跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+64已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 21:56各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 01:01 — 2026-11-17 01:01(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 21:56库内论文最新更新时间:2026-11-14 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

23,827 已收录论文19,941 AI 相关6,922 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2608.25005

The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure

Kaiqiao Han, Katarzyna Pruś, Mark Steedman, Yizhou Sun

原文摘要

Recent work uses an NLI benchmark of the imperfective paradox to argue that large language models exhibit a Teleological Bias and Calibration Crisis. We identify three validity concerns in benchmark construction, including aspectual reduction, semantic bias, and relation bias. Under a strict NLI standard, 76% of the Group A instances do not explicitly rule out culmination; in native-speaker annotation, 38% of Group A and 29% of Group C examples permit an alternative interpretation. To better isolate the semantic contrast, we construct Lexically Matched Minimal Pairs. Moreover, by formulating event-semantic NLI as a multi-step reasoning problem, we evaluate intermediate semantic judgments and use oracle-guided settings. We find that incorrect NLI entailment does not fully support teleological bias. Prompting often changes final NLI decisions without reliably improving the underlying semantic judgments, offering a possible explanation for the Calibration Crisis.

cs.CL · cs.LG

新论文 · v1arXiv:2611.11009

PIA: Agentic Physics-Informed Runtime Anomaly Detection

Ali Mohammadi Ruzbahani, Abbas Yazdinejad, Hadis Karimipour

原文摘要

Runtime anomaly detectors for cyber-physical systems are either learned as black boxes from normal data, which miss stealthy manipulations that keep every signal inside its normal range, or derived by hand from physical models, which requires expert effort for every plant. We introduce physicsinformed agents (PIA), in which a large language model agent writes the detector itself as a set of physical residuals, such as pump characteristics, tank mass balances, and controller logic, and refines every candidate against normal operating data through an evaluation workbench before deployment. The result is a compact, human-readable detector that runs in milliseconds and names the component behind each alarm. On the BATADAL water distribution attack benchmark, PIA with Claude Opus 5.5 reaches an F1 of 0.878 on the test attacks against 0.504 for the strongest of six statistical and deep baselines, keeps detecting attacks concealed by replayed and offset sensor readings, and attributes every detected test attack to the attacked component. Ablations show that testing hypotheses against data is decisive: agents that write residuals from the plant description alone lose up to 0.28 F1, whereas agents that see only anonymized signals recover most of the physical structure.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.24405

Generative OOD-regularized Model-based Policy Optimization

Aysin Tumay, Jiahe Huang, Elise Jortberg, Rose Yu

原文摘要

We study sequential decision-making with offline reinforcement learning (RL). Traditional offline RL policies may result in out-of-distribution (OOD) actions when training relies only on sparse offline representations. To ensure safe offline policies in a sparse state-action space, we explore how density estimation models can be integrated into model-based RL methods to avoid OOD regions. Generative models are capable of explicitly modeling the density in sparse state-action spaces. Building on this, we introduce Generative OOD-regularized Model-based Policy Optimization (GORMPO), a density-regularized offline RL algorithm that uses generative density modeling to restrict policy updates to high-density areas of the dataset. Furthermore, we examine whether better OOD detection corresponds to better model-based offline policies. We compare (1) the OOD detection capabilities of various density estimators and (2) their performance within the GORMPO framework on a real-world medical dataset and sparse offline RL datasets. We provide theoretical guarantees bounding GORMPO's performance gap in terms of density estimation error, ensuring near-optimal policies under imperfect density estimates. Empirically, GORMPO remains competitive in reward and improves clinical metrics compared to state-of-the-art clinical RL models, and outperforms state-of-the-art offline RL models in offline RL benchmarks. Our empirical findings show that better OOD detection generally results in improved policies in environments with stable dynamics, while conservative penalties with poor density estimation are favored when dynamics are uncertain. Code, checkpoints, sparse, and OOD D4RL datasets are available at https://github.com/Rose-STL-Lab/GORMPO.

cs.LG · cs.AI

新论文 · v1arXiv:2611.11007

Efficient 3D plant segmentation through multiscale graph learning and optimized geometric processing

Jesus Ivan Ruiz-Martinez, Andres Mendez-Vazquez, Eduardo Rodriguez-Tello

原文摘要

Plant organ segmentation on compact computing platforms requires accurate predictions and affordable geometric preparation. We develop and evaluate a multiscale edge based graph attention model that combines local shape descriptors, two neighborhood scales and a residual stem and leaf correction in approximately 78 thousand parameters. The engineering application is plant point cloud segmentation for precision agriculture, assessed through grouped accuracy experiments and physical Raspberry Pi 5 inference. Broad comparisons with hierarchical, graph and transformer baselines establish PointNeXt as the strongest external accuracy reference among the tested local recipes. A nested four variant ablation on a local maize collection separates geometric information from the combined multiscale configuration across seven outer groups and three seeds. The complete model achieves the highest mean intersection over union, 86.36%, although uncertainty and boundary errors qualify the contribution of each component. We then optimize full cloud principal component analysis, sampling and neighbor queries without changing learned weights or descriptor definitions. All 1,180 paired desktop comparisons on PlantNet and TomatoWUR preserve exact logits and predictions. Multiscale pipeline latency falls from 330.33 to 96.82 milliseconds on PlantNet and from 1,054.52 to 463.10 milliseconds on TomatoWUR. PointNeXt also benefits from optimized sampling and remains faster over the complete pipeline. These results support compact graph learning with reduced geometric overhead, while physical board measurements establish inference feasibility rather than energy efficiency or readiness for autonomous flight.

