2026-11-19 | CS.LG机器学习 | 共 118 篇,本文展示前 40 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 7 篇
2. 强化学习与序列决策 2 篇
3. 优化、泛化与理论分析 2 篇
4. 鲁棒性、不确定性与可信学习 1 篇
5. 图学习与结构化数据 1 篇
6. 迁移、元学习与持续学习 4 篇
7. 数据集、基准与评测 2 篇
8. 机器学习应用 2 篇
9. 其他/综合机器学习 19 篇
1. 深度学习架构与训练方法 | 7 篇
1. Neural Network-Based Modeling of Hysteretic Systems: From Prandtl and Preisach Neural Networks to Neuro-Madelung and Neuroplastic Continuous Models
基于神经网络的滞后系统建模:从普朗特神经网络和普雷斯查神经网络到神经马德龙模型和神经塑性连续模型
AI 总结:本综述梳理了PNNs、PreisachNNs等多种神经网络滞后模型的发展,分析其机制、架构及应用,最终提出EPNN可适配多种滞后特性,为滞后系统建模提供了系列方案。
链接:https://arxiv.org/abs/2611.23240
作者:Mehrdad Shafiei Dizaji, Farzad Shafiei Dizaji
英文摘要:Hysteresis is a complex nonlinear phenomenon characterized by memory dependence, path dependence, and, in many physical systems, degradation, non-congruency, asymmetry, and rate dependence. This review examines the development and capabilities of Prandtl neural networks (PNNs), Preisach neural networks (PreisachNNs), generalized Prandtl neural networks (GPNNs), the neuro-Madelung model (NMM), extended Preisach neural networks (EPNNs), and dynamic plastic continuous neural networks (DPCNNs). Particular attention is given to their mechanisms for representing memory, network architectures, activation functions, training algorithms, treatment of deterioration and rate dependence, and applications to nonlinear structural and material systems. The PNN introduced hysteretic memory directly into neural activation through stop operators and demonstrated accurate nonlinear dynamic analysis of structures. Preisach-NNs subsequently extended this concept through an additional nonlinear hidden layer to represent non-Masing hysteresis. GPNNs introduced deteriorating-stop neurons to capture stiffness and strength degradation and non-congruent hysteresis. A different generalization was provided by the NMM, which combined Madelung's hysteresis rules with multilayer feedforward neural networks to represent diverse rate-independent and rate-dependent behaviors. These developments culminated in the EPNN, which combines deteriorating hysteretic operators, nonlinear neural mappings, and input-rate information to accommodate Masing and nonMasing, symmetric and asymmetric, congruent and noncongruent, and rate-independent and rate-dependent hysteresis.
2. Exploring Parkinson's Diagnosis Using Machine Learning Techniques
利用机器学习技术探索帕金森病诊断
AI 总结:本研究将多种机器学习算法应用于含58人的PD数据集,发现决策树和逻辑回归准确率最高,SVM分类器灵敏度达97.56%,为帕金森病诊断提供了可行的机器学习方案。
链接:https://arxiv.org/abs/2611.23248
作者:Farhaan Qazi
英文摘要:In recent years, machine learning (ML) techniques have emerged as promising tools for accurate and timely diagnosis of Parkinson's disease (PD) which is an incurable neurodegenerative disorder. This study explores the integration of ML algorithms and PD diagnosis, highlighting their potential applications in various aspects of the disease. ML methods such as support vector machines, decision trees, multilayer perceptron, k-nearest neighbours, logistic regression and random forest (with and without particle swarm optimisation) were applied on a PD dataset obtained from Leeds Teaching Hospitals NHS Trust containing data from 58 people. In terms of accuracy, the Decision Tree and Logistic Regression performed the best with scores of 72-76% while multilayer perceptron was least effective. All the models were remarkable in classifying positive PD cases with sensitivity scores going up to 97.56%, with SVM classifier at the pinnacle. However, ability to classify healthy controls from PD cases was insignificant throughout the board. Although, all the employed models delivered reasonable results in categorising PD patients in the presented dataset; access to more data, further study and advancement of these ML approaches could lead to enhanced diagnostic outcomes, supplementing to an improved understanding of Parkinson's disease.
3. BiMa-ECGSR: reconstructing the 12-lead ECG from reduced lead sets with bidirectional state-space models
BiMa-ECGSR:基于双向状态空间模型从简化导联集重建12导联心电图
AI 总结:BiMa-ECGSR采用双向Mamba状态空间编解码器,以回归或扩散模式从简化导联集重建12导联心电图,在多数据集上优于线性方法,速度快且可提升简化导联记录的可用性。
链接:https://arxiv.org/abs/2611.23345
机构:Magna Graecia University of Catanzaro(卡坦扎罗马格那格雷西亚大学); University of Calabria(卡拉布里亚大学)
作者:Ugo Lomoio, Pierangelo Veltri, Pietro Hiram Guzzi
英文摘要: Wearables and monitors record few electrocardiogram (ECG) leads; most diagnostic tools assume 12 leads. BiMa-ECGSR reconstructs the 12-lead ECG from reduced lead sets with a bidirectional Mamba state-space encoder--decoder, as regression (BiMa-SR) or diffusion (DiBiMa-SR). Models were trained on PTB-XL for six input sets (I; II; I+II; I+II+V1; I+II+V2; I+II+V1+V4), see only the measured leads at inference, and were tested on the PTB-XL test fold (2,198 records) and two external cohorts (Georgia, 10,275 records; Chapman-Shaoxing/Ningbo, 43,559). From lead II alone, the pooled median Pearson correlation (PCC) over the 11 predicted leads was 0.914 on PTB-XL, against 0.784 for a least-squares linear filter (lead I: 0.906 against 0.789). As limb leads are exactly derivable from I and II, multi-lead inputs were compared on predicted chest leads: 0.939 against 0.849 for I+II and 0.979 against 0.962 for I+II+V1+V4. BiMa-SR exceeded the linear comparator in all 18 configuration--cohort pairs (by 0.012--0.136), a margin that shrank as chest leads were added. From lead II, regression was more accurate than diffusion (DiBiMa-SR: 0.903 one-step, 0.862 with six DDIM steps). A 12-lead classifier trained only on real ECGs reached a superclass macro AUROC of 0.912 on real PTB-XL ECGs, 0.843 on reconstructions from lead II and 0.908 from I+II+V1+V4; externally, reconstructions from three or four leads scored within 0.004 of real ECGs. BiMa-SR (2.68\,M parameters) takes 45.8 ms per 10-s record on a GPU. Reconstruction makes reduced-lead recordings usable by 12-lead tools; it cannot add information absent from the measured leads.
4. QDA: Closed-Loop LLM Quantization Design with Agents
QDA:基于智能体的闭环大语言模型量化设计
AI 总结:QDA是基于智能体的闭环大语言模型量化设计系统,通过快速评估与构建方法库,在低GPU耗时下提升量化模型准确率,且无推理开销,将发布相关工具。
链接:https://arxiv.org/abs/2611.23388
机构:MIT(麻省理工学院); NVIDIA(英伟达)
作者:Xingyang Li, Tianlang Zhao, Song Han, Ligeng Zhu
英文摘要:Post-training quantization is the standard way to serve large language models at low cost. However, the best quantization recipe differs across models and precisions. As a result, experts must redesign it for every new model, which is time-consuming and often sub-optimal. Fortunately, an LLM agent can take over this design by refining the recipe over rounds of building and evaluating candidates, so that more rounds lead to better recipes. However, evaluating one quantized reasoning model takes tens of GPU-hours, and combining methods from different codebases means porting each to the new architecture by hand. We present QDA, a system in which an agent designs the recipe for each model and precision. To make evaluation fast, QDA scores each candidate in minutes by its output KL divergence from the original model on reasoning traces that the agent never sees, and checks promising ones with long generations to catch failures such as repetition loops. To make building fast, QDA provides a library of public PTQ methods that are compatible with one another and with new model architectures. Across four reasoning models, QDA improves accuracy over the strongest public recipe by 0.9, 1.4 and 2.2 percentage points on average at W4A16, W4A8 and W3A16, using 64 GPU-hours per search. On the 320B-parameter MoE model GLM-5.3-Flash at NVFP4 W4A4, it recovers 98.3% of the FP8 model's accuracy, against 96.9% for the best vendor checkpoint. Every QDA checkpoint also runs on existing serving kernels with no inference overhead. We will release the library, the evaluator and the harness.
5. Which Tokens, in What Order, and How Fast? A Theoretical Analysis of On-Policy Distillation Objectives
哪些 token、以何种顺序、多快?对策略内蒸馏目标的理论分析
AI 总结:该研究通过理论分析明确了策略内蒸馏(OPD)的目标选择对token优先级、学习顺序及梯度优化的影响,为不同场景下OPD目标的选择提供了理论依据。
链接:https://arxiv.org/abs/2611.23397
机构:Princeton University(普林斯顿大学); Bar-Ilan University(巴伊兰大学)
作者:Hubert Strauss, Liam Fowl, Noam Razin
英文摘要:On-policy distillation (OPD) trains a student language model to match a teacher model based on its own generations. When using OPD, one must choose whether to apply it at the sequence or token level and which divergence to minimize. However, despite the wide adoption of OPD in practice, the formal understanding of which OPD objective is appropriate for a given setting is limited. Toward addressing this gap, we theoretically analyze how the choice of OPD objective governs which tokens are prioritized, in what order, and how efficiently. Our analysis reveals that sequence-level OPD exhibits a future agreement bias, which myopic token-level objectives avoid. This bias induces a reverse learning order, in which sequence-level OPD first matches the teacher at later token positions, while at earlier positions it can favor tokens that are improbable under the teacher, and thus often undesirable. As for the choice of divergence, we prove that it strongly influences the amenability of OPD to gradient-based optimization. In particular, while the forward KL divergence enjoys a well-behaved objective landscape, other $f$-divergences, such as reverse KL, can suffer from vanishing gradients even when the student and teacher are far apart. Across language model post-training settings, we demonstrate the implications of these theoretical findings for which OPD objective is preferable, highlighting the importance of accounting for the interplay between the student, teacher, and task at hand.
