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

+1673新增论文
+1257其中 AI 相关
+198已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-14 05:55 · 全站最近入库：2026-11-13 20:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-13 06:35 — 2026-11-14 06:35（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：2026-11-14 05:55最近发现新增版本：2026-11-13 20:44库内论文最新更新时间：2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,727 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 17,362 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-14 05:54（北京时间）
版本更新 · v2arXiv:2609.31016

Robust Successor Features

Erik Nikulski, Yamen Habib, Vicenç Gomez, Anders Jonsson, Rubén Moreno-Bote, Javier Segovia-Aguas

原文摘要

Generalization in Reinforcement Learning (RL) refers to the ability to execute close-to-optimal policies in unseen tasks after the agent has been trained on a different set of tasks. Building on the seminal work of the successor representation and further adaptations with function approximation, Transfer in RL has traditionally focused on generalizing to tasks that only differ in the reward function. A decade after the introduction of the successor representation, Robust RL emerged simultaneously from several articles in the field of operations research. In Robust RL, the transition kernel is unknown, and the goal is to maximize the expected reward under this uncertainty. Our work unifies these two paradigms through robust successor features, which generalize across both the reward function and the transition kernel, under the assumption that tasks are linear Markov Decision Processes. We derive a bound on Generalized Policy Improvement (GPI) that explicitly quantifies how performance degrades with the mismatch between transition kernels, recovering existing successor-feature guarantees when dynamics are shared. Finally, the generalization capabilities of robust successor features are validated on several grid-based benchmarks and compared to previous alternatives that focus solely on either the reward or the transition kernel.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06374

Corralling AI Risks with Grassroots Contracts

Ehud Shapiro

原文摘要

AI's inflection point is a fountain of alarming risks. Digital platforms in particular are vulnerable to three major AI risks, as those in control of global platforms cede control to AI, of the algorithms, of membership and of content: (1) AI control of global platforms, social and economic, used by the majority of humanity, resulting in the majority of humanity becoming vulnerable to AI control. (2) Unaccountable AI agents operating anonymously on social and economic digital platforms, side-by-side with humans, possibly masquerading as humans, serving unknown masters with unknown goals, operating under unknown restraints without accountability or culpability. (3) Unattributed deepfakes generated by anonymous AI, with people unable to distinguish them from genuine content and with their producers evading accountability and culpability. Here, we propose to corral these AI risks with grassroots contracts, a digital incarnation of a two-centuries old notion of Pierre-Joseph Proudhon. We present grassroots contracts for a social graph with accountable AI agents and for a social network with digital provenance, and working smartphone apps that implement the two and show how they corral these major AI risks: (1) AI control of global platforms. (2) Unaccountable AI agents. (3) Unattributed deepfakes.

cs.AI · cs.CL · cs.DC · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06373

Reassessing Dataset Quality and Fine-Tuning Practices for Vulnerability Detection on PrimeVul dataset

Norbert Sándor Szolnoki, Gábor Antal

原文摘要

Recent studies report promising results from supervised fine-tuning of pre-trained code language models for automated vulnerability detection on benchmarks such as PrimeVul. In this paper, we present a large-scale empirical evaluation of both model performance and dataset quality in this setting. We systematically fine-tune three widely used encoder models (CodeBERT, GraphCodeBERT, and UniXCoder) across five imbalance mitigation strategies, extensive hyperparameter sweeps, and multiple random seeds, resulting in 770 independent training runs. Our results reveal a consistent pattern. While standard metrics such as F1 and ROC-AUC occasionally suggest improvements, security-critical and calibration-aware measures tell a different story. Matthews Correlation Coefficient remains near zero, predicted probabilities are poorly calibrated, and evaluation under strict false-positive constraints reveals high false-negative rates. Neither imbalance handling, threshold optimization, nor post-hoc calibration recovers a meaningful discriminative signal. We also conduct a data quality assessment of the PrimeVul benchmark and identify structural issues such as minimal semantic differences between vulnerable and fixed functions, and annotation noise introduced by commit-level labeling. These findings suggests that the PrimeVul dataset, in its current form, presents significant challenges for reliable AI-based vulnerability detection in software engineering with the methodologies we used. Our study highlights the need for more robust dataset design, improved evaluation protocols, and rethinking of fine-tuning practices for security-critical tasks.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.21809

From Adults to Children: Benchmarking Foundation Models for Chest X-Ray Classification under Domain Shift