cs.CV

新论文 · v1arXiv:2611.11005

GradReason: LLMs as Meta-Learners that Replace Training Epochs with Training-Data-Free Weight Updates

Ali Mohammadi Ruzbahani, Abbas Yazdinejad, Hadis Karimipour

原文摘要

Standard training recipes make a fixed number of passes over the training data, even when an epoch mostly adds mini-batch noise. We study whether a large language model (LLM) that reads the weight and gradient history of a run can replace some of these epochs with updates that compute no gradient and read no training image. In GradReason, an LLM agent is called every ten epochs. In a restricted sandbox, it analyses recent weight snapshots, epoch-mean gradients, and validation metrics, then submits a Python program that computes new weights and a plan marking each of the next ten epochs as data or virtual. A virtual epoch is kept only if it passes a forward-only check on 5,000 held-out validation images. In 120 runs on CIFAR-10 and CIFAR-100 with three architectures, Claude Opus 5.5 used 32.8% fewer data epochs than the 80-epoch recipe at 0.31 percentage points lower test accuracy (95% CI -0.72 to +0.09; 0.94 points on ResNet-18), on the recipe's own frontier of data against accuracy. Unprompted, Opus averaged recent weight snapshots in every run. This choice produced the savings: a fixed rule with the same acceptance check but extrapolations from prior work saved 5.4% of the data epochs, and the same rule with averaging added saved 25.0%. The LLM's contribution is to find a working update within a single run; once found, a fixed rule implements it equally well. An Opus run cost 0.68 USD, but at this scale the agent's latency exceeded the GPU time it saved.

cs.LG · cs.AI

版本更新 · v2arXiv:2609.11894

3D Point Splatting for mmWave Radar Novel View Synthesis

Adnan Armouti, Yixuan Gao, Rajalakshmi Nandakumar

原文摘要

Solving novel view synthesis (NVS) for millimeter-wave (mmWave) radar requires a renderer that is physically faithful, complex-valued, and multi-viewpoint-tractable. No prior method achieves these three properties simultaneously. Differentiable Monte Carlo (MC) ray tracers implement the radar forward model directly with explicit material modeling and complex outputs, but a joint fit across views takes over an hour per scene. Optical-NVS ports of NeRF, hash grids, and 3D Gaussians train fast but discard phase and replace explicit material modeling with opaque learned features, restricting them to power-only range-azimuth (RA) magnitudes. We propose 3D Point Splatting (3DPS), the first differentiable point splatting renderer for radar, derived directly from the standard solid-angle form of the radar equation. Each oriented 3D point carries a material model built on ITU-R P.2040 permittivity and slab reflection, evaluated in closed form, with the resulting complex phasor splatted into range bins through a precomputed point spread function (PSF). The complex-valued output makes the renderer product-agnostic. The same optimized scene yields analog-to-digital converter (ADC), complex range profile (CRP), and RA outputs through standard fast Fourier transform (FFT) pipelines without retraining for each format. On six outdoor ColoRadar scenes, 3DPS reaches 0.587 mean Pearson correlation on held-out RA images. This is between 1.7x and 5.2x the three optical-NVS baselines (RadarSplat, Radar Fields, DART) and 1.3x the mmIR ray tracer at 1/25 of its wall-clock time. Training takes approximately 3 minutes per scene on a single RTX 4090. Project page: https://3d-point-splatting.github.io/

cs.CV · cs.GR · cs.LG · eess.SP

新论文 · v1arXiv:2611.11001

Elastic Representations via Hyperbolic Geometry

Arjun Ramesh Kaushik, Rudrasis Chakraborty, Nalini Ratha, Venu Govindaraju

原文摘要

Learned representations (or embeddings) are the foundation of modern machine learning systems, yet they are typically trained as fixed-size embeddings, without accounting for varying downstream resource or task constraints. Matryoshka Representation Learning (MRL) addresses this limitation by learning nested representations, but requires costly end-to-end retraining and does not support post hoc expansion, while Contrastive Sparse Representations (CSR) reduce training overhead via lightweight adaptors but operate at a 4x larger dimensionality. Additionally, all prior works restrict their framework towards compression only. In this work, we introduce Hyperbolic Elastic Representation Learning (HERL), a framework for learning dimension-adaptive embeddings (compression and expansion) through a lightweight adaptor without retraining the base encoder. Our key idea is to exploit the exponential capacity of hyperbolic geometry by learning a non-linear mapping from the encoder space to hyperbolic space. We train a simple MLP to downsample the representations before projecting them onto a Lorentzian and learn adaptive representations that respect the Lorentzian geometry. Our approach is model-agnostic and effective in both supervised and unsupervised settings. Through extensive experiments across image and text modalities, we show that HERL preserves downstream performance across a wide range of embedding sizes, exhibits smooth interpolation between dimensions, and achieves these benefits at a fraction of the computational cost. Code: https://github.com/arjunrkaushik/herl.