6. AllotNet: an Interpretable Mixture-of-Experts Choice Model for Moral Judgement in Humanitarian Aid Allocation, Validated against a Planted Synthetic Population
AllotNet:一种可解释的混合专家选择模型,用于人道主义援助分配中的道德判断,基于植入式合成人群验证
AI 总结:AllotNet是用于人道主义援助分配道德判断的可解释混合专家选择模型,基于560万会话的合成人群验证,参数仅23550,支持多语言运行时,目前未在真实数据上训练。
链接:https://arxiv.org/abs/2611.23474
机构:Conflux Laboratory(Conflux实验室)
作者:Mark Nowak (Conflux Laboratory)
英文摘要:Official development assistance fell by 23.1 per cent in 2025, and the decision of who is helped first when there is not enough for everyone is moving into software. A leading published machine-learning targeting system excluded 53 per cent of eligible households as deployed. If the rule of distribution ends up in code, it should carry the judgement of many cultures, and the machine should execute while a person judges. AllotNet is an interpretable mixture-of-experts conditional logit for the allocation judgements elicited by Allot, a pre-registered six-language instrument: eight linear taste experts over seven ethical criteria, weighted by a gate over participant context, with a damped residual, an encoder for household intake, an outcome head and a budget-constrained planner that builds a review queue and never rejects anyone. A model of human judgement has no answer key on real data, so we wrote one first: a planted synthetic population of 5.6 million sessions and 104 million responses (98 million usable choices), generated by the production code path from a ground truth hidden from the loss. All sixteen pre-specified checks passed: criterion ranking $\rho = 1.000$, hidden segments recovered (ARI 0.671), outcome head at 99 per cent of the noise ceiling, planner at 99.4 per cent of oracle. The caveats are reported with them: two checks are weaker than their titles, and a live-generation failure cost 260,712 seeds. The model has 23,550 parameters, is trained quantisation-aware for NVFP4 with its interpretable core in fp32 (welfare-rank parity $\rho = 0.9937$ at W4A16 on the shipped bundle; one parity threshold was relaxed post hoc), and ships as a 125 KB bundle with C11, Java, Rust and Python runtimes. Nothing has been trained on real data yet; at the study's real scale a hierarchical Bayesian mixed logit is the registered comparator.
7. Toaster: Nonlinear Memory from Cascaded Linear Memories and Target Propagation
Toaster:基于级联线性记忆与目标传播的非线性记忆
AI 总结: Toaster是一种基于级联线性记忆与目标传播的非线性记忆,在多个规模、数据集及任务上,其损失、困惑度、准确率等指标均优于KDA、Titans及注意力基线,训练效率也更优。
链接:https://arxiv.org/abs/2611.23648
机构:Google Research(谷歌研究院); University of Southern California(南加州大学)
作者:Zeman Li, Ali Behrouz, Yuan Deng, Praneeth Kacham, Rami Al-Rfou, Meisam Razaviyayn, Vahab Mirrokni
英文摘要:Recurrent memories let language models process long sequences with a fixed-size state. Linear memories such as DeltaNet and KDA store one matrix and take one delta-rule step per token. The product of a chunk of such steps has an exact WY form, so they train fast. Deep memories such as TTT-MLP and Titans store a small MLP, which can hold maps that no matrix can, but their update has no WY form. Toaster bridges the two by building on a known fact: a gradient step on a linear layer is a delta-rule write. It builds a two-layer nonlinear memory from two linear memories with an activation between them. We use target propagation to give the hidden memory its values by projecting the output error back through the second memory. Given a chunk's cross-layer signals, approximated once per chunk, each layer can then run on an unmodified delta-rule kernel. Our default runs this kernel on the output layer and updates the hidden layer once per chunk. Running it on both layers gives a better model in our ablation. At matched backbones and training-token budgets, Toaster has lower loss than KDA at all five tested sizes (0.2B-1.6B non-embedding parameters) on both C4 and PG19. Its C4 perplexity also matches or slightly improves on the attention baseline at every size. At 1.2B it is also below Titans. In a 3:1 hybrid with global attention, the Toaster hybrid has the lowest perplexity of the four hybrids tested, and it is 0.18 (C4) and 0.44 (PG19) below the attention baseline. At the largest size, Toaster's mean three-shot accuracy on 13 tasks is 51.84%, compared with 50.52% for KDA and 50.04% for Titans. In length extrapolation, Toaster's loss stays below KDA's up to 20K tokens (5x the training length). On the 145M backbone, at a hidden width matched to Titans' memory, Toaster takes at most 1.33x KDA's training-step time and is 2.8-5.5x faster than the tested Titans configurations at 32K context.
2. 强化学习与序列决策 | 2 篇
8. Efficient Variance-Aware Reinforcement Learning in Time-Inhomogeneous Linear MDPs
非齐次线性马尔可夫决策过程中高效的方差感知强化学习
AI 总结:本文针对非齐次线性 MDPs 提出 VA-LSVI-UCB++ 算法,实现了方差依赖 regret 界,适配轨迹方差最小值,消除了确定性环境中的多项式$K$依赖,收紧了置信半径。
链接:https://arxiv.org/abs/2611.23596
机构:Department of Computer Science, University of California, Los Angeles(加州大学洛杉矶分校计算机科学系)
作者:Qingyue Zhao, Qiwei Di, Jiafan He, Heyang Zhao, Kaixuan Ji, Quanquan Gu
英文摘要:We study variance-dependent reinforcement learning in episodic time-inhomogeneous linear Markov decision processes (MDPs) with feature dimension $d$, horizon $H$, and $K$ episodes. While recent works have established variance-dependent regret with $\tilde{O}(1)$ deterministic-regime overhead for linear mixture MDPs (Zhao et al., 2023) and worst-case nearly minimax optimal regret $\tilde{O}(d\sqrt{H^3 K} + d^7 H^8)$ for linear MDPs (He et al., 2023),, existing variance-aware analyses for linear MDPs (Li and Sun, 2023; Huang et al., 2023) rely on a coarse concentration step whose resulting regret guarantees retain a polynomial $\tilde{O}(K^{1/4})$ additive term even in deterministic environments. We propose VA-LSVI-UCB++, a computationally efficient algorithm that achieves the variance-dependent regret bound $\tilde{O}(d\sqrt{H\min\{\mathrm{Var}_K^*,\mathrm{Var}_K^\pi\}}+d^5H^4)$, where $\mathrm{Var}_K^*$ and $\mathrm{Var}_K^\pi$ denote the cumulative conditional variances of the optimal value function and the played policies' value functions along the realized trajectory. Our result adapts to the minimum of the two realized trajectory variances, recovers the worst-case minimax optimal leading term $\tilde{O}(d\sqrt{H^3 K})$, and collapses to $\tilde{O}(d^5 H^4)$ in deterministic environments, free of polynomial-in-$K$ dependency. At the core of our analysis is a simultaneous three-way reference-advantage decomposition for the optimistic, pessimistic, and squared value function estimators coupled with variance self-bounding and Freedman-type value-difference arguments, which tightens the pessimistic and second-moment confidence radii by a factor of $\tilde{O}(d H)$ and removes the inverse-variance-floor blowup.
9. Communicative On-Policy Distillation: Distilling Black-Box Teacher Capabilities through Communication for Long-Horizon Tasks
通信式在线策略蒸馏:通过通信蒸馏黑盒教师能力以解决长视野任务
AI 总结:针对传统在线策略蒸馏依赖黑盒教师对数的局限,提出通信式在线策略蒸馏(COPD),通过学生自主咨询黑盒教师并保留交互进行自蒸馏,在 CAMG-II 等基准上显著提升长视野任务成功率。
链接:https://arxiv.org/abs/2611.23673
作者:Lirui Luo, Kelong Mao, Xinwei Yang, Rongqing Li, Luyu Chen, Kieran Wong, Yudong Guo, Xinrui Wang, Jiayin Zhu, Gu Simiu, Sulong Xu, Cong Fang
英文摘要:On-policy distillation (OPD) is a powerful paradigm for improving language-model agents on long-horizon tasks, yet its conventional formulation relies on teacher logits that text-only black- box models do not expose. To address this limitation, we introduce Communicative On-Policy Distillation (COPD), which uses natural-language communication as a medium for distilling a stronger model's capabilities into a smaller student. During task execution, the student au- tonomously decides when to consult a black-box teacher and formulates open-ended natural- language requests without predefined question templates or intervention schedules. Successful student-teacher interactions are retained as privileged references to supervise fresh adviser-free student rollouts through on-policy self-distillation, jointly with task-reward reinforcement learning. On CAMG-II, COPD achieves 2.46 times the gain of the strongest black-box OPD baseline. The capabilities it learns through communication generalize to Terminal-Bench 2.1 and SWE-Bench Pro V2, improving task success without adviser access.
