跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1102新增论文
+897其中 AI 相关
+79已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 10:13 · 全站最近入库：2026-11-10 10:13各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 10:17 — 2026-11-10 10:17（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：2026-11-10 10:13最近发现新增版本：2026-11-10 10:13库内论文最新更新时间：2026-11-07 14:03

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。

18,563 已收录论文15,842 AI 相关4,675 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 15,842 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 10:11（北京时间）
版本更新 · v2arXiv:2605.00654

Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation

Andrzej Ruszczynski, Tiangang Zhang

原文摘要

For a risk-averse finite-horizon Markov Decision Process, we introduce a special class of Markov coherent risk measures, called mini-batch measures. We also define the class of multipattern risk-averse problems that reduce to linear MDPs in the risk-neutral case. We use both concepts in a feature-based $Q$-learning method with multipattern $Q$-factor approximation and we prove a high-probability regret bound of $\widetilde{\mathcal{O}}\big(d^{3/2}HN^{H-1}\sqrt{K}\big)$, where $d$ is the number of features, $H$ is the horizon, $N\ge2$ is the mini-batch size, $K$ is the number of episodes, and $\widetilde{\mathcal{O}}$ hides logarithmic factors. We also propose an economical version of the $Q$-learning method that streamlines the policy evaluation (backward) step. The theoretical results are illustrated on a stochastic assignment problem and a short-horizon multi-armed bandit problem.

cs.LG · cs.AI · math.OC · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01817

CoGSeq-LTV: Scalable Missing-Aware Graph-Sequence Modeling for Multi-Business Transaction Analytics

Ziyang Su, Yao Zhou, Kelin Liu, Guanjie Zheng, Linghe Kong

原文摘要

Large-scale super-apps generate heterogeneous transaction logs in which users interact with multiple businesses, item identifiers are only partially available, and future value targets are sparse, heavy-tailed, and cumulative over time. We study multi-business, multi-horizon value prediction as a data-intensive analytics problem over such logs, rather than as a single-table task. (i) a batch-induced user-item graph that provides collaborative signals without materializing a global graph and remains applicable when item identifiers are missing through reserved unknown-item handling, (ii) business-aware sequence encoders that preserve recency, inter-event gaps, payment context, and goods-table availability, and (iii) cross-view contrastive alignment that transfers user-level intent across businesses while retaining business-specific temporal patterns. To handle zero-inflated and long-tailed cumulative targets, CoGSeq-LTV adopts a zero-inflated mixture log-normal head with MAE-aligned point supervision and validation-calibrated zero-aware inference. Experiments on the BiBiSheng transaction-log dataset show that CoGSeq-LTV improves over representative LTV baselines across businesses and horizons, including under a later out-of-time evaluation window.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01815

When Does Latent Prediction Error Support Physical Surprise Claims in Video World Models?

Anton Hristov, Aleksandar Slavov, Vasil Vasilev

原文摘要

Prediction errors from video world models are often treated as physical surprise, but they can also reflect appearance, static content, motion, or ordinary prediction difficulty. We present an evaluation framework that separates what frozen representations contain, how they organize appearance and physical differences, and what changes a model's own prediction error. On IntPhys2, a benchmark of physically possible and impossible events, we compare representations from latent prediction, masked pixel reconstruction, and simple visual statistics. Appearance remains easy to decode, while V-JEPA2 exposes modest information about whether events are possible or impossible. Looking at the latent geometry, appearance changes become smaller compared with differences between videos, their directions line up more consistently across scenes, and their overlap with physical changes decreases in deeper layers. Across action-conditioned models, incorrect actions raise prediction error, while appearance changes also produce substantial responses. In Physion++ video clips, repeating a single frame can produce higher error than the original clip, while changing color throughout the clip can lower it. Using Kubric, a simulation and rendering framework, we find that impossible events can produce lower error than possible events. A fixed error threshold also incorrectly flags many possible events as impossible. A model can therefore represent physical information and respond to incorrect actions without its native prediction error reliably measuring physical surprise.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01814

Control Barrier Functions for Safety-Aware Latent-Space Motion Planning

Chandrakiran Ravula, Siddhanth Ramesh

原文摘要

Latent-space path planning (LSPP) compresses the configuration space of a robotic manipulator into a compact, differentiable manifold learned by a variational autoencoder, enabling fast gradient-based planning without explicit inverse kinematics. Existing LSPP frameworks enforce obstacle avoidance with a binary collision classifier, whose saturated gradients near obstacle boundaries and lack of temporal structure cause the optimizer to stall and provide no forward-invariance guarantee. We replace the classifier with a neural control barrier function (CBF) learned directly in the latent space. The barrier is trained with a three-term objective that combines safe and unsafe sign constraints with a discrete-time decrease condition evaluated on transitions of an obstacle-blind nominal planner, and it is enforced at planning time by a closed-form, first-order correction that projects each goal-directed latent step back onto the CBF constraint. On a 7-DoF Franka Panda manipulator, the CBF planner achieves a 75.6\% success rate on a fixed-obstacle task, 12.0 percentage points above the best of 35 tuned classifier configurations, and 83.8\% on a multi-position task. A sweep of the decay rate $α$ characterizes the safety--performance trade-off, with the best operating points in $α\in [0.10, 0.20]$. In a fully general random-obstacle setting, success drops to 33.0\%, which we trace to covariate shift between the obstacle-blind training transitions and the states visited by the corrected planner.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03726