cs.LG · cs.CV

新论文 · v1arXiv:2611.10999

Differentiable Agent-Based Modeling for Multi-Echelon Supply Chains: Gradient-Based Optimization of Heterogeneous Policies at Scale

Bulent Soykan, Murtadha Alsayegh, Sean Mondesire, Ghaith Rabadi

原文摘要

Global supply chains rely on the interactions of thousands of heterogeneous agents, posing significant challenges for optimization. While traditional optimization often assumes homogeneity to ensure tractability, Reinforcement Learning struggles with sample inefficiency when scaling to high-dimensional state spaces. We propose a Differentiable Agent-Based Model for multi-echelon inventory management. By implementing stochastic dynamics via differentiable tensor operations, we enable direct gradient propagation through the simulation. We validate the framework by recovering theoretical Newsvendor optima without supervision. Crucially, we demonstrate ``Mass Personalization'' by optimizing 10,000 distinct agent policies simultaneously in seconds, achieving a 53% cost reduction compared to scalar baselines. Furthermore, we utilize gradient sensitivity analysis to generate causal heatmaps, accurately recovering inherent lead-time delays from the computation graph. This approach bridges the gap between simulation and optimization, enabling the efficient training of self-correcting Digital Twins.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.05755

Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement

Haodong Liang, Lifeng Lai

原文摘要

We investigate the ability of transformers to perform in-context reinforcement learning (ICRL), where a model must infer and execute learning algorithms from trajectory data without parameter updates. We show that a linear self-attention transformer block can provably implement policy-improvement methods, including semi-gradient SARSA and actor-critic, via explicit parameter constructions. Beyond existence, we design a teacher-mimicking training procedure, analyze its gradient-flow dynamics, and establish the first convergence guarantee in the ICRL literature: under suitable richness conditions on the training MDP distribution, gradient flow converges locally and exponentially to an optimal parameter manifold corresponding to the desired RL update. Empirically, training transformers on randomly generated tabular MDPs confirms these predictions: the learned models recover the parameter structure of our explicit constructions and, when deployed on unseen MDPs, deliver strong in-context control performance. Together, these results illuminate how transformer architectures internalize and execute classical reinforcement learning algorithms in context, bridging mechanistic understanding and training dynamics in ICRL.

stat.ML · cs.AI · cs.LG

版本更新 · v3arXiv:2405.12886

Improved Asymptotic Runtime of Gotzmann's Decomposition

Joseph Donato

原文摘要

In the study of Hilbert schemes, the integer partition or Gotzmann's decomposition of a Hilbert polynomial helps researchers identify some geometric and combinatorial properties of the scheme in question. To aid researchers in extracting such information from a Hilbert polynomial, we describe an efficient algorithm which can identify if $p(x)\in\mathbb{Q}[x]$ is a Hilbert polynomial and if so, recover the integer partition $λ$ associated with it.

cs.SC

新论文 · v1arXiv:2611.10997

Open Problems in Chatbots and Mental Health

Jared Moore, Jacy Reese Anthis, William Agnew, Andrea Mock, Kevin Klyman, Sanmi Koyejo, Nick Haber, Stevie Chancellor 等 11 位作者

原文摘要

General-purpose chatbots are increasingly used for emotional and mental health support. They can be useful, but issues such as sycophancy, reinforcement of delusional beliefs, and poor crisis response create risks that are difficult for researchers to study and evaluate. In this paper, we review the most critical open problems for researchers and policymakers in the use of general-purpose chatbots and their effects on mental health. First, there are tractable problems in the controlled evaluation of chatbots: establishing the construct and ecological validity of evaluations, evaluating multi-turn interactions, and connecting evaluations to improvements in chatbot behavior. For example, conventional benchmarks that primarily rely on static datasets cannot establish chatbot safety, and novel simulation methods need validation. Second, researchers must connect their studies of chatbots and mental health to real-world evidence. This includes analyzing the chatbot products that AI companies and mental health practitioners have deployed, including their user interfaces and human review and escalation practices for user welfare concerns. However, clinical analysis opportunities afforded by real chat log data sharing are complicated by significant privacy concerns. Finally, we argue that researchers should take an active role in the construction and refinement of evidence-based policy through corporate and governmental decisions such as user protections, standards of care, protected access to user chat logs, data sharing between institutions, incident reporting, and post-deployment monitoring. Such behavioral evaluations, studies of real-world outcomes, and data governance depend on each other and must be addressed in tandem. We believe a coordinated research effort would have substantial real-world impact.