3. 优化、泛化与理论分析 | 2 篇
10. JEPA as a Transferable Optimizer: Learning and Understanding Black-Box Optimization from Reward-Agnostic Pretraining
作为可迁移优化器的JEPA:通过与奖励无关的预训练学习和理解黑盒优化
AI 总结:本文提出JEPA-PS优化器,通过与奖励无关的预训练学习黑盒优化,在15个控制环境中优于LLM优化器2倍以上,可零样本迁移至新环境,且其使用的历史信息依赖于任务类型。
链接:https://arxiv.org/abs/2611.23608
机构:Arizona State University(亚利桑那州立大学)
作者:Mayukh Debnath, Manan Roy Choudhury
英文摘要:Black-box optimization evaluates candidates through simulations, rollouts, or experiments, often without gradients. Learned optimizers are usually judged by whether they outperform existing methods. We ask a complementary question: what information does a learned optimizer use from its search history? We introduce JEPA-PS (JEPA Policy Search), based on a Joint-Embedding Predictive Architecture. It is pretrained on random rollouts using parameter vectors and scalar returns. Its latent-prediction objective predicts the next point in an optimization trajectory rather than its reward or gradient, allowing us to examine what was tried and how well it performed. At test time, JEPA-PS reads a short evaluation history and proposes a candidate in one forward pass, without task descriptions, reward shaping, or test-time gradients. We evaluate it on 15 control environments against 12 optimizers, including evolutionary methods, Bayesian optimization, CMA-ES, and an LLM optimizer. JEPA-PS is competitive with tuned classical baselines and outperforms the LLM optimizer by more than 2x on Swimmer at 71x lower per-step cost. It also transfers zero-shot to environments excluded from pretraining. Null-model comparisons and decoder-training ablations indicate that its latent representation carries information beyond simple history statistics; every trained decoder variant performs worse than the default frozen representation. Our main finding is that the history JEPA-PS uses depends on the task. On smooth landscapes it uses the full trajectory, whereas on rugged landscapes the best-seen point carries nearly all the signal. This memory requirement has a weak positive correlation with fitness-distance correlation (FDC; r=0.112, n=7), while an independent reward-ordering sensitivity probe does not corroborate the relationship (r=-0.024, n=7). Code: this https URL.
11. What Interpolators Store and What They Express: An Information-Theoretic Framework for Benign Overfitting and Label-Free Model Selection
插值器存储的内容与表达的内容:良性过拟合与无标签模型选择的信息论框架
AI 总结:该研究提出信息论框架区分插值器的存储与表达,揭示良性过拟合为表达消失,提出无需标签的模型选择准则V,在15个带噪数据集上表现优于传统方法。
链接:https://arxiv.org/abs/2611.23630
机构:University College London(伦敦大学学院)
作者:Nikolaos Nikolaou
英文摘要:Overparameterized learners can fit noisy training labels perfectly and still predict well, which neither classical complexity measures nor information-theoretic generalization bounds explain. We develop an information-theoretic framework that separates two things an interpolating learner does with its sample: storage, the information the trained model retains about its training labels, and expression, the information about the sample that reaches its predictions at fresh inputs. We first characterize the ideal model: for a loss l, the least complex l-sufficient representation is the Bayes act, whose entropy is the minimal sufficient complexity; this generalizes, and corrects, an earlier "lossless maximal compression" view of boosting. We then show that every interpolator stores exactly nH(Y|X) bits of label noise, so storage, and bounds built on it (including CMI bounds), cannot tell interpolators apart. Expression can: excess risk is bounded above and below by the expressed information V, the entropy over training samples of the prediction at an input, plus a modal-bias term, exactly so for binary labels. Benign overfitting is therefore vanishing expression, a picture that covers nearest-neighbour rules, averaging, minimum-norm least squares and double descent, and that links V to classical bias-variance decompositions and to model disagreement. Finally, V gives a model-selection criterion that needs no held-out labels. Among overparameterized learners on 15 noisy datasets, V estimated from two disjoint halves has 60% less regret than holdout validation at the same cost and matches 5-fold cross-validation at a quarter of its cost; at matched cost it also beats selection by conditional mutual information. We characterize when it fails and give remedies. Code: this https URL
4. 鲁棒性、不确定性与可信学习 | 1 篇
12. Toward Out-of-Distribution Generalization in Neural AC Power Flow
面向神经网络交流潮流的分布外泛化
AI 总结:针对电力系统分布外泛化难题,该研究评估物理信息损失、多电网训练等方法,提升图神经网络潮流模型从小电网到500节点系统的零样本迁移性能,明确各方法的实际效果。
链接:https://arxiv.org/abs/2611.23729
机构:Massachusetts Institute of Technology(麻省理工学院); Laboratory for Information and Decision Systems(信息与决策系统实验室)
作者:Ojas Sanghi, Anvita Bhagavathula, Alvaro Carbonero, Priya L. Donti
英文摘要:Growing uncertainty in power system operations from renewables integration, extreme weather, and data center loads challenges the reliability of traditional power flow solvers at scale. Machine learning-based proxies are a potentially promising alternative, but the prohibitive cost of generating training data for large grids makes out-of-distribution generalization a key capability for deployment; currently, models trained on small grids lack that capability. In this work, we systematically evaluate how physics-informed losses, multi-grid training, and perturbation-based data augmentation improve the zero-shot transfer of three graph neural network-based power flow models from smaller systems to a larger, unseen 500-bus system. We find that (1) physics-informed losses improve transfer relative to purely supervised objectives; (2) multi-grid training on smaller systems matches the best single grid but does not close the gap to target-grid training; (3) perturbation-based augmentation on edge attributes improves transfer by up to 54.6%; and (4) random line/generator dropout does not consistently improve performance.
5. 图学习与结构化数据 | 1 篇
13. FairPGT: Partitioned Graph Transformers for Dual-Level Fair Graph Clustering
FairPGT:用于双层级公平图聚类的分区图变换器
AI 总结:提出FairPGT分区图变换器,通过限制注意力于METIS分区、双层级公平约束及图感知自训练,在多基准图聚类中实现更优性能与公平性。
链接:https://arxiv.org/abs/2611.23631
机构:L3S Research Center(L3S研究中心); Leibniz University Hannover(汉诺威莱布尼茨大学); Free University Berlin(柏林自由大学); University of Mons(蒙斯大学); TIB – Leibniz Information Centre for Science and Technology(TIB——莱布尼茨科学与技术信息中心); Research Institute CODE, University of the Bundeswehr Munich(慕尼黑联邦国防军大学CODE研究所)
作者:Siamak Ghodsi, Amjad Seyedi, Sahar Tahmasebi, Eirini Ntoutsi, Sören Auer
英文摘要:Clustering on attributed graphs can produce demographically biased clusters, particularly when communities align with protected groups. Graph transformers can amplify this bias through same-group attention, while global attention limits scalability. We propose FairPGT, a partitioned graph transformer for fair graph clustering. FairPGT restricts attention to METIS partitions and connects them through routing tokens, which divides the quadratic cost of attention by the number of partitions. A graph-aware self-training target guides clustering, with a provably bounded deviation from the standard DEC target. Fairness is imposed at two levels: a mutual-information term promotes demographic parity in cluster assignments, while a normalized cross-group attention ratio (nCGAR) guides attention toward group neutrality through self-distillation. We prove that the nCGAR correction moves attention toward neutrality and establish a condition preventing overshooting. Across seven benchmarks, FairPGT achieves the best clustering performance and statistical parity on the three largest graphs (Credit, Pokec-n, Pokec-z), with a statistical-parity gap approximately ten times lower than DMoN, and is Pareto-dominated on only one dataset. On controlled stochastic block models, FairPGT attains 97% of the derived upper bound on NMI for exactly fair clustering when communities and protected groups coincide. These graphs further show that, under strong alignment, assignment-level fairness alone makes the attention group-heterophilous, whereas attention-level fairness alone improves neutrality without ensuring fair clusters. Code for reproducibility is available at this https URL.
6. 迁移、元学习与持续学习 | 4 篇
14. Stability Does Not Mirror Plasticity: A Module-Level View of Declarative and Procedural Learning in Transformers
稳定性与可塑性并不对称:Transformer中陈述性与程序性学习的模块级视角
AI 总结:该研究从模块级视角探究Transformer的持续学习,发现QK、VO与MLP模块在不同学习任务上的可塑性不同,且稳定性与可塑性不对称,为持续学习提供了新的模块级思路。
链接:https://arxiv.org/abs/2611.23427
机构:Columbia University(哥伦比亚大学)
作者:Jinjun Peng, Wailiang Zhao, Baishakhi Ray, Zhou Yu, Jufeng Yang
英文摘要:Plasticity and stability in continual learning are typically studied at the entire-model level and in a task-agnostic manner, yet prior work has reported divergent conclusions across settings. Inspired by cognitive distinctions between declarative and procedural memory, we instead study how plasticity and stability vary across transformer modules and task types. In a controlled synthetic environment with clean measurement, we show a double dissociation: query-key (QK) and value-output (VO) projections are the most plastic on procedural tasks, whereas MLPs are the most plastic on declarative memorization. Stability, however, does not simply mirror plasticity: when learning a new procedure, updating QK retains over half of the stored declarative memory, while updating MLPs retains far less and updating VO loses roughly four-fifths. Targeted module reset-and-recovery experiments explain this asymmetry: plasticity tracks which module is best suited to a task's primary computation or storage, whereas stability depends on all ways the existing capability relies on that module, including access to information stored in other modules. Experiments on a realistic model and tasks broadly echo these asymmetric dynamics. Overall, our work shows that plasticity and stability depend on different aspects of a module's functional role, offering a task-dependent, module-level perspective on continual learning.