DualClusterNet: Personalized Pattern-Space Composition for Next-POI Recommendation

Ziyang Su, Guanjie Zheng, Jilin Hu, Linghe Kong

原文摘要

Next point-of-interest (POI) recommendation supports personalized place discovery on location-based Web platforms. Mobility routines can recur across users while being realized at different places and adapted to individual preferences. We present DualClusterNet, a causal sequential recommender that composes two population-shared prototype dictionaries. At each observed prefix, soft routers retrieve pattern and spatial mixtures; a factorized multiplicative interaction couples them, feature-wise affine modulation adapts the shared representation, and a separate user-conditioned branch with an additive--projective gate retains individual variation. The prediction head combines this representation with a learned first-order transition term and ranks the complete training POI vocabulary. We evaluate on NYC and TKY using a training-only vocabulary and an original-final-target protocol that neither bridges unknown POIs nor substitutes earlier targets. The available single-seed results show competitive full-candidate ranking, while controlled analyses support the contribution of the compositional and personalized branches. Code is available at https://anonymous.4open.science/r/DualClusterNet-F4EE/.

cs.IR · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01812

Domain-Aware Hierarchical Federated Learning for UAV Swarms Across Heterogeneous Environments

Taha Mahmood, Mudassar Shakeel, Ahmed Naeem, El Mehdi Amhoud, Rizwan Ahmad, Salman Ghafoor

原文摘要

Hierarchical federated learning (HFL) enables communication-efficient training in unmanned aerial vehicle (UAV) swarms, but performance degrades under changing and heterogeneous environments. This paper proposes domain-aware HFL (DA-HFL), integrating mobility-informed clustering, cluster-level aggregation, cloud-based Fisher-weighted merging, a domain-adversarial shared backbone, environment-specific heads, and gated inference with local adaptation. A mission-weighted optimization formulation incorporates energy, latency, and cluster-head eligibility constraints. Theoretical analysis establishes resource feasibility, a conditional backbone-stationarity bound, the quadratic optimality of Fisher-weighted merging, and communication and computation complexity bounds. Simulations across four heterogeneous environments demonstrate faster convergence, improved accuracy during environmental transitions, and more stable, purer clusters than the evaluated baselines, with modest energy overhead over resource-aware HFL. Ablation studies validate the contributions of the proposed components.

eess.SP · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.20436

Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models

Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz

原文摘要

Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption. A checkpoint can appear fixed under evaluation-style prompts while the same behavior persists under ordinary-use prompts. Output scores reveal this mismatch but do not locate it. We investigate whether the distinction is encoded in a stable internal site and introduce an audit that fits a paired activation contrast at a path-patching-informed mid-depth window, then modifies the resulting coordinate on held-out prompts. The intervention reduces the evaluation-to-deployment gap by more than $0.12$ in ten of twelve model--behavior settings and closes it (post-intervention gap below $0.06$) in four, across four full-matrix instruction-tuned model instances; among the eight settings with $n{\geq}120$ paired questions, six reduce and one closes. A fifth model supports localization and edit-provenance checks, and in the twelve settings deployment-framed rates change by at most $6.1$pp. On retrained checkpoints, random directions at the same dose do not reproduce the effect, and off-window controls do so only in part. The strongest literal evidence for an evaluation-versus-deployment distinction comes from sandbagging, whose prompt framing is explicitly evaluative; sycophancy and refusal test framing-contingent task distinctions. The two weak cells, both sycophancy, show where a single-coordinate audit at a fixed window is not sufficient. The audit is a non-adaptive, white-box diagnostic for controlled fine-tuned checkpoints, not a training-time defense, a guarantee of deployment safety, or evidence about naturally arising failures.

cs.CL · cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01809

Shared relations, specific choices: conditional sensitivity and competing pathways in language models

Kaixiang Shu

原文摘要

How does a relational representation shared across queries drive a query-specific choice? Controlled entity-binding experiments with GPT-2 Small, Qwen2.5-1.5B and Llama-3.2-1B reveal a low-dimensional relational background that is predominantly shared across query roles and transfers to new names. Same-domain interactions persist when another attribute domain is queried. After removing this component, restoring independently trained relation directions brings output contrasts closer to their original values than sign-reversed or equal-norm random controls in all three models. Yet a transferable relational representation need not have a transferable functional sign. In Qwen2.5, fixing model weights, the training-mean relation vector and edit dose yields opposite selection effects across binary and lexical-mapping prompts with different answer vocabularies. A factorial contrast of downstream sensitivities across attribute-query combinations determines the shared direction's local signed selection gain. In a separate eight-condition protocol, mean local gain is positive in Qwen2.5 and negative in Llama3.2. Late-component clamps resolve opposing pathway contributions: in Llama3.2, negative transmission through selected attention-only paths is partially offset by positive transmission through paths traversing both selected attention and MLP sets. Source-coordinate analyses establish distributed factor coverage, hidden-receiver readouts reveal layout-dependent combination, and instance-geometry interventions separate response direction from amplitude. These findings show how conditional sensitivity and competing pathways give shared relational structure its effect on specific choices.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2606.03056

SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale

Tong Bai, Zhenglin Wan, Pengfei Zhou, Xingrui Yu, Yang You, Ivor W. Tsang

原文摘要

Large skill libraries are now standard equipment for LLM agents, and which subset reaches the prompt decides what the agent can do. Enumeration and top-$K$ embedding retrieval both treat skills as independent documents, assuming relevance is a property of one skill at a time. It is not: skills depend on, conflict with, specialize, and duplicate one another, so the closest match to a task can name it while omitting a prerequisite it needs. Graph retrieval encodes these relations but spends them in a fixed pipeline, handing the agent an opaque bundle. We present SkillDAG, which exposes a typed skill graph to the LLM as an agent-callable interface rather than consuming it for the agent: search returns vector matches, typed-edge neighbors, and conflict signals, and a propose-then-commit protocol lets it register execution-backed edges as it works. Across two benchmarks and three model families, SkillDAG outperforms full-library prompting, vector retrieval, and Graph-of-Skills, gaining +14.3 points of ALFWorld success and tying only at ceiling; its ranking holds flat across a $10\times$ pool expansion that degrades the fixed pipeline. Inter-skill structure, these results suggest, is worth more to an agent that can query and revise it than to a retriever that consumes it.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01799

Learning AI Agents, Market Makers, and Stress in Automated Markets

Irene Aldridge

原文摘要

Automated markets increasingly route order flow from learning trading agents through automated market makers (AMMs). We model trader archetypes as AI agents defined by their reward functions and analyze the feedback they create on a constant-product AMM. Herd-dominated and arbitrage-dominated markets of equal size have identical return distributions and turnover, so no rule based on volatility, value-at-risk, stress frequency, or volume can tell them apart; yet their stress episodes differ in length by a factor unbounded in the feedback-to-noise ratio $β/s$. Serial statistics identify the feedback sign from $Θ((s/β)^2\log(1/δ))$ observations, and this rate is tight. When agents trade together, profit-seeking agents ride herds rather than lean against them, leading to all-or-nothing participation. Spread-earning market makers restore stability but make liquidity fragile, with discontinuous collapse and hysteresis; maker--taker pricing, not a uniform fee, is the effective instrument.

econ.EM · cs.LG · econ.TH · q-fin.TR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01791

RIFT: Residual-Informed Flow Transfer for One-Step Generative Video Compression

Qizhe Wang, Jiaye Fu, Feng Ye, Haocheng Tang, Zetian Song, Chuanmin Jia, Siwei Ma, Jiaqi Zhang

原文摘要

Recent advances in video generation have enabled generative video compression to reconstruct details lost during coding using pretrained spatiotemporal priors. However, a substantial gap remains between codec-induced degradation and the perturbation trajectories learned by flow-matching models. In this paper, we identify a compression-dependent directional mismatch that degradation-strength-based timestep calibration alone cannot resolve. Compressed latents remain strongly aligned across codec operating points, while their reconstruction residuals vary substantially in magnitude and direction. To bridge this gap, we propose RIFT, a Residual-Informed Flow Transfer framework for one-step generative video compression. At its core, RIFT introduces a Residual Geometry Inducer (RGI) that converts the pretrained flow prediction into a content-adaptive restoration update using decoder-visible codec cues. RGI integrates flow-timestep conditioning with a learned full-band residual-strength estimate and content-conditioned direction and gain modulation, aligning the orientation and magnitude of the update with the compression-dependent residual geometry. Extensive experiments on three public video compression benchmarks show that RIFT outperforms competing generative video compression methods. The code is publicly available on RIFT.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.02206

Validity-Gated Evaluation of Multimodal Machine Unlearning

Abdullah Ahmad Khan, Hamid Laga, Ferdous Sohel

原文摘要

Machine unlearning aims to remove the influence of training data without retraining a model from scratch. Evaluation of vision-language models relies on forget accuracy (FA), retain accuracy (RA), membership inference, and similarity to a retain-only reference, but evaluation pipelines are rarely tested. We propose a validity-gated unlearning audit (VGUA) with three checks: the forget set must be memorized without duplicate leakage into the retain set, the scorer must measure correctness, and the training code must implement the intended procedure. Applying these checks reveals that random MMBench splits leak duplicate questions, a lenient scorer hides memorization, and two coding errors remove the signal while training completes. After correcting these problems, we evaluate 234 unlearned models using six methods, three learning rates, and three backbones. Each model is compared with a retain-only reference trained using low-rank adaptation (LoRA). The results depend on update strength. Among models with RA at or above 0.70, lower FA generally indicates closer agreement with the retrained FA-RA operating point. Aggressive updates overshoot this point, collapse RA, and reverse method rankings. Relative to the original model, 78% of healthy models move closer to the retrained model's scores, whereas 94% move farther from it in activation space. Membership-inference advantage does not reliably track retraining alignment. Under option-shuffled training, unlearned models answer 25% of reordered forgotten ScienceQA questions, compared with 6% for the retain-only reference. These results show that multimodal unlearning conclusions depend on pipeline validity, update strength, and the comparison criterion.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01790