Sara Inácio, Hugo Proença, João C. Neves

原文摘要

Foundation models have shown significant potential across diverse fields and have been applied to medical imaging, but their robustness across patient populations remains unclear. In this work, we investigate foundation models' ability to generalize from adult to pediatric chest X-ray classification. To the best of our knowledge, this is the first benchmark to compare multiple foundation models under a common adult-to-pediatric evaluation setting while also analyzing the effect of adaptation depth. We harmonize VinDr-CXR and PediCXR into a five-label classification task and evaluate six foundation models and two CNN baselines. All models are adapted using adult data only and tested in both the in-domain and pediatric domains using linear probing, partial fine-tuning, and full fine-tuning. The benchmark reveals a clear and consistent trend: all models suffer a substantial performance degradation when transferred from adult to pediatric data, with drops exceeding 10 percentage points. While Macro-AUROC values reach approximately 92% on the adult test set, performance decreases to around 78% on the pediatric domain. Another important finding is that increasing the depth of adaptation improves pediatric performance on average, although the effect varies across models. Moreover, strong in-domain performance does not necessarily indicate greater robustness to domain shift.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06372

Give Up to Get More: Priors, Not Policies, Govern Test-Time Compute Allocation

Jinhyung Bae

原文摘要

When many inputs share a budget of repeated attempts by a large language model (LLM), a common rule gives harder inputs more. On public math, code and formal-proof samples, the best published difficulty-proportional rule captures half or more of the oracle gain on benchmarks the model mostly solves, but at most 13% on hard workloads, even given true pass rates. Because the value of one more attempt peaks at intermediate difficulty, the optimal static allocation is inverted-U and gives little to inputs that are hopeless at the current budget. In a strict survey of 221 LLM allocation papers, at least 13 give the hardest inputs the most attempts; their easier settings sit at budgets where this is near-optimal, so the cost appears on harder workloads. Acting on it requires knowing which inputs are solvable, so information, not the policy, drives the gain. With a verifier and a prior from a related model's past runs on the same inputs, Thompson Sampling raises the solved share on the hardest workload from 14% to 27%; without such a prior, no policy we tested beats round-robin. For the policies we tested, the gain vanishes between prior rank correlations of about 0.3 and 0.55, which cheap text-based priors barely reach on the weakest models, and it requires a verifier whose false acceptances are rare relative to the pass rate. On new Qwen2.5 samples the pattern holds, and tempering the prior avoids losses on easy workloads. We turn these results into a decision guide.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06371

Training-Free Character-Length Control in Summarization with Diffusion Language Models

Steffen Castle, Nils Feldhus, Christopher Ebert, Leonhard Hennig, Sebastian Möller

原文摘要

Summarization with a fixed character length is important for tasks such as headline and article preview generation, where text must fit an exact space. Autoregressive language models (LMs) struggle with precise character-length control: training-based methods require task-specific fine-tuning, while zero-shot prompting strategies achieve only approximate compliance. We propose DELTA (Diffusion Expected Length Targeting Algorithm), a training-free inference-time method for masked diffusion LMs that estimates expected character length at each denoising step and dynamically inserts or removes masked positions to steer toward a target length. DELTA requires no fine-tuning and is designed for off-the-shelf masked diffusion LMs. Across three summarization benchmarks, it reduces character-length errors by an order of magnitude compared to baselines while maintaining competitive summary quality in both automatic and human evaluation.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2607.07779

From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier

Eric Jiang, Xiao Liang, Junyi Zhang, Justin Baker, Zhi Zhang, Yingjia Wan, Yubei Li, Jinxi Yu 等 41 位作者

原文摘要

Large language models have made rapid progress in generating machine-checked proofs for well-defined mathematical problems. Extending this progress to research mathematics requires more than solving isolated theorems. Research involves choosing questions, developing definitions and conjectures, connecting results, and combining formal proofs with expert judgment. This survey examines how LLM-driven systems can support these broader activities. We review formal-mathematics tasks, datasets, and autoformalization, and organize proof-generation methods into three overlapping areas: training strategies, inference-time search and adaptation, and agentic workflows. We then examine benchmark results, selected research projects, and platforms for collaborative mathematical work. A central distinction runs throughout the survey: checking a formal proof does not by itself establish that it captures the intended problem or makes a new mathematical contribution. We therefore distinguish theorem benchmarks, repository tasks, formalization projects, and research claims, and discuss the evidence needed to assess each. Finally, we identify five priorities for progress: better data and evaluation, representations of mathematical relationships, conjecture and concept generation, reliable tool integration, and human--AI collaboration. Together, these perspectives connect advances in proof generation to the practical demands of mathematical research.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06364