15. When Does Subspace Direction Matter for LoRA? Regime Analysis of the Magnitude Principle in Few-Shot Adaptation
LoRA的子空间方向何时重要?少样本适应中幅度原理的机制分析
AI 总结:该研究分析少样本适应中LoRA初始化子空间方向的作用机制,提出对齐系数ρ,设计PivotLoRA方法,在少样本分类等任务上取得优于普通LoRA的性能。
链接:https://arxiv.org/abs/2611.23428
机构:Univ. of Delaware(特拉华大学); Microsoft Research(微软研究院)
作者:Nischal Subedi, Cencheng Shen, Peng Zhao
英文摘要:We show that the importance of a LoRA adapter's initial input-subspace direction is regime-dependent, and we characterize this dependence in theory and experiment. This refines the recent view that spectral initializers help through update magnitude alone. Direction matters most when labeled data are scarce relative to the representation dimension and the activation subspace used for initialization captures supervised task structure. In this regime, the adapter's row span remains sensitive to its starting point, making task-aligned initialization especially useful. A spiked-covariance perturbation analysis characterizes the finite-sample stability of the estimated subspace. A first-step analysis of LoRA training explains why the subspace's alignment with the task matters and motivates an alignment coefficient $\rho$ that closely tracks gains across classification tasks. We test this account with PivotLoRA, which initializes adapters from activation PCA at prediction-relevant positions and applies one output-preserving orthogonal pivot early in training. In few-shot BERT-base classification, PivotLoRA achieves the best average rank among 13 methods and improves over vanilla LoRA in 29 of 30 settings, even though it starts from a smaller input-factor initialization norm. Additional classification experiments extend the evaluation to 7B and 8B Llama decoders. Classification gains diminish with more labeled data, consistent with the proposed regime dependence. A targeted extension to completion-only reasoning also shows improvements on GSM8K and StrategyQA. These findings identify conditions under which initialization direction matters, with subspace-task alignment offering a low-cost diagnostic before training for classification.
16. DuoCL: Dual-Path Online Continual Learning
DuoCL:双路径在线持续学习
AI 总结:DuoCL是一种双路径在线持续学习框架,通过快速分析路径累积特征统计、慢速路径调整骨干网络,在四个数据集和三个计算预算下,比现有方法平均提升在线准确率9.67个百分点,在分布偏移场景表现更优。
链接:https://arxiv.org/abs/2611.23598
机构:University of Southern California(南加州大学); DEVCOM Army Research Office(DEVCOM陆军研究办公室)
作者:Jebacyril Arockiaraj, Dhruv Parikh, Rajgopal Kannan, Viktor Prasanna
英文摘要: Online continual learning (OCL) requires learning from a data stream whose arrival rate is independent of model training speed. When training cannot keep pace, computationally expensive gradient-based methods update less frequently, limiting adaptation. Analytic methods reduce this overhead, but their frozen backbones cannot adapt representations to changing distributions. We propose DuoCL, a dual-path OCL framework whose fast analytic path accumulates feature statistics from every incoming minibatch while its slow path periodically adapts the backbone. The slow path adjusts its sample count to the available compute budget without interrupting fast-path learning. Feature alignment compensates for drift in the accumulated classifier statistics. Across four datasets and three computational budgets, DuoCL improves online accuracy by an average of 9.67 percentage points over the strongest gradient-based baseline in each setting. DuoCL consistently outperforms analytic learning under distribution shifts, with gains of up to 4.00 percentage points on CIFAR-C, and achieves higher accuracy than prior methods across disjoint class-incremental, domain-incremental, and Si-Blurry settings.
17. Learning through Discernment: when a small language model learns from user feedback on the job, and when it decays
通过辨别力学习:小型语言模型何时从工作中的用户反馈学习,何时发生衰减
AI 总结:本研究探讨设备端小型语言模型从用户反馈学习的规律,发现仅在判定器排除失败、用户可见结果时学习有效,辨别力感知器可短期维持性能,长期因稀缺教训衰减。
链接:https://arxiv.org/abs/2611.23716
机构:Decentralized Science, Inc.(去中心化科学公司); Kasetsart University(เกษตรศาสตร์มหาวิทยาลัย(泰国农业大学))
作者:Sirisilp Kongsilp
英文摘要:Small language models on devices could keep improving by learning, overnight, from their own daily work. Without a true outcome, however, something must decide which attempts are worth learning from, and both the model's own judgment and the user's reaction can be wrong. We study a small model (Qwen3 0.6B and 1.7B) with a LoRA adapter, fine-tuned each night on the attempts a judge accepts, over 127 lives of up to a year on WebShop and $\tau^2$-bench. We compare the true outcome, the user's stated verdict and the model's own judgment with a separate, frozen "feedback sense" that reads the user's reaction, built in three versions. Judging itself, the model improved and then decayed, over a year and whatever its adapter. A sense that took polite give-ups for success collapsed 3 of 5 lives; one built for discernment, which first asks whether the user gave a clear verdict, kept 4 of 5 near the oracle for two weeks, then faded on clean but scarce lessons, to the level of self-judging by day 60. When the user cannot see the outcome ($\tau^2$-bench), the sense read reactions correctly, yet 80% of its lessons were failures the customer had thanked. Across 97 lives, the share of failed attempts among the lessons predicted the outcome (Spearman $\rho$ = -0.81). In our experiments, learning from users held up only where the judge kept failures out and the user could see the outcome; lopsided lessons may also narrow the model.
7. 数据集、基准与评测 | 2 篇
18. GridForge: An Open Physics-Informed Digital Twin and Benchmark Suite for UK 11 kV Underground Distribution Cables
GridForge:面向英国11kV地下配电电缆的开源物理信息数字孪生与基准套件
AI 总结:针对英国11kV地下配电电缆监测领域框架匮乏问题,提出开源物理信息数字孪生与基准套件GridForge,集成热模型、合成数据集、PINN替代模型及五任务基准,为故障诊断预测提供评估支撑。
链接:https://arxiv.org/abs/2611.23241
作者:Lilliane Linnet Musoke
英文摘要:The UK distribution-cable monitoring sector is data-rich but framework-poor: each Distribution Network Operator (DNO) collects megabytes of telemetry per asset per day, but there is no public benchmark dataset, no shared reference model, and no commonly agreed evaluation protocol for benchmarking sectoral, data-intensive models for operational decision support; notably for maintenance planning and prioritisation. We address this gap with GridForge, an open-source physics-informed digital twin and benchmark suite for fault diagnosis and prediction, integrating four building blocks: (i) a verified steady state and transient thermal model based on IEC 60287 and IEC 60853; (ii) a calibrated synthetic dataset of 64 cables (covering 320 cable-years) representing four canonical UK 11 kV thermal archetypes and four condition modes; (iii) a Physics-Informed Neural Network (PINN) surrogate that satisfies the algebraic balance defined by IEC 60287 during training and reaches an RMSE of 0.148 °C on an independent held out set against the reference analytical oracle; and (iv) a five-task benchmark suite that includes three reference baseline models (pure physics, gradient-boosted trees, and the PINN). All numerical parameters are sourced from public standards, the code is licensed under the MIT licence, and the trained PINN converges in only two minutes (as run on the computing platform in Section 10.1), enabling independent verification by DNO engineering and research practitioners. At present only the virtual-sensor task (T4) discriminates between the reference baselines; the other tasks tie or are undefined on this test split, so extending the baselines with task-specific logic is a priority future enhancement. For open validation, the dataset, test sets and models are made available at this https URL
19. Agent Verifiers in Counterfactual Analysis: A Pilot Study Benchmarking Agentic Heterogeneous Treatment Effects
反事实分析中的智能体验证器:智能体异质性处理效应的试点研究基准
AI 总结:本研究提出三层基准协议验证智能体生成协变量的有效性,在11个数据集上对比会话隔离检索与GrokBot工作空间协作体,发现编码器选择会显著影响异质性信号,且时间过滤不足以验证协变量。
链接:https://arxiv.org/abs/2611.23621
机构:Institute for Analytical Sociology, Linköping University(林雪平大学分析社会学研究所); AI and Global Development Lab(人工智能与全球发展实验室); The University of Texas at Austin(德克萨斯大学奥斯汀分校); Uppsala University(乌普萨拉大学); Chalmers University of Technology(查尔姆斯理工大学)
作者:Satiyabooshan Murugaboopathy, Entejar Alam, Adel Daoud, Connor T. Jerzak
英文摘要: Agents can expand the covariate space of randomized experiments by retrieving fast-moving local context missed by slow-changing survey baseline covariates, helping characterize who benefits most from an intervention. Verifying such covariates is difficult: individual treatment effects are unobserved, retrieval leakage can pull post-treatment information into nominally pretreatment summaries, and encoder leakage can inject post-treatment pretraining knowledge into representations even after temporal filtering of inputs. Guided by a two-channel information bound separating summary provenance from encoder weights, we propose a three-layer benchmark protocol: (i) retrieval admissibility via pre-treatment date filtering; (ii) heterogeneity validation scored rank-weighted average treatment effects (RATEs); and (iii) encoder admissibility checked with chronologically vintaged encoders, future-fact probes, and weight perturbations. Across 11 datasets anchored by Uganda's Youth Opportunities Program, we compare session-isolated retrieval (sandboxed, bounded-budget agent runs per study) against a persistent workspace teammate (xAI's GrokBot) that builds one date-verified corpus per study while blinded to outcomes. The workspace teammate yields higher mean RATE ratios in 6/11 datasets for text alone and 7 for combined features, though paired tests show neither workflow universally dominates. Even on fixed retrieved text, encoder choice significantly shifts heterogeneity signal. Chronologically vintaged probes show no clear evidence of weight leakage, but single-record adapter perturbation analyses show that memorized future facts, once present, persist until injected noise degrades model output. Temporal filtering of retrieval is necessary but insufficient: verifying agent-generated covariates requires jointly examining source provenance, out-of-sample treatment-effect signal, and encoder weights.