Detection Instead of Inversion: T1-T2 Microstructure Quantification With Detection Transformers

Sebastian Endt, Fatih Özkan, Marion I. Menzel

原文摘要

T1-T2 correlation MRI has strong potential to quantify microstructural compartments without imposing a biological model. Traditionally, full T1-T2 spectra per voxel are reconstructed with an ill-conditioned and time-consuming Inverse Laplace Transform. We propose to view this challenge as an object detection task: A Detection Transformer (DETR) takes 64 TI/TE signals and directly predicts a set of compartments specified by T1, T2, and signal fraction. We achieve a mean average precision mAP@10 of 76.8% on simulated data, outperforming both our previous model design (53.8%) and regularized NNLS (66.1%). We show that our DETR approach outperforms NNLS in almost every setting across compartment count, compartmental signal fraction, and SNR. Reconstruction is orders of magnitude faster than NNLS. The results are fully reproducible from our public code: github.com/SebastianEndtTHI/t1t2-detr

cs.CV · cs.LG · physics.med-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.10575

Acceptance Cards:A Four-Diagnostic Standard for Safe Fine-Tuning Defense Claims

Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz

原文摘要

Safe fine-tuning defenses are often endorsed on the basis of a held-out gap reduction, but the same reduction can come from sampling noise, subject artifacts, capability loss, or a mechanism that does not transfer. We introduce Acceptance Cards: an evaluation protocol, a documentation object, an executable audit package, and a claim-specific evidential standard for safe fine-tuning defense claims. The protocol checks statistical reliability, fresh semantic generalization, mechanism alignment, and cross-task transfer before treating a gap reduction as a full-card pass. Re-scored under this installed-gap protocol, SafeLoRA fails the full-card pass on Gemma-2-2B-it: under strict mechanism-class coding it fails all four diagnostics, and under a permissive shrinkage relabel it still fails three of four. This is a narrow installed-gap audit on one model family, not a global judgment of SafeLoRA's effectiveness. In a 46-cell audit, no cell satisfies the strict conjunction. The closest family is a near miss that passes reliability and mechanism checks where the required data are available, but fails the fresh-subject threshold, lacks a strict transfer pass, and carries a measurable deployment-accuracy cost.

cs.CR · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2509.25808

Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse

Yuheng Zhang, Wenlin Yao, Changlong Yu, Yao Liu, Qingyu Yin, Bing Yin, Hyokun Yun, Lihong Li

原文摘要

Group relative policy optimization (GRPO) trains large language models with verifiable rewards by normalizing rewards within response groups. When every response in a group receives the same reward, the advantages vanish and the group provides no policy gradient signal. We propose Adaptive Rollout and Response Reuse Policy Optimization (AR3PO) to obtain informative groups with fewer generations. Adaptive rollout samples responses to each prompt in stages and stops sampling once the model generates a correct response. If all sampled responses are incorrect, response reuse replaces one of them with a past correct response to the same prompt, when available, and recomputes the group advantages. Policy-recomputed reuse trains on the updated groups using probabilities recomputed under the rollout policy; advantage-only reuse uses historical responses only to compute advantages. Across four mathematical benchmarks with 7B and 8B models, AR3PO consistently improves over GRPO and achieves performance comparable to DAPO while requiring up to $4.2\times$ fewer generated responses. Experiments with a 32B model also show comparable performance to DAPO at a similar training stage with substantially fewer generated responses.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01786

IncVNM: An Interactive Recommender System with Incremental von Neumann-Morgenstern Utility Learning

Jiaxin Wei, Jia Liu

原文摘要

In modern recommender systems, users are often presented with products whose outcomes are random. The values of such products depend on their entire outcome distributions and on users' attitudes toward risk, making them difficult to evaluate using traditional product-level recommendation methods. We propose \textsc{IncVNM}, an interactive recommender system that incrementally learns a user-specific von Neumann--Morgenstern (VNM) utility function from ordinal click feedback generated during ordinary webpage browsing. At each interaction, \textsc{IncVNM} converts the click order within a displayed product list into pairwise comparisons between outcome distributions and updates the nominal utility by minimizing its deviation from the previous estimate while incorporating the newly observed pairwise comparisons. To close the interaction loop, an entropy-regularized sampling policy balances exploitation of the learned utility against exploration for additional preference information. We evaluate \textsc{IncVNM} in a rolling-window experiment with different response-error probabilities and show that it substantially outperforms the expected-return, mean--variance, discounted-UCB, and distribution-aware BPR baselines.