Estimating the Volume of a Union of Convex Bodies

Eeshan Banerjee, Aranya Kumar Bal, Debabrota Basu, Sourav Chakraborty, Debarshi Chanda, Uddalok Sarkar

原文摘要

The \textit{Union Volume Estimation problem}, i.e. yielding an $(\varepsilon, δ)$-approximation of the volume of the union of convex bodies, is a classical problem in computational geometry and formal methods. In this paper, we first detect where and why the efficient union volume estimators with approximate sampling and PAC volume estimation oracles fail. Specifically, we show that having only TV-distance guarantees on the approximate sampler does not suffice, and demonstrate this bottleneck by constructing the sunflower families of convex bodies. In this context, we propose the concept of \textit{tail-controlled samplers} that can yield with high-probability almost-$\ell_{\infty}$ closeness. Secondly, we leverage this concept to propose a generic algorithmic framework \texttt{Alpona} that properly combines a PAC volume computation and approximate point sampling oracles with tail-controls to yield an $(\varepsilon, δ)$-estimate of the union volume for any collection of convex bodies. We show that \texttt{Alpona} needs only linear (in number of convex bodies) oracle calls to be $(\varepsilon, δ)$-correct. Finally, we provide a tail-controlled analysis of the Hit-and-Run sampler~\citep{lovasz2006fast}. We further provide a novel geometric analysis to improve the required walk length of Hit-and-Run. We further instantiate \texttt{Alpona}'s correctness for the sparse frequency streams of convex bodies: a special case of the union volume estimation problem where no convex body intersects more than $τ$ many other bodies.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.24033

Event-based SLAM Benchmark for High-Speed Maneuvers

Sheng Zhong, Junkai Niu, Guillermo Gallego, Kaizhen Sun, Yang Yi, Zhiqiang Miao, Dewen Hu, Yaonan Wang 等 10 位作者

原文摘要

Event-based cameras are bio-inspired sensors with pixels that independently and asynchronously respond to brightness changes at microsecond resolution, offering the potential to handle visual tasks in high-speed maneuvering scenarios. Existing event-based approaches, although successful in mitigating motion blur caused by high-speed maneuvers, suffer from many limitations. Some of them highlight a success of pose tracking for a fronto-parallel fast shaking camera closed to the structure, while others assume pure (optionally aggressive) three-degree-of-freedom rotations. The former requires persistent local map visibility within the field of view (FOV), whereas the latter fails to generalize to six-degree-of-freedom (6-DoF) motions where both linear and angular velocities may be large. Consequently, current successes do not fully demonstrate that event-based state estimation under arbitrary aggressive maneuvers is a fully solved problem. To quantitatively assess the extent to which the potential of event cameras has been unlocked, we conduct a thorough analysis of state-of-the-art (SOTA) event-based visual odometry (VO)/visual-inertial odometry (VIO) methods and report shortcomings in current public datasets. Furthermore, we introduce a benchmarking framework for event-based state estimation, called EvSLAM, characterized by sufficient variation in data collection platforms, diverse extreme lighting scenarios, and a wide scope of challenging motion patterns under a clear and rigorous definition of high-speed maneuvers for mobile robots, along with a novel evaluation metric designed to fairly assess the operational limits of event-based solutions. This framework benchmarks state-of-the-art methods, yielding insights into optimal architectures and persistent challenges.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.07865

KL for a KL: On-Policy Distillation with Control Variate Baseline

Minjae Oh, Sangjun Song, Gyubin Choi, Yunho Choi, Yohan Jo

原文摘要

On-Policy Distillation (OPD) has emerged as a dominant post-training paradigm for Large Language Models, especially in reasoning domains. However, OPD remains unstable in practice due to the high gradient variance of its single-sample Monte Carlo estimator, and recipes for stable training are still immature. We propose vOPD (On-Policy Distillation with a control variate baseline), which casts OPD as policy-gradient RL and stabilizes it by introducing a control variate baseline---canonically a value function---from the RL literature. We show that the OPD value function admits a closed form: the per-token negative reverse KL divergence between student and teacher, available directly from the existing forward pass with no additional critic or inference. Existing stabilization methods either compute the full token-level reverse KL over the entire vocabulary, adding significant overhead, or restrict it to a top-k support, biasing the objective. vOPD instead preserves the lightweight single-sample estimator and subtracts the value function as a detached baseline to keep the gradient unbiased while reducing variance. Moreover, we show that a top-k approximation of the baseline further lowers cost without compromising performance. Across mathematics, science, and instruction-following benchmarks, vOPD consistently outperforms base OPD and matches the most expensive full-vocabulary method, offering an efficient stabilization of OPD through principled RL variance reduction.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06359