cs.CL · cs.CY

新论文 · v1arXiv:2611.10996

Toward a theory of Evaluability

Kunal Talwar

原文摘要

Machine learning models, particularly large foundation models, are increasingly evaluated along multiple axes that are relevant for their usage. In addition to accuracy measures appropriate for the specific task of interest, measures capturing safety, calibration and fairness properties are often of interest. The classical approach to these problems assumes that the test set has been held out from the training process, an assumption that is increasingly harder to justify for large foundation models. In this work, we formalize a notion of evaluability without this assumption, and ask if it is feasible to evaluate black-box models in settings where our test samples may have been used during training. We study this problem under different settings, capturing different levels of access to the model. We first study the natural setting, where the evaluator only looks at the output of the model on the test set. We fully characterize the class of distributions where accurate evaluation is possible, and show tight upper and lower bounds on the sample complexity of evaluation. Our results show that black-box evaluation in this setup is feasible if and only if the distribution is close to being small support. We then consider evaluation algorithms that can query the model on additional inputs and demonstrate connections to self-correctors studied in program testing. Using these, we show that a small amount of query access can increase the power of the evaluator for natural distributions and concept classes.

cs.LG · stat.ML

新论文 · v1arXiv:2611.10994

RoboMoCap: A Large-Scale Whole-Body Motion Capture Dataset with Egocentric Vision for Robot Learning

Mayur Deshmukh, Aaron Tung, Junyi Li, Nikash Bhardwaj, Ademi Adeniji, Vincent Liu, Michael Cho, Jiafei Duan

原文摘要

Humanoid robots must coordinate locomotion and manipulation to navigate complex environments and perform everyday tasks. Learning such behaviours from human demonstrations requires accurate whole-body motion paired with egocentric vision, particularly for lower-body movements and foot placements that are frequently invisible from a first-person perspective. However, existing egocentric datasets often lack high-fidelity optical motion capture or systematic coverage of diverse loco-manipulation behaviours. To address this gap, we introduce RoboMoCap, a large-scale multimodal dataset combining egocentric vision with marker-based optical motion capture, specifically designed for locomotion-centric humanoid learning. RoboMoCap comprises over 200 hours of recordings from 14 participants, featuring six head-mounted cameras, wrist-mounted visual and inertial sensing, and optical full-body motion capture at 120 Hz. The dataset systematically covers diverse locomotion primitives, dynamic whole-body movements, and loco-manipulation tasks, including variable-speed walking, turning, constrained navigation, terrain traversal, object transportation, and manipulation during locomotion. It provides temporally aligned multimodal observations and metric whole-body motion representations, enabling the study of human movement beyond directly observable body regions. We systematically evaluate existing methods on three benchmark tasks: egocentric full-body motion reconstruction, foot contact and placement estimation, and human-to-humanoid motion retargeting. By pairing egocentric vision with high-fidelity human motion across diverse locomotion and interaction scenarios, RoboMoCap provides a foundation for egocentric motion understanding and humanoid learning from human demonstrations.

cs.RO

版本更新 · v2arXiv:2605.05973

Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking

Jiefu Zhang, Yang Xu, Haixiang Sun, Zihan Zhou, Tianyu Cao, Vaneet Aggarwal

原文摘要

Adaptive prompt and program search makes LLM evaluation selection-sensitive. Once benchmark items are reused inside tuning, the observed winner's score need not estimate the fresh-data performance of the full tune-then-deploy procedure. We study inference for this procedure-level target under explicit tuning budgets. We propose SIREN, a selection-aware repeated-split reporting protocol that freezes the post-search shortlist, separates splitwise selection from held-out evaluation, and uses an item-level Gaussian multiplier bootstrap for uncertainty quantification. In a fixed-shortlist regime with smooth stabilized selection, the estimator admits a first-order item-level representation, and the bootstrap yields valid simultaneous inference on a finite budget grid. This supports confidence intervals for procedure-performance curves and pre-specified equal-budget and cross-budget comparisons. Controlled simulations and MMLU-Pro tuning experiments show that winner-based reporting can be optimistic and can change deployment conclusions, while SIREN remains close to the finite-sample reporting target.

stat.ML · cs.AI · cs.LG · stat.AP

版本更新 · v2arXiv:2607.09645

Deep Gaussian Processes on Directed Acyclic Graphs

Federico L. Perlino, Oliver Hamelijnck, Adam M. Johansen, Theodoros Damoulas

原文摘要

Many real-world processes can be represented as compositions of functions along a directed acyclic graph (DAG). In causal modelling, these correspond to the underlying mechanisms; in engineering, to multiple fidelity levels; and in gene-regulatory networks, to transcription factors. These functions are partially observed across the DAG, with noisy and heterogeneously sampled measurements, posing significant challenges for reconstruction, uncertainty propagation, and inference. To tackle these challenges, we place priors over functions and naturally arrive at Deep Gaussian Processes over DAGs. We theoretically study their prior-collapse behaviour and the effect of graph topology and intermediate observations on the preservation of information. We obtain almost-sure lower bounds on the asymptotic frequency of depths at which the distinction between inputs is preserved, identify broad kernel classes for which these hold, and prove an observation by \citep{dunlop2018} on the role of input connections. We offer a structured variational approximation that retains graph dependencies, preserves compositional uncertainty, and captures the explaining-away behaviour of colliders. Finally, we empirically validate our theory and methodology at scale and under DAG misspecification. We then model a latent-collider DAG, a protein signalling network, and a multi-fidelity \mbox{heavy-ion} collision emulation task, attaining state-of-the-art performance while recovering low-fidelity contributions and yielding interpretability over the simulator hierarchy.