cs.IR · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01785

Rubric-Based Assessment of Student Reports Using Small Language Models

Sandesh Kumar Kafle, Jan Vykopal, Valdemar Švábenský

原文摘要

Language models can analyze and assess student texts using predefined rubrics and deliver structured feedback, reducing instructors' workload. However, existing solutions often rely on external services that are resource-intensive, costly, and raise privacy concerns, making them unsuitable for constrained environments. This study evaluates an automated assessment pipeline with three key aims: design for low-resource environments, privacy, and focus on a novel context in cybersecurity education. The pipeline integrates lightweight language models for textual evaluation and a vision-language model for image interpretation. Responses from 105 students were collected over two semesters of an undergraduate course during a cybersecurity exercise on incident response. Results across different hardware configurations show that small models in low-resource environments can achieve up to 97% accuracy in text-only and up to 94% in rich-text assessments. This rivals or even outperforms a large model while adding the benefits of locally hosted assessment. Our solution can help educators and practitioners who need grading assistance without replacing human oversight, especially in environments where cloud-based solutions may be impractical. This study contributes an open-source, locally deployable AI-assisted scoring pipeline that runs on affordable hardware and can be extended to various types of student reports in computing education. As a result, it makes automated assessment accessible to a broad range of educators and institutions.

cs.CY · cs.CL · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01783

OCBI: Order-Sensitive Cross-Branch Interaction for Image Manipulation Localization

Zhouli Yu

原文摘要

Image manipulation localization combines semantic structure with forensic traces to identify modified pixels. Within-branch spatial mixing and RGB-guided cross-branch mixing can produce different messages when composed in opposite orders. We propose OCBI, an extension of Co-Transformers that models the discrepancy between these two composition orders for localization. A local cross-branch fusion module uses the commutator of RGB-guided cross-attention and forensic self-attention to add a learnable signed correction to feature transfer. Pixelwise adaptive multiscale aggregation then combines spatial contexts before prediction. OCBI uses the Co-Transformers backbone and supervision. We compare OCBI with retrained Co-Transformers using CASIA-only task training, a 50-epoch budget, and final-epoch evaluation. Across five clean test datasets, OCBI achieves a macro PixelF1 of 0.5773, exceeding the baseline by 0.43 percentage points. Under JPEG compression, Gaussian blur, and resizing on three datasets, its average PixelF1 over 21 dataset-transformation conditions exceeds the baseline by 0.95 percentage points.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01778

MemRole: From Memories to Decisions for Long-Horizon Reasoning in Role-Playing Agents

Mengting Li, Xilong Cheng, Zhihao Xiao, Zhenhua Xu, Jingyuan Zhou, Linfeng Li, Long Zhang, Borui Cai 等 9 位作者

原文摘要

LLM-based role-playing agents are fluent at imitating a character's style, yet struggle to make role-consistent decisions over long narrative horizons. Such decisions are shaped by experiences spanning many prior scenes, which are often partial and may point in different directions. Existing methods inject cross-scene memories as context, but do not reason about how past events shape a character's current motivations and behavior. We propose MemRole, a framework that makes this memory-to-decision process explicit. It introduces Long-Horizon Memory Thinking (LHMT), a reasoning schema that decomposes hidden reasoning into context understanding, memory activation, and response strategy planning, trained on a novel-derived dataset whose character-grounded, timeline-constrained memory pools limit each character to what it could plausibly know at the current narrative point. Beyond supervised fine-tuning, we propose Self-Refining On-Policy Self-Distillation (SR-OPSD): the model critiques its own rollouts against the reference under a data-driven rubric, and a critique-conditioned teacher view of the same model distills token-level guidance back into the policy. MemRole-32B improves over its backbone by 15.2 points on memory-grounded role-playing, performs on par with frontier LLMs such as GPT-5.4, and achieves the best character-motivation recognition accuracy on CroSS-MR.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.09025

MedFL-Stress: A Systematic Robustness Evaluation of Federated Brain Tumor Segmentation under Cross-Hospital MRI Appearance Shift

Kiran Naseer, Naveed Anwer Butt

原文摘要

Federated learning lets hospitals train segmentation models without sharing patient data, but standard evaluation reports one number: mean Dice across all sites. That number can look competitive while one hospital runs far behind the rest. Our results suggest this gap is not primarily a federation problem. Under controlled MRI appearance shift on BraTS 2020, even a centralised model trained on all data (single seed) shows a 0.055 best-worst client gap. Under FedAvg, federation adds a further 0.030 on top of that. In our setup, appearance shift accounts for most of the gap and federation widens it. We test five methods - centralised, FedAvg, FedProx, FedBN, and q-FedAvg - under this protocol. q-FedAvg achieves the best worst-client Dice in both full-data and subsampled regimes while also maintaining the highest mean Dice among FL methods: no accuracy-fairness tradeoff in our setting, though its margin over FedAvg is not significant at five seeds (p=0.436). FedProx significantly lowers the worst client across five seeds (p=0.019). Worst-client rankings are identical across both evaluation regimes, but FedBN's worst-client spread across seeds is nearly double FedAvg's - a reliability gap that single-seed evaluation cannot see. MedFL-Stress packages this stress test as a reproducible protocol. The main practical message: report worst-client Dice and confirm rankings across evaluation regimes before drawing conclusions from any FL benchmark.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01775