Vortex-Induced Torque in Grasping Soft Objects: Influence of Geometry and Pneumatic Parameters

Roman Mykhailyshyn, Tomohiro Motoda, Ivan Virgala, Ann Majewicz Fey, Yukiyasu Domae

原文摘要

Vortex grippers are commonly integrated into automated systems for handling objects with complex geometries in packaging, sorting, and assembling. However, their interaction with compliant objects remains difficult to predict, particularly with respect to the vortex-induced torque transmitted during grasping. This study investigates vortex-induced torque during the grasping of compliant objects and quantifies the coupled effects of supply pressure, tangential nozzle diameter, surface geometry, and curvature. The results show that increasing the tangential nozzle diameter primarily enhances the sensitivity of the generated torque to supply pressure rather than producing a uniformly higher torque. Surface geometry also strongly influences the rotational interaction, with dome-concave surfaces generally producing substantially greater torque than corresponding dome-convex surfaces, whereas the difference between cylindrical concave and convex surfaces is comparatively small. The strongest and most repeatable response was observed for a dome-concave surface exhibiting favorable object-gripper geometric matching. Among the evaluated machine-learning regression methods, Gaussian Process Regression provided the best overall predictive performance under repeated cross-validation, demonstrating that vortex-induced torque can be estimated from combined pneumatic and geometric parameters. These findings provide a basis for predicting and utilizing vortex-induced torque in the dexterous manipulation of soft objects.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06358

Keeping Fuzzers on Duty: Repairing Fuzzing Build Breakages in Continuous Open-Source Fuzzing

Zhuang Zhao, Jiongchi Yu, Yao Zhang, Dongge Liu, Qiang Hu, Xiaohong Li, Yang Liu

原文摘要

Continuous fuzzing platforms such as OSS-Fuzz provide sustained security testing for open-source projects, but long-term build breakages reduce security coverage and waste infrastructure resources. In OSS-Fuzz, around 20% of integrated projects remain in build-failure states, leaving their fuzzers off duty. These failures expose a maintenance gap between platform maintainers, who lack project-specific context, and project maintainers, who often lack fuzzing and infrastructure expertise. Existing program-repair techniques cannot be directly applied because fuzz build breakages span evolving project and infrastructure artifacts and require repeated infrastructure-aware diagnosis. We present FuzzMedic, an automated agent for fuzz build repair. FuzzMedic performs evidence-guided diagnosis across project and fuzzing-infrastructure artifacts. It explores repairs over a repair-state graph (RSG) that records the evolving workspace and build feedback. Branching and rollback enable FuzzMedic to recover from unproductive repair paths during long-horizon debugging. Candidate patches are validated to restore executable fuzz targets rather than merely suppress build failures. We evaluate FuzzMedic on 128 reproducible OSS-Fuzz build failures extracted from 1,820 real-world failures. FuzzMedic achieves a 48.44% repair rate and outperforms three representative program-repair baselines. In real-world use, it produces 29 patches merged into upstream or OSS-Fuzz main branches, including repairs for three failures that had remained unresolved for more than one year and two cases that had never built successfully.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.02313

From Outcome to Representation: Tracing Reasoning Mechanisms through Integrated Policy Gradient

Changming Li, Kaixing Zhang, Haoyun Xu, Yingdong Shi, Zheng Zhang, Kaitao Song, Kan Ren

原文摘要

Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, yet the internal mechanisms driving these multi-step processes remain opaque. Existing mechanistic interpretability approaches often rely on superficial text-pattern co-occurrences or capture only short-term effects, struggling to trace the long-horizon, outcome-driven influence of internal components such as neurons or sparse features in multi-step reasoning.In this paper, we introduce Integrated Policy Gradient (IPG), a novel, training-free framework that brings policy-based attribution into mechanistic interpretability for LLM reasoning. Grounded in \textit{outcome-oriented} and \textit{sequential-influence-aware} principles, it backpropagates outcome-level, non-differentiable behavioral signals (e.g., reasoning outcome correctness) through entire inference trajectories, utilizing path integration to isolate outcome-relevant mediators at component level for reliable attribution. This provides a linear approximation of Causal Mediation Analysis (CMA) in reasoning. Empirical evaluations demonstrate that \method achieves precise localization and reveals mechanistic insights by identifying sparse, concentrated subsets of internal components associated with specific reasoning behaviors. Our method also enables modulation of reasoning capabilities, offering a powerful and reliable framework for understanding LLM reasoning. The project page is at https://foundation-model-research.github.io/IPG .