stat.ML · cs.LG · math.ST · stat.CO · stat.ME

新论文 · v1arXiv:2611.10993

DPDP: Diffusion Policy-Steered Diffusion Planner for Offline Reinforcement Learning

Ruyi An, Mingyuan Zhou

原文摘要

In offline reinforcement learning, diffusion models fill two roles with complementary strengths. Typically guided by a critic, a diffusion policy is value-aware and favors high-return, behavior-supported actions, but it is short-sighted: it never lays out the states it intends to visit. A diffusion planner is far-sighted, synthesizing such a long-horizon trajectory, but it is only behavior-driven at execution, realizing each planned transition using only offline behavior.Each is strong exactly where the other is weak. We introduce DPDP to bring them together at the planner's execution step, where a planned transition becomes an action. Reading the planner's inverse-dynamics executor as a posterior over actions: the environment's transition likelihood relates an action to the planned next state, while the behavioral prior determines its weight under the offline data. Replacing this prior with a value-optimized diffusion policy preserves the planned transition likelihood and favors valuable actions that can serve the plan. We target the resulting clean-action distribution in two ways. A training-free sampler composes policy and inverse-dynamics scores at matched action noise levels and applies Langevin correction; this route uses a shared action noise schedule and an approximately common terminal prior. A preference objective instead amortizes the transfer into a single diffusion executor. Across D4RL, DPDP improves the planner it builds on, staying competitive with reactive diffusion policies on locomotion and leading on long-horizon navigation.

cs.LG

新论文 · v1arXiv:2611.10992

Hydro-Dataset: A Multi-Modal Open-Source Pipeline for Nordic Hydrological Research and Foundation Model Benchmarking

Getnet Demil, Md Moinul Islam, Mourad Oussalah

原文摘要

Despite world-class snow monitoring by the Swedish Meteorological and Hydrological Institute (SMHI) and Finnish Meteorological Institute (FMI), no station-anchored, multi-parameter snow benchmark dataset exists for the Nordic boreal domain. We present Hydro-Dataset v1.1, a reproducible open-source pipeline that harmonizes 582 SMHI meteorological observation stations across nine hydrological winters (2015/16-2023/24) into a CF-1.9 NetCDF product with 1.8~million annotated station-days. Six derived snow parameters, such as Snow Water Equivalent (SWE), snow phenology, melt rates, degree-day melt factor, rain-on-snow flags, and freeze-thaw cycles, supply benchmark-ready labels for hydrological foundation model training. ERA5-Land cross-validation (Pearson R=0.78, bias=-262mm) confirms observation-anchored SWE provides a more reliable benchmark than reanalysis for machine learning training.

cs.LG

新论文 · v1arXiv:2611.10991

Sensitivity-Gated Accumulator Caching for On-Device Learning of Low-Bit Hand Networks

Soroor Ghandali, Kanika Mamgain, Manjot Kaur, Akanksha Shukla, Shashira Guntuka

原文摘要

Small hand-tracking networks are deployed as 4- and 8-bit codes, and they should keep adapting to a user's camera after deployment, on the device and within roughly the memory of the model itself. Quantization-aware training cannot do this cheaply, because it keeps a 32-bit master copy of every weight together with its optimizer state, about 96 bits per weight. Training the codes directly with stochastic rounding needs no copy but injects rounding noise at every step, and the methods that remove this noise keep a residual buffer for every weight. We introduce sensitivity-gated accumulator caching (SGAC), which keeps residual state for only a small and changing set of weight groups. A set-associative cache of 8-bit accumulators collects the sub-step updates of the groups with the largest Fisher-weighted squared code step and writes them into the codes as whole steps; an evicted line is flushed by stochastic rounding, and a group without a line does not move until it is admitted. We prove that the write-back is unbiased and show, under a local quadratic model, that rounding a sub-step update costs loss of the same order as the update's own gain, so that rounding pays only where the expected gradient is large relative to the curvature. On a 383k-parameter hand-keypoint network, SGAC trains with 8.1 bits of state per weight. Scored on the 4/8-bit network that the device runs after adaptation, it has the highest mean accuracy of nine deployed low-bit networks on two simulated cameras. On twelve ImageNet-C corruptions it has the highest average of corrupted and clean accuracy of seven deployed methods, ahead of the PEQA-style, ECO-style and direct low-bit baselines with confidence intervals that exclude zero, and it matches an 8-bit accumulator kept for every weight with 56% of that state.

cs.CV · cs.LG

版本更新 · v3arXiv:2602.00474

Persistent-Transient Policy Evaluation for Markov Chains via Minimal Peripheral Quotients