Spectral Signatures of Memorization Basins in Diffusion Trajectories

Achref Jaziri, Martin Mundt, Ahmed Imtiaz Humayun, Visvanthan Ramesh

原文摘要

Diffusion models are known to reproduce individual examples from their training data as a form of memorization with implications for generalization, privacy, and downstream use. Recent work demonstrated that memorized training samples reside inside contiguous regions of the data/latent space known as basins of memorization -- once a denoising trajectory enters a basin, under finite perturbations it irreversibly reproduces a memorized example. Prior empirical work on such basins in trained models has primarily focused on classifier-free guidance based detection and mitigation strategies in text-to-image models, leaving basin entry and their formation largely uncharacterized. In this paper, we present a geometric characterization of memorization basins for conditional, unconditional, and rectified-flow-based diffusion models. We observe a characteristic signature in the local spectrum of the function geometry that distinguishes basin entry: the emergence of a dominant singular mode followed by a sharp spectral recovery. This signature appears at two timescales: along denoising trajectories during inference and over the course of training. We further investigate whether these geometric signatures can be used to intervene on memorization. During training, we suppress memorization by acting on the dominant mode. At inference, we develop methods to identify trajectories entering memorization basins and steer them away. We find that these interventions remain effective even with low-dimensional approximations of the underlying geometry, and demonstrate that geometry-informed steering extends to large-scale text-to-image diffusion models. Together, our results corroborate that local spectral geometry provides a common basis for characterizing memorization and for suppressing, detecting, and steering away from it across training and generation.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.06884

Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition

Sayantan Choudhury, Xiaoran Cheng, Martin Takáč, Sen Na, Mladen Kolar

原文摘要

Most first-order optimizers treat matrix-valued parameters as vectors, ignoring the intrinsic geometry of hidden-layer weights in neural networks. Muon addresses this mismatch by updating along the polar factor of a momentum matrix, but its theoretical understanding has lagged behind practice. In particular, practical implementations incorporate Nesterov momentum, compute the polar factor only approximately, and operate with stochastic gradients that may be heavy-tailed. We close this gap by developing a convergence theory for Muon with Nesterov momentum and inexact polar decomposition in non-convex matrix optimization under heavy-tailed noise. Our analysis builds on a unified framework for inexact polar decomposition that captures practical iterative approximations such as Newton-Schulz and quantifies how their errors propagate through the optimization dynamics. Under uniform bounds on polar errors, we establish an optimal iteration and sample complexity of $O \left(\varepsilon^{\frac{-(3α-2)}{(α-1)}} \right)$ for finding an $\varepsilon$-stationary point, where $α\in(1,2]$~denotes the heavy-tail index. For the inexact-polar setting with $σ_1=0$, we also provide guarantees that do not require prior knowledge of $α$. We analyze a randomized low-rank polar decomposition that is substantially more efficient than full-space methods while remaining compatible with our theory. Numerical experiments further demonstrate the effectiveness of the proposed inexact and randomized~variants.

math.OC · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.14320

Early Failure Detection and Intervention in Video Diffusion Models

Byungki Kwon, Sohwi Lim, Nam Hyeon-Woo, Moon Ye-Bin, Tae-Hyun Oh

原文摘要

Text-to-video (T2V) diffusion models have rapidly advanced, yet generations still occasionally fail in practice, such as low text-video alignment or low perceptual quality. Since diffusion sampling is non-deterministic, it is difficult to know during inference whether a generation will succeed or fail, incurring high computational cost due to trial-and-error regeneration. To address this, we propose an early failure detection and diagnostic intervention pipeline for latent T2V diffusion models. For detection, we design a Real-time Inspection (RI) module that converts latents into intermediate video previews, enabling the use of established text-video alignment scorers for inspection in the RGB space. The RI module completes the conversion and inspection process in just 39.2ms. This is highly efficient considering that CogVideoX-5B requires 4.3s per denoising step when generating a 480p, 49-frame video on an NVIDIA A100 GPU. Subsequently, we trigger a hierarchical and early-exit intervention pipeline only when failure is predicted. Experiments on CogVideoX-5B and Wan2.1-1.3B demonstrate consistency gains on VBench with up to 2.64 times less time overhead compared to post-hoc regeneration. Our method also generalizes to a higher-capacity setting, remaining effective on Wan2.1-14B with 720p resolution and 81-frame generation. Furthermore, our pipeline is plug-and-play and orthogonal to existing techniques, showing seamless compatibility with prompt refinement and sampling guidance methods. We also provide evidence that failure signals emerge early in the denoising process and are detectable within intermediate video previews using standard vision-language evaluators.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01769