8. 机器学习应用 | 2 篇
20. TRACE-MAS: Diagnosing and Repairing Collaboration Failures in Multi-Agent Systems
TRACE-MAS:多智能体系统中协作故障的诊断与修复
AI 总结:提出TRACE-MAS细粒度框架,通过学习正常协作模式检测偏差、归因定位根因并最小干预修复,在5个MAS基准上使根因定位准确率提升60.2%,任务恢复增益显著。
链接:https://arxiv.org/abs/2611.23362
机构:Beijing Institute of Technology(北京理工大学); Minzu University of China(中央民族大学); Sun Yat-sen University(中山大学); Shandong University, Weihai(山东大学威海校区)
作者:Zekai Chen, Yihan Sun, Xunkai Li, Xun Wu, Xinmo Jin, Yinlin Zhu, Haodong Lu, Xuaner Chen, Rong-Hua Li
英文摘要:LLM-based multi-agent systems (MAS) rely on not only individual agent behaviors but also the interactions that connect agents, including message exchanges and task dependencies. Existing MAS safeguards mainly perform agent-level anomaly detection, which becomes insufficient when failures originate from agent interactions and detected anomalies do not necessarily reveal their true sources. To address this limitation, we propose \textbf{TRACE-MAS}, a finer-grained framework for diagnosing and repairing MAS failures. TRACE-MAS learns normal collaborative execution patterns from benign trajectories and detects deviations in agent state changes, message transitions, and task dependency evolutions. It further identifies responsible execution elements through source-aware attribution and selects minimal interventions to restore collaboration while preserving task-critical capabilities. Experiments on five MAS benchmarks demonstrate that TRACE-MAS significantly improves root-cause localization accuracy by \textbf{60.2}\% and achieves consistent gains in task recovery over strong MAS safeguards.
21. Conformally Calibrated Adaptive Computation in Neural Operators
神经算子中的保形校准自适应计算
AI 总结:该研究针对神经算子自适应计算未减少推理时间的问题,用保形校准选择傅里叶模式或通道宽度,通过三角不等式包络和直接评分规则约束误差概率,实验表明静态宽度在覆盖率和速度上更优,需结合覆盖率与运行时间评估自适应计算。
链接:https://arxiv.org/abs/2611.23440
机构:Deutsches Elektronen-Synchrotron DESY(德国电子同步加速器研究所); University of L’Aquila(拉奎拉大学)
作者:Abdul Qadir Ibrahim, Martin Burger, Abel Maviano Jonathan
英文摘要:Selecting less computation in a neural operator need not reduce inference time. We study this gap using conformal calibration to choose Fourier modes or channel width per input subject to a fixed error budget. A triangle-inequality envelope bounds all candidates simultaneously; a direct-score rule handles non-monotone candidate errors and, with an input-independent score, calibrates a static baseline under the same marginal guarantee. Under frozen-model and exchangeability assumptions, both rules bound the probability of issuing a prediction outside the budget and abstain when calibration is infeasible. On Burgers and Darcy flow across three training seeds, mode selection reduces active spectral support without a measurable latency reduction, because full-grid transforms and channel mixing dominate the cost. Narrowing channels does reduce Darcy forward cost, but reference-based selection must first compute the dense prediction. An input-only binary width selector avoids that pass and runs at 0.52-0.95 times dense latency; yet static widths calibrated under the same rule are often as fast or faster, and on a separately generated 1,000-example test set they generally achieve higher coverage, while the selector falls below its 90% target in more than half of the settings. Adaptive computation in neural operators should therefore be judged by achieved coverage and complete runtime against a matched static comparator.
9. 其他/综合机器学习 | 19 篇
22. Biologically-Inspired Spike Encoding and Optimization for Spiking Neural Networks
受生物启发的脉冲编码与脉冲神经网络优化
AI 总结:该研究结合生物启发脉冲编码与Rouser自适应阈值代理梯度、K-FAC二阶优化,在MNIST等数据集上验证了生物启发编码器可提升SNN精度、缩小与非脉冲模型的差距。
链接:https://arxiv.org/abs/2611.23242
作者:Ayaan Qayyum, Bruce Yi Bu, Zicong Li, Jingfeng Zhou
英文摘要:Spiking Neural Networks (SNNs) offer theoretical energy-efficiency advantages over conventional deep networks, but realizing these advantages on vision tasks requires sparse spike representations that naive rate-coding methods fail to provide. We combine biologically motivated spike-encoding schemes with two training improvements: Rouser adaptive-threshold surrogate gradients and Kronecker-Factored Approximate Curvature (K-FAC) second-order optimization. The spike encoding schemes experimented with are rate coding, latency coding, DVS-style delta modulation, and Difference-of-Gaussians (DoG) filtering. Experiments on MNIST and Fashion-MNIST demonstrate that biologically inspired encoders yield the largest accuracy gains in capacity-constrained regimes and serve as an effective parameter-efficiency lever. DoG and delta modulation encoders produce significantly sparser spike trains than rate coding. K-FAC yields modest but consistent accuracy improvements over Adam-trained baselines, and Rouser's learnable per-neuron thresholds improve Fashion-MNIST accuracy from 87.37% to 88.13% by enabling homeostatic firing-rate regulation. Biologically grounded pre-processing methods can help close the accuracy gap between SNNs and non-spiking baselines without increasing model size.
23. Goemans's Unsplittable-Flow Conjecture: The Anatomy of AI-Assisted Counterexample Discovery
Goemans的不可拆分流猜想:AI辅助反例发现的剖析
AI 总结:本文开发正向反例构建流水线,结合ChatGPT验证其可迁移性,解释了Goemans不可拆分流猜想的7顶点反例的成因及AI辅助搜索的优势。
链接:https://arxiv.org/abs/2611.23244
机构:The University of Hong Kong(香港大学); Central University of Finance and Economics(中央财经大学); Tsinghua University(清华大学)
作者:Jingwei Ge, Na Xie, Li Li, Jiayang Li
英文摘要:Goemans conjectured that any fractional single-source flow could be converted into an unsplittable flow without increasing total cost and while increasing any arc load by at most the largest demand. Recently, Dmitry Rybin announced a seven-vertex counterexample found through an interaction with ChatGPT, which disproved this long-standing conjecture. However, the interaction did not reveal why this particular topology and its demand, fractional-flow, and cost choices work together, whether the example belongs to a broader family, or which structural features determine where counterexamples can occur. It also left unclear why the AI-assisted search succeeded where earlier human efforts had not. In this paper, we develop a forward counterexample construction pipeline. It starts from an arborescence on which failure is impossible and adds terminal-entering shortcut arcs. The resulting load constraints define a finite set of admissible route choices; their convex hull, the conflict polytope, yields exact conditions for demands, fractional flows, and costs. Starting from a simple arborescence, the pipeline selects Rybin's topology and characterizes all counterexamples it supports. Experiments further demonstrate the pipeline's transferability: when instructed to follow it while varying the initial arborescence and shortcut placement, ChatGPT produced counterexamples on topologies genuinely different from Rybin's and found valid constructions starting from 93 other rooted arborescence shapes. The theory also explains why the original example was difficult to discover through blind enumeration and suggests that Rybin's interaction lies between blind enumeration and a complete theory-guided construction.
24. Response-Relevant Information Is Not Sufficient for Neural Training-State Equivalence
与响应相关的信息不足以实现神经网络训练状态等价
AI 总结:该研究证明与响应相关的信息不足以实现神经网络训练状态等价,通过实验验证了训练状态可测量,发现15个描述符的响应预测优势无法与安慰剂区分,表明信息组织无需成对几何。
链接:https://arxiv.org/abs/2611.23245
机构:H&K Research Studio, Clevix LLC(H&K研究工作室,Clevix有限责任公司)
作者:Truong Xuan Khanh
英文摘要:Response-relevant information is not sufficient evidence that two neural networks are in the same training state. We define training-state equivalence operationally: two checkpoints are equivalent, relative to an intervention family and horizon, if they respond alike when training is perturbed and continues. On fresh runs of a one-layer transformer learning modular addition, response to a weight-decay pulse is highly reproducible relative to between-checkpoint differences (rho_state = 0.934 at 500 steps), establishing the target as measurable. Fifteen descriptors of weight spectra, representation geometry and optimiser geometry carry within-run response-relevant information beyond weight norm and loss on a development dataset, predicting held-out response deviation across seed blocks. But their apparent 16.1% advantage at matching checkpoints by future response does not separate from a conditional placebo preserving each descriptor's fitted dependence on the conventional observables, and a calibrated positive control makes simple insensitivity an unlikely explanation. Information a decoder can extract need not be organised in the pairwise geometry that similarity judgments require.