Yang Xu, Vaneet Aggarwal

原文摘要

We study fixed-policy evaluation for finite Markov chains that may be reducible and periodic. Classical evaluation methods with gain and bias decomposition are not always diagnostic: the gain records only invariant Cesàro averages, while persistent phase-dependent behavior is absorbed into the bias together with genuinely transient effects. We identify the real peripheral invariant subspace $\mathcal{K}(P)$ of the transition matrix $P$ as the source of this ambiguity. Quotienting by $\mathcal{K}(P)$ is the minimal exact quotient that removes all non-decaying modes and makes the remaining dynamics strictly stable. After choosing a gauge projection $Π$ with kernel $\mathcal{K}(P)$, the reward admits a unique decomposition $r = g_Π^\star + (I-P)v_Π^\star$, where $g_Π^\star$ is a persistent regime profile and $v_Π^\star$ is a gauge-fixed transient component. An exact comparison with classical normalized gain and bias shows that the new pair reallocates the same information into a persistent profile and a gauge-fixed representative of the transient quotient. This decomposition reconstructs finite-horizon returns, recovers statewise average reward, admits a transient-cost interpretation, and yields a stable estimator under a generative model.

stat.ML · cs.LG · math.NA

新论文 · v1arXiv:2611.10987

Horizon-Scalable Q-Learning

Haoran Xu, Pragya Srivastava, Xinjie Liu, Siddhant Agarwal, Amy Zhang

原文摘要

Learning accurate off-policy state-action value functions (Q-functions) from offline datasets becomes harder as the task horizon grows. One-step temporal-difference (TD) learning bootstraps after every transition, so small per-step errors accumulate along the horizon, and early states can be badly misvalued even when the TD loss is small. Multi-step TD shortens this chain by following the dataset trajectory for several steps; however, since the behavior policy is often suboptimal, every followed action adds a bias, and no fixed number of steps suits a whole trajectory. In this paper, we propose Horizon-Scalable Q-Learning (HQL), a simple method that enables accurate long-horizon value learning by automatically balancing between one-step and multi-step returns. HQL extends a target through a dataset action only when the critic values it at least as highly as the best-of-N actions sampled from the BC policy, and otherwise falls back to a one-step target. We show that this rule is a principled off-policy correction that needs no action densities, which makes HQL compatible with expressive flow and diffusion policies. Experiments show that HQL avoids the failures of both one-step and multi-step TD on a combination-lock task across horizons, and outperforms prior horizon-reduction methods on long-horizon OGBench and OCBench tasks.

cs.LG · cs.AI

新论文 · v1arXiv:2611.10986

The forces at hand: social learning is permissive, not instructive, for the evolution of phenotypic plasticity

Nam H. Le

原文摘要

Evolution can favour a trait for two reasons: an instructive cause makes selection favour the trait; a permissive one lets it persist once selection no longer removes it. The distinction matters most for phenotypic plasticity and its replacement by inherited behaviour, genetic assimilation, the Baldwin effect. Social learning is credited with favouring plasticity on evidence that cannot tell the two apart: how much plasticity remains at the end of a simulation. Here we show, analytically and computationally, which role it plays in a minimal model of learning and evolution. Writing expected fitness as a function of plasticity, we find that environmental change is the only source of benefit from plasticity, and the social channel enters only its cost. Simulation confirms this: in a static environment selection against plasticity never reverses sign at any channel strength; when the environment changes, it reverses at a threshold the channel lowers, and without the channel the population collapses before reaching it. Social learning is permissive, not instructive: it supplies the means to be plastic, never the reason. For the debate over whether plasticity leads evolution, this is one case settled by measurement: environmental change directs, socially inherited information permits, and neither suffices alone.

q-bio.PE · cs.NE

版本更新 · v3arXiv:2605.18445

What's Holding Back Latent Visual Reasoning?

André G. Viveiros, Nuno Gonçalves, André F. T. Martins, Matthias Lindemann

原文摘要

Humans can approach complex visual problems by mentally simulating intermediate visual steps, rather than reasoning through language alone. Inspired by this, several works on Vision-Language Models have recently explored chain-of-thought reasoning with continuous latent tokens as intermediate visual imagination steps. In this work, we investigate how recent models leverage such latent tokens. Surprisingly, we find that model accuracy is unaffected when latent tokens are replaced by uninformative dummy tokens. This indicates that latent tokens play a minimal causal role in the model's final prediction. To better understand this phenomenon, we analyze both the training signal provided by oracle latent representations and the quality of the latent tokens generated at inference time. Our experiments reveal two crucial issues holding back latent visual reasoning: First, in most existing datasets, oracle latent tokens provide limited additional information beyond the original image and do not substantially simplify the task, leading models to ignore them during training and effectively bypassing them at inference time. When fine-tuned on a diagnostic dataset, in which latent tokens provide sufficient support for the final prediction, we show that models can causally rely on them. Second, the latent tokens produced at inference time deviate from their corresponding oracle representations, collapsing to a narrow region and preventing benefits even when the model relies on them. Overall, our findings suggest that future progress in latent visual reasoning depends on two key pillars: high-quality datasets with informative intermediate steps and more precise latent token prediction.

cs.CV · cs.AI · cs.CL · cs.LG

新论文 · v1arXiv:2611.10984

Network Contention State Aware Dynamic Optimizer for Accelerator Collective Communication Libraries