Silent Reward and Environment Defects in EV Charging Simulation Benchmarks: A Diagnostic Checklist

Nour-Eddine Moumni, Rachid Alaoui, Driss Kiouach

原文摘要

Reinforcement-learning (RL) benchmarks built on microscopic traffic simulators such as SUMO are increasingly used to compare agent architectures for electric vehicle (EV) charging assignment. Unlike crashes, defects in the reward function, the environment's stochastic model, or the state encoding often fail silently: the simulation completes, produces plausible numbers, and the comparison is biased. We report five such defects, found by auditing a five-agent benchmark on OpenStreetMap road networks, stated generically: a shared random generator that desynchronises seed-paired comparisons, an ablation-specific reward clip applied unconditionally, a normalisation mismatch that zeroes a reward term, a per-timestep penalty that should fire once per event, and a state dimensionality documented but never wired into the network. We quantify three: a rejection counter inflated up to 125x across agents/cities, a reward term bounded at about $10^{-4}$ of its intended scale, and a 16.6%/16.3% greedy-action divergence from a state-encoding mismatch. Re-analysing a historical ablation, no A1-A2 effect survives family-wise correction; a 56-run campaign confirms the RNG defect's mechanism directly while showing its correction does not change that conclusion. We provide an eight-item checklist as a low-cost first-pass audit; in a later regeneration, three checks caught two new defects while three further process/artefact defects fell outside its boundary.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.38356

Encode Once, Answer Many: Internalizing Context via Parametric Flow

Xinhao Zhong, Mengxuan Wu, Chonghua Liao, Linxi Xie, Ruicheng Feng, Kangqiao Xu, Yanpei Guo, Hao Tan 等 26 位作者

原文摘要

Large language models are typically adapted to a task either by placing knowledge in the input context, which keeps it external and re-encodes it on every call, or by fine-tuning, which internalizes it but demands a costly round of optimization per task. We aim to internalize the knowledge carried by a context directly into model parameters, without per-task optimization and without keeping the context in the input at inference time. To this end, we propose CLIK, a context-conditioned parameter generator that maps a given context to LoRA parameters for internalizing knowledge in a single forward pass through a Transformer encoder with cross-attention, requiring no test-time gradient updates. Once the generated LoRA is inserted into a frozen base model, the model answers downstream queries from the query alone, having internalized the context into its weights rather than re-reading it. Because the adapter depends only on the context, it is generated once and reused for every query on the same document, so the cost of reading that document is amortized across queries. On document question answering, CLIK substantially improves over the no-context base model and outperforms existing hypernetwork-based generators, while remaining behind a base model that reads the context directly, and it carries over to multi-turn dialogue without any multi-turn-specific training. Analysis further shows that the context-dependent part of the generated adapter concentrates in a compact and specific substructure.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01765

FinishStrong: Learning to End Well after Imperfect Start in Video Temporal Grounding

Yuda Zou, Boxiang Zhou, Xin Zhou, Yibo Chen, Dejia Song, Xu Tang, Yao Hu, Yongchao Xu

原文摘要

A poor start lowers the ceiling, but does not negate the value of finishing well. In autoregressive video temporal grounding, models systematically exhibit an endpoint performance asymmetry, predicting ends significantly worse than starts. A committed flawed start acts as an immutable physical constraint, irreversibly capping the attainable overlap as a sunk loss. While models should minimize the remaining conditional regret, standard post-training paradigms fail to teach this adaptation. Specifically, teacher-forced SFT suffers from strict prefix exposure bias, and holistic trajectory evaluation in standard GRPO inadvertently penalizes conditionally optimal ends if they follow a poor start. To address this, we introduce FinishStrong, a novel two-stage post-training framework explicitly designed to teach optimal continuations. First, Online-start SFT exposes the end prediction to the model's own generated contexts. Second, Conditional-tree GRPO restructures the sampling topology, centering end rewards exclusively within the same-start branch to mathematically isolate the conditional end quality from the inherited start penalty. FinishStrong-9B achieves a state-of-the-art 61.7\% overall IoU on TimeLens-Bench, remarkably outperforming flagship closed-source models like Gemini-3.8-Flash and Qwen3.8-Max. Crucially, when forced to continue from imperfect starts, it reduces the subsequent end prediction error by 36.5\%, proving its exceptional ability to end well after flawed starts. Code will be open.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.10634