25. Chebyshev Polynomial Zonotope Abstractions for Certified Reachability of Learning-Enabled Systems
用于可学习系统的可达性验证的切比雪夫多项式 zonotope( zonotope 为 zonotope 正式名称,保留英文)抽象
AI 总结:该研究针对可学习系统的可达性验证问题,提出切比雪夫多项式 zonotope 抽象方法,解决了泰勒展开覆盖范围受限的问题,在闭环系统和 MNIST 分类器上验证了其有效性。
链接:https://arxiv.org/abs/2611.23246
作者:Peng Xie, Amr Alanwar
英文摘要:Nearly all current methods for computing reachable sets of nonlinear dynamics propagate them with truncated Taylor expansions plus rigorous remainders. The expansion is pointwise: once its argument is a whole set rather than a point, one polynomial must stay accurate across that set, and it reaches only as far as its disc of convergence. The limit binds hardest on the rational terms and sigmoid gates of modern controllers: smooth as these look on the real line, in the complex plane they blow up at points just off the real axis, closer as a gate sharpens, and those points cap the set width a Taylor expansion can cover, most tightly on the switching surface where the controller decides. We prove a dichotomy: no Taylor degree certifies sets wider than that cap, while a Chebyshev abstraction of equal degree, anchored to the whole set in the same polynomial-zonotope pipeline, has no cap and gains width at a geometric rate in degree. Measured walls match the formulas to between 89 and 94 percent. We give closed-form rigorous remainders, among them the first polynomial softmax transformer; existing sound treatments are linear relaxations. On closed loops, certificates survive where the Taylor ones diverge, and specifications flip from unknown to proven; on trained classifiers up to real MNIST digits, the Chebyshev frontier certifies input territory the Taylor basis surrenders. Every certified claim passed large Monte-Carlo harnesses with zero violations, and an applicability map states in advance where the basis provably cannot matter.
26. Budgeted Proper Loss Design for Uncertain Decision Thresholds
面向不确定决策阈值的预算约束恰当损失设计
AI 总结:该研究针对有限指定族的不确定决策阈值,设计了带预算约束的恰当损失,推导了最小化决策遗憾的最优权重,经实验验证其性能优于均匀和平均密度权重。
链接:https://arxiv.org/abs/2611.23247
机构:International Institute of Information Technology Bangalore(班加罗尔国际信息技术学院)
作者:Ankit Sharma (International Institute of Information Technology Bangalore)
英文摘要: A binary probability estimate may be used by several decision makers with different error costs. Proper scoring rules can emphasize selected probability thresholds, but a single average threshold distribution need not give a good worst-case regret guarantee. We study the choice of a proper loss when the threshold distribution belongs to a finite specified family. Among integrable loss weights with a positive pointwise floor and a fixed total mass, we derive the weight that minimizes the sharp, distribution-free multiplier from surrogate regret to threshold-averaged decision regret. The solution clips a rescaled upper envelope of the threshold densities at the prescribed floor; its normalization is found by a one-dimensional root search. We give proofs of sharpness, optimality, and stability under density misspecification, as well as a limitation for atomic threshold laws. An exact histogram implementation and two synthetic experiments across 20 seeds verify the construction. The optimized multiplier improves over uniform and average-density weights, while fitted-model performance does not improve uniformly. The result is a loss-design guarantee under an explicit budget, rather than a general claim of predictive superiority.
27. Optimize the Cob, Then the Kernel: Optimizing Beam Search for Generative Recommendation Inference
先优化波束,再优化内核:针对生成式推荐推理的束搜索优化
AI 总结:本研究针对生成式推荐推理的束搜索优化,采用 Tree Attention 等技术,在不使用自定义内核的情况下,将昇腾 NPU 上的端到端延迟较 vLLM 降低最多 25 倍,验证了生成流水线整体优化的有效性。
链接:https://arxiv.org/abs/2611.23339
机构:Huawei Technologies Co., Ltd.(华为技术有限公司)
作者:Shing Wai Pun, Kai Wu, Pengfei Xia, Hui Zang, Wei Guo, Yong Liu
英文摘要:Generative recommendation (GR) inference differs substantially from conventional LLM serving, featuring long input sequences, wide beam search, and only a few fixed output tokens. Existing LLM serving engines such as vLLM process beams as batched independent sequences, causing redundant KV cache accesses over the shared prompt prefix. Furthermore, vLLM executes each beam search generation step as a separate engine invocation, incurring host-side beam processing overhead between decoding steps and substantial runtime KV block management in PagedAttention. Using Tree Attention, we concatenate beams along the sequence dimension to eliminate redundant KV accesses, and further optimize execution through pre-generated partial-attention masks, static KV cache allocation, loop-unrolled generation dispatch, TorchAir graph compilation, automatic operator fusion, and vocabulary-constrained decoding. Without the use of custom kernels, our approach reduces end-to-end latency by up to 25x over vLLM on Ascend NPUs, and achieves generation latency comparable to a SOTA solution using custom kernels, showing that the generation pipeline should be optimized holistically before resorting to custom kernel development.
28. Confidence-Based Materials Data Quality Assessment via Domain Knowledge and Graph-Structured Learning
基于置信度的材料数据质量评估:结合领域知识与图结构学习
AI 总结:该研究提出结合领域知识与图结构学习的置信度材料数据质量评估框架,经多组基准实验验证可显著提升数据质量评估及模型预测性能。
链接:https://arxiv.org/abs/2611.23342
机构:Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心); University of Chinese Academy of Sciences(中国科学院大学); School of Materials and New Energy, Ningxia University(宁夏大学材料与新能源学院)
作者:Sihan Liaing, Ji Zhang, Kehan Wang, Zihao Gao, Wei Ma, Yangang Wang, Zongguo Wang
英文摘要:The rapid development of materials machine learning relies on large-scale, heterogeneous datasets, yet model reliability is often compromised by imperfect data from diverse experiments, simulations, and database integration. Real-world materials databases may contain measurement errors, failed calculations, missing or duplicate records, and hidden violations of physicochemical constraints. Such problems are difficult to identify because corrupted samples may remain statistically plausible rather than appearing as explicit outliers. In this paper, we propose a confidence-based materials data quality assessment framework that integrates domain knowledge with graph-structured learning. Data quality is formulated as a continuous confidence estimation problem rather than a binary anomaly identification task, enabling sample-level assessment and historical-reference-based batch comparison. A nine-dimensional feature-quality prior and duplicate-aware sample initialization are calibrated using materials domain rules and statistical evidence. Confidence is further refined through sample-feature bipartite graph propagation and weakly supervised graph attention, while a Memory-GAT module provides historical reference scoring. Experiments on 23 ODDS benchmark datasets show that the generic module achieves an average AUC-ROC of 0.866. In five repeated mixed-contamination experiments on mp\_20, rule calibration improves HistGradientBoostingRegressor test $R^2$ from $0.538\pm0.008$ to $0.616\pm0.014$. Graph refinement increases average precision from $0.943\pm0.004$ to 0.953\pm0.004$, while the rule-calibrated configuration has the highest mean test $R^2$ among the evaluated screening configurations. Five repeated MACE subset experiments further show an increase in $R^2$ from $0.590\pm0.053$ to $0.880\pm0.027$ after rule-based screening.
29. Implementing Binary Transformers with Approximate Memories with Permutation Invariance Enabled Selective (PIES) Protection
采用近似存储器实现二值Transformer的排列不变性启用选择性(PIES)保护
AI 总结:本文以BERT为案例评估二值Transformer的可靠性,提出PIES方案保护二值权重,可在10%误码率下恢复性能损失,开销低于传统方案,证实近似存储器运行二值Transformer的可行性。
链接:https://arxiv.org/abs/2611.23358
作者:Zhen Gao, Xiao Yin, Kexin Liang, Pedro Reviriego, Shanshan Liu, Fabrizio Lombardi
英文摘要:Quantization is an effective technique to reduce memory storage, computation complexity and power for Transformers, and the binarization of the weights is important for meeting these requirements. Approximate memory can further reduce the power for memory, but it also introduces errors. Current research for binary Transformers focuses on task performance, but the model dependable operation against errors on the memory has not been well studied. In this paper, we first evaluate the dependability of binary Transformers with the Bidirectional Encoder Representations from Transformers (BERT) as a case study. A large accuracy loss occurs only at high Bit Error Rates (e.g. BER = 5% or 10%). Then we propose a novel Permutation Invariance Enabled Selective (PIES) scheme to protect the binary weights at very low overhead. This scheme exploits the invariance of Transformers to permutations in the rows and columns to group the critical weights and perform selective protection on those weights. Simulation results show that PIES can recover most of the performance loss caused by bit errors at BERs as high as 10%, at an overhead significantly lower than traditional error correction schemes. These results confirm the feasibility of running binary Transformers using approximate memory with aggressive voltage scaling on resource-limited low power edge devices. The code for PIES is released on github ( this https URL ).
30. Incremental Roseland: Batch-wise Landmark Diffusion via Kernelized Sequential Karhunen--Loève Update
增量Roseland:通过核化序列Karhunen-Loève更新实现批量地标扩散
AI 总结:提出增量Roseland(iRoseland),通过核化序列Karhunen-Loève更新实现批量地标扩散,仅需单次遍历数据,在长数据流和漂移数据上精度优于Roseland。
链接:https://arxiv.org/abs/2611.23414
作者:Jeanie Schreiber
英文摘要:Landmark diffusion (Roseland) computes a diffusion-map-style spectral embedding from the singular value decomposition of a degree-normalized data-to-landmark kernel matrix, at a cost far below that of full diffusion maps. It assumes, however, that all data are available at once. We introduce incremental Roseland (iRoseland), which casts the landmark affinity as a row-growing matrix whose SVD can be updated with a kernelized Sequential Karhunen--Loève (SKL) scheme. Degre correction is handled by a first order expansion about a reference mean kernel row and so that the landmark-side eigenbasis may be recovered from a single landmark-by-landmark eigendecomposition at each step. The presented method requires only a single pass over the data and runs in bounded-memory with state independent of the number of points processed. A forgetting factor lets the method track drifting distributions, and a sample-size-invariant embedding keeps outputs comparable across time. Experiments show agreement with Roseland to round-off on stationary data, and accuracy that exceeds equal-memory Roseland by an order of magnitude on long streams. On drifting data, we observe large gains from forgetting with a window matched to the drift.