Rajat Bisht, Tevfik Kosar, Anthony Skjellum, Gene Cooperman, MD S Q Zulkar Nine

原文摘要

Collective Communication Libraries (CCL) are critical for large-scale distributed AI/ML training, yet their configurations are determined by static heuristics that do not account for real-time network conditions. Our empirical study shows that these heuristics perform near-optimally in contention-free environments, but degrade substantially under background traffic. To address this, we present a cooperative multi-agent run-time optimizer for accelerator collective communication. Our approach employs a two-agent architecture: (i) detector- a Long Short Term Memory(LSTM) recurring neural network fed classifier head with a sequential probability ratio test that distinguishes sustained contention from transient spikes; and (ii) selector- a configuration selector built on a Dueling Double DQN (D3QN) with Conservative Q-Learning that adapts configuration parameters in response. We implemented this dynamic tuner over NCCL, a widely used CCL developed by NVIDIA. When evaluated on Chameleon Cloud's isolated bare-metal cluster, this dynamic tuning approach reduces AllReduce latency by 36% over NCCL and 32% over a fully converged AutoCCL. We further evaluated it across six real AI workloads spanning convolutional networks, transformers, and recommendation architectures. Our multi-agent tuner approach delivers up to 65% speedups on Delta cluster with NVIDIA A100 GPUs and Slingshot-11 fabric internode connectivity.

cs.DC · cs.LG · cs.MA

版本更新 · v2arXiv:2606.25402

LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models

Daniele Cipollone, Sergey Titov, Maliheh Izadi, Egor Bogomolov, Arie van Deursen

原文摘要

Large software projects often depend on older versions of libraries, even as APIs continue to evolve across releases. This creates a challenge for LLMs: they must maintain knowledge of multiple API versions, not merely the latest or most common one. However, current LLMs are trained on temporally mixed corpora and lack explicit mechanisms for such version-specific reasoning, leading to anachronistic errors - calling APIs as they exist in a different library version. To systematically evaluate this phenomenon, we introduce LibEvoBench, a multi-task benchmark spanning multiple versions of widely used Python libraries, along with a new metric, the Software Evolution Understanding Score (SEUS), to measure models' consistency when working with evolving APIs. Our results show that state-of-the-art models are largely version-oblivious: performance degrades for evolving APIs, while for stable APIs it remains the same across versions. Moreover, simply specifying the target version provides no benefit, while relevant documentation significantly boosts models' accuracy. These findings highlight a systematic limitation of current training paradigms and motivate new approaches for temporally grounded knowledge in code generation.

cs.SE · cs.AI

版本更新 · v2arXiv:2602.04131

Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting

Mehrdad Moghimi, Anthony Coache, Hyejin Ku

原文摘要

Distributional reinforcement learning (RL) is a powerful framework increasingly adopted in safety-critical domains for its ability to optimize risk-sensitive objectives. However, the role of the discount factor is often overlooked, as it is typically treated as a fixed parameter of the Markov decision process or tunable hyperparameter, with little consideration of its effect on the learned policy. In the literature, it is well-known that the discounting function plays a major role in characterizing time preferences of an agent, which an exponential discount factor cannot fully capture. Building on this insight, we propose a novel framework that supports flexible discounting of future rewards and optimization of risk measures in distributional RL. We provide a technical analysis of the optimality of our algorithms, show that our multi-horizon extension fixes issues raised with existing methodologies, and validate the robustness of our methods through extensive experiments. Our results highlight that discounting is a cornerstone in decision-making problems for capturing more expressive temporal and risk preferences profiles, with potential implications for real-world safety-critical applications.

cs.LG

版本更新 · v3arXiv:2604.00449

Convergence of Byzantine-Resilient Gradient Tracking via Probabilistic Edge Dropout

Amirhossein Dezhboro, Fateme Maleki, Arman Adibi, Erfan Amini, Jose E. Ramirez-Marquez

原文摘要

We study distributed optimization over networks with Byzantine agents that may send arbitrary adversarial messages. We propose Gradient Tracking with Probabilistic Edge Dropout (GT-PD), which combines a universal self-centred projection that clips incoming messages to a radius-$τ$ ball around the receiver with a fully decentralized probabilistic dropout rule driven by a threshold-gated, dual-metric trust score in the decision and tracking channels. These identity-free defences bound adversarial perturbations while preserving doubly stochastic mixing. The projection preserves the honest network average exactly in every realization, even when honest messages are clipped. Under complete Byzantine isolation ($p_b=0$), GT-PD converges linearly to a neighbourhood of order $ασ^2/(μn_{\mathcal H})$ plus higher-order network terms, matching centralized stochastic gradient descent to first order in the step size. We also give a radius computable from problem data that ensures honest messages remain unclipped with high probability. Under partial isolation ($p_b>0$), a leaky variant, GT-PD-L, controls accumulated tracking perturbations and converges linearly to a bounded neighbourhood governed by stochastic variance and the clipping-to-leak ratio, under explicit conditions on the step size, leak, and aggregate Byzantine mixing weight. With two-tier dropout and $p_h=1$, Byzantine isolation adds no variance to honest consensus dynamics. MNIST experiments under Sign Flip, ALIE, and Inner Product Manipulation attacks show that GT-PD-L outperforms coordinate-wise trimmed mean by up to 4.3 percentage points under stealth attacks.