Teacher-Aware Evolution of Heuristic Programs from Learned Optimization Policies

Minyu Chen, Song Qin, Ling-I Wu, Jianxin Xue, Guoqiang Li

原文摘要

LLM-based automatic heuristic design has shown promise for generating executable heuristics for combinatorial optimization, but existing methods mainly rely on delayed endpoint performance. We propose a \emph{teacher-aware evolutionary framework} that uses independently trained learned optimization policies as behavioral teachers. Instead of deploying or imitating the teacher, our method queries it on states visited by candidate heuristic programs and uses its action preferences as local feedback for evolution. The resulting search discovers static executable heuristics guided by both task performance and teacher-derived behavioral signals. Experiments on scheduling, routing, and graph optimization benchmarks show that our method improves over performance-driven LLM heuristic evolution baselines while requiring no neural inference at deployment. These results suggest that learned optimization policies can be repurposed as behavioral feedback sources for automatic heuristic discovery.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.37687

WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation

Muhammad Huzaifa, Lea Schönherr, Thorsten Eisenhofer

原文摘要

Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively querying supervision. However, most existing ATTA methods implicitly assume that supervision can be requested for every incoming test batch, which can incur substantial annotation cost over long test streams. In this work, we introduce budgeted ATTA in which labels are available for only a fraction of test batches. This formulation shifts the central challenge from deciding what to label within a batch to deciding when supervision should be applied over time. To address this challenge, we propose a budget-aware approach WISE-ATTA that allocates supervision over the test stream based on lightweight signals computed online, prioritizing periods where supervision is likely to be most useful. When a batch is selected for supervision, we further employ a drift-based sample selection criterion that targets samples exhibiting ongoing, unconverged adaptation dynamics, enabling effective updates from a single labeled example. We evaluate this approach on synthetic corruptions (ImageNet-C) and natural distribution shifts (ImageNet-R/K/A). Across settings, WISE-ATTA achieves competitive or improved performance compared to recent ATTA methods while requiring substantially fewer labels. Overall, we find that the timing of supervision is a key, yet underexplored, aspect of active test-time adaptation. Code: https://github.com/Muhammad-Huzaifaa/WISE-ATTA

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01759

Teleoperation System for Service Robots using Virtual Reality Headset and Pose Estimation

Eduardo Fernandes, Tiago Ribeiro, Antonio Ribeiro, Carolina Lopes, Gil Lopes, Fernando Ribeiro

原文摘要

This paper presents a teleoperation system for service robots that integrates human pose estimation with virtual reality (VR) to enable intuitive remote control. By using the Mediapipe framework for 2D pose detection and extending it with RGB-D data from the Intel RealSense D455 camera, a comprehensive 3D human pose estimation is achieved. This data is then mapped to the robot's kinematics, allowing the operator to control the robot's movements naturally. A VR interface was developed to provide an immersive perspective, enhancing the operator's situational awareness. Real-world experiments were conducted using the CHARMIE service robot to validate the system's effectiveness in tasks involving object manipulation. While the current system successfully demonstrates the potential of VR-based teleoperation, challenges remain in accurately capturing certain joint angles (e.g., wrist yaw) and ensuring precise mapping between human and robot movements. Future work includes the integration of inertial measurement units (IMUs) for improved rotational tracking and the implementation of more advanced control algorithms. Overall, this research contributes to the development of more intuitive and effective teleoperation systems for service robots, facilitating their deployment in complex and dynamic environments. This work further introduces a novel approach to teleoperation by combining RGB-D sensing with an innovative algorithm for real-time joint angle computation using Mediapipe, enhancing the precision of human-robot motion mapping and enabling immersive control through a VR interface. These contributions represent significant advancements in the field of human-robot interaction, particularly for service robot applications.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01755

A Bounded Evaluation Protocol for Representational Systematicity

Boyu Cao, Wenshuo Wang

原文摘要

Multiple studies have shown that neural networks can be behaviorally systematic, producing correct outputs for novel combinations of familiar parts. Whether they are also representationally systematic, that is, whether they represent these parts and their roles and use them to produce the outputs, remains hard to test, because each kind of evidence can mislead on its own: correct outputs can come from shortcuts, a decodable signal need not be used, an intervention can act through unintended pathways, and a failed search does not show absence. We propose a bounded evaluation protocol for representational systematicity (Bounded-RS): for an explanation that attributes a systematic behavior to a declared representation, it tests on a matched behavioral contrast whether that representation is recoverable and whether it is causally used, checks the validity of this evidence, and assigns the explanation one of four bounded states, Unsupported, Present-only, Causal-use, or Undetermined, through control-calibrated scores, gates, and stop rules. On a semantic-parsing testbed of 96 matched sets that we release, the tested role-filler Binding explanation of fine-tuned T5 models is Causal-use and the distributed Geometry explanation is Unsupported within its declared search space, verdicts that hold across calibration-compatible parameter configurations, training seeds, and T5-base. On 41 cases with known causal status, full adjudication licenses a false Causal-use in 1 of 34 noncausal cases, against 13 when recoverability is taken as use, without missing any causal case. Bounded-RS thus turns the question of representational systematicity, debated since Fodor and Pylyshyn, into comparable and falsifiable verdicts on declared explanations, each reported with the evidence pattern that licenses it and, for a negative, the search space that bounds it.

cs.CL

查看论文
arXiv ↗PDF ↗