer: Learning a World Model from Multimodal Earth Observations
WeatherDreamer:从多模态地球观测数据中学习世界模型
AI 总结:WeatherDreamer是从18个全球观测系统端到端学习递归滤波循环的世界模型,在多类气象要素预报上优于GEFS等业务系统,可直接从观测数据联合学习同化与预报,推理效率高。
链接:https://arxiv.org/abs/2611.18393
机构:Zeus AI, Inc.(宙斯人工智能公司)
作者:Kate Duffy, Elise Penn, Tristan Ballard, August Posch, Thomas J. Vandal
英文摘要:Machine learning weather models now rival operational global forecasts but still start from analyses produced by separate, expensive data assimilation (DA) systems, which for global models are typically updated every six hours. Observation-to-observation models avoid this dependence, but most omit the recursive filtering cycle that lets DA systems carry a background state through sparse, irregular observations. We introduce WeatherDreamer, a world model that learns this cycle end-to-end from 18 global observing systems, without reanalysis. It infers a latent state from observations, carries it forward hour by hour with learned dynamics, corrects it each hour with new observations, and can predict what any of its observing systems would measure at any location. At held-out stations, its ensembles beat NOAA's Global Ensemble Forecast System (GEFS) for temperature, dew point and wind out to 12 h and are better calibrated than GEFS and the ECMWF ensemble. Precipitation, cloud-top height and solar irradiance, never inputs at inference, are inferred with skill matching or exceeding operational products at short leads. Against the first guess of NOAA's Gridpoint Statistical Interpolation (GSI) DA system, WeatherDreamer's short-range departures are within 10% of GSI's at surface stations and within 25% for moisture-sensitive microwave channels, but up to five times larger for temperature-sounding channels. Never given observation errors, its learned update assumes errors close to known instrument and retrieval errors of microwave sounders and scatterometer winds. WeatherDreamer also separates viewing geometry from atmospheric state, recovering 83-96% of observed limb darkening and producing seamless nadir-view imagery. Producing an hourly global analysis in about 1.5 minutes on one GPU, WeatherDreamer shows that assimilation and forecasting can be learned together directly from observations.
76. PACT: A Decoder-Confidence-Guided Two-Round Receiver for Joint Channel and Phase-Noise Estimation in Sub-THz OFDM
PACT:用于子THz OFDM中联合信道与相位噪声估计的解码器置信度引导两轮接收机
AI 总结:针对子THz OFDM接收中频率选择性衰落与相位噪声的联合损害,提出解码器置信度引导的两轮PACT接收机,在$E_b/N_0=30$dB时较最优学习基线降低码块错误率,且具备跨多种配置的适用性。
链接:https://arxiv.org/abs/2611.18450
机构:University of Victoria(维多利亚大学)
作者:Ruilin Wang, Xiaodai Dong
英文摘要:Frequency-selective fading and oscillator phase noise (PN) jointly impair coded sub-THz OFDM reception. We propose a decoder-confidence-guided two-round receiver combining a {pilot-aware complex transformer} (PACT) estimator, banded linear minimum mean-square error equalization, and neural normalized min-sum decoding. PACT jointly estimates the frequency-domain channel and effective time-domain PN through interacting complex-valued branches. Decoder-derived pseudo-pilots and continuous constellation-aware confidence guide second-round refinement through PACT inputs and attention, with parameters shared across rounds. At $E_b/N_0=30$~dB, the PACT receiver achieves approximately $70\%$ and $57\%$ lower code-block error rates than the best-performing learning-based baseline in the two benchmark settings, respectively. Frozen-weight tests further demonstrate applicability across channel/PN models, carrier frequencies, and FFT/bandwidth configurations.
77. Asymptotic Margins and Feature Confinement in Conic Classification Heads under Softmax Cross-Entropy
Softmax交叉熵下锥形分类头中的渐近间隔与特征约束
AI 总结:该研究探究Softmax交叉熵训练下锥形分类头的类别区域是否约束特征,推导了渐近间隔的计算方式,在CIFAR数据集上验证了锥形头单元均具正间隔、原型头多数单元有界的理论结论。
链接:https://arxiv.org/abs/2611.18507
机构:Eskişehir Technical University(埃斯基谢希尔技术大学)
作者:Omer Nezih Gerek
英文摘要:Classification heads built on conic functions give each class a bounded region of the feature space, and such regions are used to reject samples of unseen classes. We ask whether these regions also keep the features bounded when the head is trained with softmax cross-entropy. For a head whose class scores combine a linear term with a Euclidean norm, we first show that the region of each class is bounded by a quadric of revolution, whose eccentricity is the reciprocal of one learned ratio. We then attach to each class an asymptotic margin, which compares the growth of its score with the growth of all the other scores and can be computed by a second-order cone program. The loss of a class has infimum zero exactly when its margin is positive, and it then approaches zero only along diverging features. When the margin is negative, the loss is coercive and its minimizers lie in an explicit ball. Since softmax depends only on the differences between scores, a class with a bounded region can still have a positive margin, so bounded regions do not confine the features. The result extends to other norms, including the polyhedral conic functions. On CIFAR-10 and CIFAR-100, all 1210 cells of 67 trained conic heads have positive margins, whereas a prototype head keeps nine of its ten cells bounded, as the theory predicts.
78. Pairing AIS with RF: Analysis of a Markovian Approach for Maritime Data Fusion
将AIS与RF配对:一种用于海事数据融合的马尔可夫方法分析
AI 总结:本研究针对海事数据融合问题,应用配对隐马尔可夫模型(PHMM)结合AIS与RF数据,经实验其性能接近但未超越时间加权最近邻基线,为海事活动监测提供了新方法。
链接:https://arxiv.org/abs/2611.18563
机构:Tilburg University(蒂尔堡大学); University of Calabria(卡拉布里亚大学)
作者:Daniel Grimm, Kyra Jongman, Renato Cordeiro Ferreira, Giuseppe Cascavilla, Alfredo Cuzzocrea, Willem-Jan Van Den Heuvel
英文摘要:Monitoring maritime activities is important for safety and security, particularly for detecting illegal activities, but remains challenging due to the size and complexity of the maritime domain. The Automatic Identification System (AIS) is commonly used for this purpose, despite its known vulnerabilities. In contrast, space-based radio frequency (RF) observations provide an independent source of vessel activity but lack ship identification and therefore cannot identify vessels on their own. Following the CRISP-DM process, this study applies a Pair Hidden Markov Model (PHMM) to align individual RF detections with AIS trajectories, using temporal and spatial information while modeling noise and timing discrepancies. We evaluate it on NOAA AIS data with synthetic RF detections against nearest-neighbor baselines and analyze its errors with bias tests on trajectory length, sampling density, stationarity and AIS--RF distance. The length-corrected Forward score reaches a top-1 precision of $0.7776$ on the validation split of multi-candidate detections, where errors are possible, and an AUC of $0.637$ for detecting dark vessels among the detections that pass the prefilter. With a single RF detection, the score mostly reflects the AIS trajectory itself, and its errors favor longer and more stationary trajectories. A log-odds score, which compares the full model with a null model without match transitions, raises precision to $0.8580$ and AUC to $0.852$. Its length-corrected variant no longer shows a significant bias towards stationary trajectories and short inter-message distances, but still favors candidates farther from the RF detection. A time-weighted nearest-neighbor baseline without fitting remains ahead (precision $0.9013$, AUC $0.904$), so this single-detection, hand-designed PHMM formulation approaches but does not beat it.