cs.LG · cs.MA · eess.SY

新论文 · v1arXiv:2611.10982

Think or Remember: The Exchange Rate of Agentic Inference

Juan Wisznia, Santiago Luis Groba Alonso, Matías Gómez Taddeo, Gonzalo Zabaleta, Joaquín Cullen, Luciano Del Corro

原文摘要

Agents built on reasoning models resend their growing transcript at every call. Two transacting parties, not the model, decide what that costs: the client keeps or edits messages; the server decides whether earlier reasoning returns in the prompt and what its cache reuses. We define a cost model whose counts match an instrumented engine exactly; the architecture charges $c$ per token processed and $β$ per pair attended. Their ratio $P^*=c/β$ is an exchange rate between thinking and remembering: per token, processing dominates below this context length, a thinking regime, and attention above it, a memory regime. A policy change has a mechanical cost, incurred even if the agent writes the same tokens, and a behavioral one: it writes different tokens, changing cost and outcome. Serving alone can flip which policy is cheaper: on recorded Qwen3-8B ScienceWorld runs, dropping earlier reasoning costs 1.74 times keeping it when the server reuses generated states and 0.34 times when it reuses nothing. In live reruns, dropping it cuts correct HotpotQA answers by 9-23 percentage points on four models, at lower point-estimate cost. Comparing context policies means comparing systems: architecture and serving set the cost of the history kept and the work it induces.

cs.CL · cs.AI

版本更新 · v3arXiv:2605.20555

LAPO: KL-Free Logit-Averaged Policy Optimization to Leverage RL and SFT in LLM Post-Training

Xingwei Gan, Ying Zhu

原文摘要

From a classical statistical perspective, model averaging and parameter shrinkage (e.g., Ridge regression with an $l_2$-penalty) are deeply connected mechanisms designed to reduce estimator variance and lower mean squared error. Motivated by this insight, we introduce Logit-Averaged Policy Optimization (LAPO), a KL-free and critic-free post-training framework that replaces explicit KL regularization with logit averaging inside Group Relative Policy Optimization (GRPO); in particular, averaging the logits of the trainable policy and a frozen reference policy functions as an implicit structural regularizer that stabilizes rollout trajectories. For selecting the mixing weight, we propose a compute-efficient adaptive algorithm that dynamically balances exploration and structural anchoring throughout training, evaluated against a static fixed-weight baseline. This adaptive mechanism eliminates explicit KL penalty backpropagation and expensive, fragile hyperparameter sweeps while reducing the incidence of uninformative zero-reward rollout groups. Mathematically, embedding logit averaging within the reinforcement learning loop operates as an in-training Product of Experts (PoE): the multiplicative geometric mean enables the reference anchor to act as a soft logical "AND" that vetoes non-compliant tokens, enforcing schema rigor and safety guardrails without the catastrophic forgetting typical of sequential fine-tuning. Evaluated across Qwen2.5-Instruct models (1.5B, 3B, and 7B), LAPO consistently outperforms canonical KL-regularized GRPO, achieving a 7%-15% accuracy gain on MATH and a 2%-5% gain on cn_k12 and MMLU. Finally, the resulting mixed teacher policy can be distilled back into a single student network, fully restoring standard $1\times$ inference latency.

cs.LG · cs.AI

版本更新 · v2arXiv:2606.14029

Utility-Constrained Policy Optimization

Mehrdad Moghimi, Bernardo Avila Pires

原文摘要

Constrained MDPs (CMDPs) are a widely adopted framework for incorporating safety into RL agents; however, the framework does not support risk-sensitive constraints. This can be problematic: For example, CMDPs allow for optimal solutions that, in order to satisfy the risk-neutral constraints, mix infrequent catastrophic behaviors and frequent, overly conservative ones. Moreover, prior empirical results suggest that enforcing stricter, risk-sensitive constraints can improve performance even under risk-neutral evaluation. The natural framework to incorporate risk-sensitive constraints is utility-constrained MDPs (UCMDPs), but no practical solutions for this problem existed. In this work, we introduce a simple yet powerful methodology for UCMDPs and constrained RL. Besides allowing for risk-sensitive constraints, our framework does not require us to fix constraint limits in advance of training the agent, provided that a sensible range is known. This increases policy flexibility and, in practice, allows for adjustments to these limits at no extra training cost. Besides benefiting from the generality of the framework, our agent shows strong performance in practice, consistently matching or outperforming existing baselines in several Safety Gymnasium benchmark tasks.

cs.LG

新论文 · v1arXiv:2611.10981

An Analysis of Reinforcement Learning with Function Approximation

Francisco S. Melo, Sean P. Meyn, M. Isabel Ribeiro

原文摘要

We address the problem of computing the optimal Q-function in Markov decision problems with infinite state-space. We analyze the convergence properties of several variations of Q-learning when combined with function approximation, extending the analysis of TD-learning in Tsitsiklis and Van Roy (1996) to stochastic control settings. We identify conditions under which such approximate methods converge with probability 1. We conclude with a brief discussion on the general applicability of our results and compare them with several related works.

cs.LG