31. FACT: Fixed-Budget Allocation and Cross-Step Training for Speculative Decoding
FACT:用于推测解码的固定预算分配与跨步训练
AI 总结:本研究提出 FACT 框架,发现置信度引导的草稿候选分配可显著提升推测解码加速比,且训练与分配需结合执行条件联合评估。
链接:https://arxiv.org/abs/2611.23463
机构:American University of Beirut(贝鲁特美国大学)
作者:Hadi Fares, Mayssa Hajj Hassan, Ali Salman, Ammar Mohanna
英文摘要:Speculative decoding accelerates language-model generation by verifying multiple draft tokens in a single target-model pass. However, better draft predictions and longer accepted continuations do not necessarily produce faster generation. To examine this gap, we present FACT (Fixed-Budget Allocation and Cross-Step Training), an experimental framework for studying how drafter training, candidate allocation, and execution conditions jointly affect acceptance and latency. Using a lightweight feature-prediction drafter with a frozen Llama-3-8B-Instruct target under greedy decoding, we first examine how training translates into accepted tokens. Backpropagating through predicted-feature rollouts with greater weight on early steps improves acceptance by 15-24% over uniformly weighted detached training, yet average rollout proxy cross-entropy does not reliably rank drafters by acceptance. Beyond prediction quality, the placement of draft candidates also matters: with a fixed 256-node budget and matched per-depth widths, replacing static allocation with confidence-guided allocation increases speedup over autoregressive decoding from $1.46\times$ to $2.02\times$ on HumanEval and from $1.31\times$ to $1.75\times$ on MT-Bench. This allocation benefit extends to an independently trained drafter, but stronger training does not consistently amplify it, showing that the two improvements do not necessarily reinforce each other. Even these speed gains depend on execution conditions: changing only host-thread settings can nearly eliminate speedup without changing acceptance. Together, these findings show why training and allocation must be evaluated jointly using both acceptance and end-to-end latency under controlled execution conditions.
32. Stability of Parallel Transport Convolution under Riemannian Metric Perturbations
黎曼度量扰动下平行传输卷积的稳定性
AI 总结:本文研究黎曼度量扰动下平行传输卷积的稳定性,通过微分几何与分析方法推导相关扰动估计,解决割迹难点,建立卷积输出对度量的连续依赖性,连接几何扰动理论与深度学习卷积分析。
链接:https://arxiv.org/abs/2611.23543
机构:University of New Mexico(新墨西哥大学)
作者:Hongnian Huang, Andrew Stump
英文摘要:Geometric convolutions on Riemannian manifolds depend on the geometry of the underlying domain, making stability under metric perturbations a fundamental question in geometric deep learning. This paper studies this question for parallel transport convolution through methods from differential geometry and analysis. On a fixed compact manifold, we establish that, for a continuous input signal and a continuous reference kernel supported in a sufficiently small normal neighborhood, the convolution output depends continuously in $L^2$ on the Riemannian metric in the $C^2$-topology, under the specified localization and transport-path conventions. The analysis develops perturbation estimates for geodesics, parallel transport, Jacobi fields, and exponential maps, and uses these estimates to compare the transported kernels. A central difficulty is the cut locus, which obstructs uniform comparison of the transport construction over the entire manifold. We address this difficulty by combining uniform estimates away from the cut locus with integral bounds on neighborhoods of arbitrarily small volume, while also controlling the change in the Riemannian volume measure. The resulting qualitative stability theorem connects perturbation theory for Riemannian geometric constructions with the analysis of spatial convolution operators in geometric deep learning.
33. Safe to Omit, Worth Omitting? Keeping the Answer and Cutting Latency When an LLM Agent Skips Another's Message
可安全省略,值得省略?当大语言模型智能体跳过另一个智能体的消息时保留答案并降低延迟
AI 总结:本研究针对多智能体系统中接收方智能体等待辅助智能体消息导致延迟的问题,提出基于置信度和有限样本检验的跳过机制,在保证答案变化率≤5%的前提下,可有效降低延迟并保留大部分性能增益。
链接:https://arxiv.org/abs/2611.23570
机构:University of Houston(休斯顿大学); Argonne National Laboratory(阿贡国家实验室); Oregon State University(俄勒冈州立大学)
作者:Xinyang Li, Chih-Hsuan Yang, Xiaolong Ma, Anjir Ahmed Chowdhury, Vikram Vasudevan, Rajeev Thakur, Feng Yan
英文摘要: In multi-agent systems, a receiver agent often waits for a helper agent's message (text or its latent KV cache), which can improve performance but adds latency. We study when a receiver agent can skip the message safely (the final answer rarely changes) and beneficially (the time saved exceeds the cost of deciding). Our mechanism reads the receiver agent's confidence without the message and uses a finite-sample test to certify a threshold at which, with high probability, at most 5% of skipped answers change; if none passes, the system keeps communicating. We test it on OpenBookQA, ARC-Challenge, and MMLU-Pro with three Qwen model pairs, on cross-family agents, and on SQuAD and GSM8K. Four insights emerge. First, oracle headroom is weak evidence that messages help: control inputs without answer-specific content, matched to change answers as often as real messages, reproduce a median 76% of the oracle's gain. Second, whether a message can be skipped depends on how often and how predictably it alters the answer, not on its accuracy; every certified KV-cache path is less accurate than the receiver agent alone. Third, where text messages help, skipping keeps most of their gain: on unseen questions in the four such settings, the policies skip 59 to 80% and keep an estimated 76 to 95% of the gain. In two prospective tests with all rules fixed in advance, our mechanism skips a three-agent system's verifier on 39.9% of sealed questions, keeping 12.55 of its 12.80-point gain, and a 32B helper on 68.4% of held-out questions, keeping its whole gain. Fourth, safety does not determine efficiency: at batch size one, skipping text saves hundreds of milliseconds per query and skipping KV cache far less. Certification extends to SQuAD but not to GSM8K. In eleven tests on unseen questions, every certified policy we could test kept its change rate's 95% upper bound below 5% under our answer parsers.
34. Entropy-Regularized Integrated Gradients for Stable Feature Attribution
用于稳定特征归因的熵正则化积分梯度
AI 总结:提出ERIG方法,通过熵正则化加权提升归因稳定性,在11种骨干网络的两个数据集上,较IG实现47倍平均稳定性提升,定位性能提升24%,计算成本可忽略。
链接:https://arxiv.org/abs/2611.23600
机构:Florida International University(佛罗里达国际大学); University of Florida(佛罗里达大学)
作者:Rukmangadh Sai Myana, Sumit Kumar Jha, Yanzhao Wu
英文摘要:Path-based attribution methods like Integrated Gradients (IG) are widely used to interpret neural networks, yet imperceptible input perturbations can drastically alter their attribution maps while leaving model predictions unchanged. We introduce Entropy-Regularized Integrated Gradients (ERIG), a path-based attribution method that intrinsically attenuates gradient irregularities along the integration path using maximum-entropy softmax weighting with temperature parameter $\tau$. We quantify the effect of the entropy-regularized weighting on attribution stability by using the Lipschitz properties of the model and its gradients. We decompose the attribution change under an input perturbation into a model-response term, whose bound is $\tau$-independent, and a weight-variation term, whose bound decreases at rate $\mathcal{O}(1/(2\tau))$. Their ratio $R(\tau)$ characterizes the trade-off between gradient information and attribution stability. We further add a new dimension to attribution evaluation by adapting classical noise estimators into two metrics, LINV-C and LINV-P, that quantify attribution noise. Across eleven CNN and Transformer backbones on ImageNet and Oxford-IIIT Pet datasets, our experiments show that, relative to the next-best method, ERIG remains comparable on ranking-based fidelity metrics while improving localization by approximately 24% and attribution stability by approximately 47-fold on average, reaching up to four orders of magnitude improvement over IG, all at negligible additional computational cost.
35. Label-Free Role-Aware Segmentation of Classroom Recordings: Recovering the Teacher from Transferable Structure
无标签的课堂录音角色感知分割:从可迁移结构中恢复教师角色
AI 总结:本研究提出无标签的教师-学生分割流程,利用可迁移结构在课堂录音中恢复教师角色,在多语言多教师数据集上F1值达0.81/0.87,性能优于基线,且适配移动设备,可实现隐私保护部署。
链接:https://arxiv.org/abs/2611.23609
机构:Hector Research Institute of Education Sciences and Psychology, University of Tübingen(图宾根大学赫克托教育科学与心理学研究所); Technical University of Munich(慕尼黑工业大学); Tübingen AI Center, University of Tübingen(图宾根大学图宾根人工智能中心)
作者:Nitin Jain, Tim Fütterer, Babette Bühler, Çağatay Yıldız
英文摘要:How much the teacher talks and when are among the most informative and costly-to-measure signals of teaching. Yet, classroom audio is among the most sensitive data an AI system can process: recordings capture minors and fall under GDPR, preventing raw audio from leaving the recording device. We present a teacher-student segmentation pipeline designed to meet exactly this constraint: label-free at inference, running on a recording device, and requiring no per-session calibration. The pipeline chains a lightweight voice activity detector, compactly pretrained speaker embeddings, agglomerative clustering, and a small logistic regression that assigns the teacher role based on session-relative structure rather than voice identity. We show that our structural cue transfers across classrooms, languages, and acoustic conditions. In leave-one-teacher-out cross-validation on 292 recordings from 63 teachers across English and German corpora, our pipeline achieves teacher F1 of 0.81 and 0.87, respectively, outperforming both enrollment-based baselines and a 30-second supervised enrollment ceiling. On a commodity smartphone, its performance matches pyannote, a strong neural diarization tool, while running 4.8x faster at comparable peak memory at a real-time factor of ~0.18. We also find that transcribing filtered audio only marginally increases teacher's word error rate from $0.26$ to 0.28. Residual failures concentrate where teacher and student voices are not acoustically separable. However, we show how to flag these sessions label-free at inference so that they can be routed to human review, enabling selective, privacy-preserving deployment.
36. Error accumulation in reverse diffusion with an imperfect score: beyond path-space analyses
带不完善得分的反向扩散中的误差积累:超越路径空间分析
AI 总结:本文针对带不完善得分的反向扩散采样,通过规避路径空间分析,在p满足庞加莱不等式时缓解了误差积累,且该框架适用于任意分布p,还证明扩散采样器对给定庞加莱常数界的p几乎达到最优总变差误差。
链接:https://arxiv.org/abs/2611.23617
机构:CMU(卡内基梅隆大学); MIT(麻省理工学院); UC Berkeley(加州大学伯克利分校)
作者:George Giapitzakis, Ankur Moitra, Andrej Risteski, Dhruv Rohatgi
英文摘要:Diffusion modeling is a popular method of sampling from a complex, high-dimensional distribution $p$ using learned approximations of its (noised) score functions. Generating a single sample requires simulating the reverse diffusion process, which requires many queries to the learned scores. Thus, a priori, the learning errors can easily compound. Indeed, in existing theoretical analyses, the sampling error (as measured in total variation distance to $p$) accumulates polynomially with the horizon of the stochastic process. This is a consequence of bounding the error of the output law by the error of the law of the entire reverse diffusion path. In this paper, we demonstrate that by circumventing the "path-space" analysis, the error accumulation of the diffusion sampler can be mitigated when $p$ satisfies a Poincaré inequality. Moreover, we achieve this result as a special case of a broader framework that applies to any distribution $p$, but relaxes the error metric from total variation distance to a weaker metric capturing all sample statistics that do not "witness" the multimodality of $p$. We then zoom out from analyzing the diffusion sampler to the information-theoretic question: given a learned score with some error bound, how accurately can we identify $p$? We show that, for any given bound on the Poincaré constant of $p$, the diffusion sampler already nearly achieves optimal total variation error.
37. EEG2MCU: Sensing-to-Execution Co-Design for Wearable EEG Inference
EEG2MCU:面向可穿戴脑电推理的感知到执行协同设计
AI 总结:EEG2MCU 是面向可穿戴脑电推理的感知到执行协同设计框架,通过任务感知导联选择、INT8 区域生成优化及内存布局改进,大幅降低 Cortex-M7 MCU 的 SRAM、延迟与能耗,同时保留 94%-96% 的全导联准确率。
链接:https://arxiv.org/abs/2611.23619
机构:Case Western Reserve University(凯斯西储大学); Purdue University(普渡大学)
作者:Shoma Yukawa, Meghna Roychowdhury, Arnab Sanyal, Chengwei Zhou, Shreyas Sen, Gourav Datta
英文摘要:Wearable EEG inference is constrained not only by model size, but also by the channel-dependent sensing front end that must process high-dimensional inputs before compact downstream computation. We present EEG2MCU, a sensing-to-execution co-design framework that treats electrode count as a hardware design variable through task-aware montage selection. EEG2MCU retains a compact time-frequency representation and generates only the INT8 regions required by each first-layer tile, avoiding full input materialization. Halo reuse and access-aware placement across Flash, SRAM, and tightly coupled memory further reduce redundant generation and data movement. On a Cortex-M7 MCU, EEG2MCU reduces peak SRAM by 11.38x relative to the baseline, including a 1.71x reduction from the 62-to-19 electrode montage, while reducing latency by 2.57x and energy by 2.48x. It retains 94-96% of full-montage accuracy, demonstrating practical high-dimensional EEG inference under tight embedded-resource constraints.
38. Simpler Tiny Recursive Models
更简单的微型递归模型
AI 总结:提出简化版微型递归模型STRM,以单状态统一更新替代TRM的复杂递归,在数独等多类谜题任务上较TRM取得性能提升,且训练速度更快。
链接:https://arxiv.org/abs/2611.23677
机构:Heinrich Heine University Düsseldorf(杜塞尔多夫海因里希·海涅大学)
作者:Torben Glass, Zhengxi Zhang, Paul Swoboda
英文摘要:Small models that execute deep looped computational graphs have shown great experimental results on puzzle-like problems like Sudoku, finding shortest paths through mazes, etc. The most well-known one is TRM (tiny recursive model), a simplification of HRM (hierarchical reasoning model). However, the underlying recursion is complicated and involves a high-level and a low-level state, a nested loop recursion, and the network calls with different input and output signatures depending on where we are in the loops. These mechanisms are needed to avoid memorization and overfitting. We propose STRM, a simplified design with a single state and a uniform update. STRM does not sacrifice generalization, improves training speed and final performance. Our key architectural choices that allow our simpler recursion to work are exponential moving updates on the states with varying rates that are jittered during training and readout of the solution on slow-updating channels only. We test STRM on Sudoku-Extreme, PPBench and Maze-Hard with the same data, parameters and compute as TRM: we improve over TRM by $3.8$ points on Sudoku-Extreme and $8.4$ points on PPBench and match it on Maze-Hard. On ARC-AGI-1 and ARC-AGI-2, STRM improves over the published TRM results by $5.4$ and $0.5$ points. We will release our code upon acceptance of the paper.
39. Variable Length Diffuse Everything: Arbitrary Length Generative Modeling on Arbitrary State Spaces
可变长度扩散一切:任意状态空间上的任意长度生成建模
AI 总结:该研究针对现有生成模型难以处理任意状态空间可变长度多模态数据的问题,提出VL-DE框架,通过插入机制处理可变长度并开发高阶采样器,在布局和分子生成任务中验证了方法的有效性。
链接:https://arxiv.org/abs/2611.23684
机构:Georgia Institute of Technology(佐治亚理工学院); University at Albany, SUNY(纽约州立大学奥尔巴尼分校)
作者:Kevin Rojas, Felix X.-F. Ye, Molei Tao
英文摘要:Diffusion and flow-based generative models have achieved remarkable results across diverse applications, but most assume data of fixed-dimension/length. Meanwhile, real-world problems such as layout generation often involve variable-length, multimodal data, such as continuous bounding box coordinates paired with discrete types. Existing methods typically address variable length by padding data to a fixed size or by introducing specialized objectives to model lengths explicitly, adding complexity and limiting generality. We propose Variable Length Diffuse Everything (VL-DE), a simple and general framework for variable-length multimodal generation on arbitrary state spaces. Instead of padding, VL-DE handles variable length through an insertion-based mechanism grounded in a principled theoretical framework, yielding a tractable training objective. In addition, by utilizing the fact that VL-DE is based on a generator with an additive form, we develop a higher-order sampler by appropriately handling the time dependence. Extensive experiments on layout and molecule generation demonstrate the effectiveness of our approach.
40. HypoLoop: Revising Weight-Editing Plans from Scientific Feedback
HypoLoop:基于科学反馈修正权重编辑方案
AI 总结:HypoLoop是一类将权重编辑选择与实验反馈关联的原生权重编辑方法,经22项科学任务验证,可有效降低预测误差,修正方案能提升空间预测效果。
链接:https://arxiv.org/abs/2611.23718
机构:Hong Kong Institute of Science and Innovation(香港科学创新研究院); Jinan University(暨南大学); University of Macau(澳门大学); Sichuan University(四川大学); The University of British Columbia(不列颠哥伦比亚大学); University of Luxembourg(卢森堡大学); Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所); University of Rochester(罗切斯特大学); Westlake University(西湖大学)
作者:Mengran Li, Xichen Yan, Bo Li, Chengyang Zhang, Jinfeng Xu, Zheng Lin, Zelin Zang, Zhen Lei, Jiebo Luo, Victor C. M. Leung, Stan Z. Li
英文摘要: Scientific experiments continually reveal prediction errors. Effective updates depend on which parameters change and which errors drive the correction. We introduce HypoLoop, a family of native weight-editing methods that connects these choices to experimental feedback. Fixed, numerically adaptive, and LLM-guided policies produce editing plans; numerical solvers compute weight patches, and internal validation selects the deployed predictor. Successive observations and validation records support revisions to editable locations and fitting rules. Experiments cover 22 scientific tasks and both DeepSeek and Claude. On Burgers, reallocating a matched parameter budget reduces error by 58.80% and 47.72% relative to fixed locations. On DIODE, positive-residual weighting reduces absolute relative error (AbsRel) by 13.35% in internal cross-validation, with the same 33 editable coordinates. Revising the complete plan across rounds lowers final AbsRel by 10.59% relative to keeping the initial plan fixed. SpaceNet7 and Make3D connect accepted edits to improved spatial predictions. These results show how experimental evidence can shape the update problem itself. Code: this https URL.
因公众号篇幅限制,更多论文请扫码查看