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06355

FlashRelight: Portrait Video Relighting with Dynamic Lighting

Jiahui Sheng, Le Li, Limin Lin, Jiahao Li, Wansen Feng, Hong Gu, Shuhan Chen, Xiaorun Li 等 9 位作者

原文摘要

Portrait video relighting aims to modify the illumination of a portrait video while preserving photorealism and temporal stability. The task becomes particularly challenging under dynamic lighting, where illumination direction, intensity, and color vary over time. To tackle this problem, we introduce FlashRelight, a novel two-stage framework for dynamic portrait video relighting. FlashRelight first suppresses the source illumination through delighting, and then synthesizes the target dynamic lighting on an illumination-neutral portrait video. FlashRelight supports three complementary control modalities: envmap sequences for explicit frame-level lighting control, dynamic lighting text for semantic illumination editing, and lighting reference videos for visual lighting transfer. Training follows a low-cost hybrid strategy that combines static one-light-at-a-time (OLAT) data with generated dynamic-lighting portrait videos, covering both controlled illumination variation and realistic portrait motion. Extensive experiments show that FlashRelight achieves temporally coherent and photorealistic dynamic relighting while enabling flexible cross-video lighting transfer. Code is available at https://github.com/vivoCameraResearch/FlashRelight

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06353

Traffic-VL: Reinforced Vision-Language Models for Generalizable End-to-End Traffic Signal Control

Xingchen Zou, Maonan Wang, Kemou Jiang, Jie Li, Yiqi Chen, Xi Chen, Hai Yang, Yuxuan Liang

原文摘要

Existing traffic signal control methods typically rely on structured traffic states produced by dedicated perception pipelines. Emerging visual approaches often use idealized simulator images and convert them into intermediate representations before control, limiting their ability to directly exploit roadside visual observations. To bridge both the visual-domain and perception-to-decision gaps, we introduce SynTra-V and Traffic-VL. SynTra-V converts physics-based traffic simulations into photorealistic multi-view surveillance imagery across diverse road topologies and sensing conditions, and automatic semantic auditing checks that control-critical geometry, vehicle movements, and lane semantics match the simulator state. Traffic-VL is an eight-billion-parameter vision-language model that directly maps synchronized multi-view images and natural-language phase descriptions to signal decisions without intermediate structured states. Building on Traffic-R1's two-stage reinforced reasoning framework, Traffic-VL adapts its vision encoder via offline reinforcement learning on SynTra-V and freezes it during online visual stepwise trajectory policy optimization in closed-loop simulation. Experiments show that Traffic-VL matches structured-state Traffic-R1 while outperforming image-based controllers and general-purpose vision-language models, including Gemini 3 Pro. Evaluations on unseen topologies, degraded sensing conditions, real surveillance footage, and a three-week deployment across ten intersections further demonstrate robust visual generalization and effective constrained online control.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06350

On Existence and Computational Complexity of Quasi-strict Equilibria

Kristoffer Arnsfelt Hansen, Xinhao Nie

原文摘要

Quasi-strict Nash equilibrium, introduced by Harsanyi in 1973, is the Nash equilibrium refinement that requires every pure best response to be played with positive probability. Norde established that any bimatrix game admits a quasi-strict Nash equilibrium. We give a substantially simpler proof of this result that in particular avoids an intricate limit argument used in the final step of the proof by Norde. Our existence proof allows us to positively resolve the outstanding open question of PPAD membership of the problem of computing a quasi-strict Nash equilibrium, thereby settling its precise complexity. In games with three or more players, a quasi-strict Nash equilibrium is not guaranteed to exist, leading to the natural problem of deciding the existence of a quasi-strict Nash equilibrium in a given strategic form game. We show that this problem is $\exists\mathbb{R}$-complete, strengthening a previous NP-hardness result.

cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06349

PMRecBench: A Benchmark for Personalization in Recommendation Agents under Multimodal Queries

Xiaoyu Zhang, Yougang Lyu, Bin Wu, Sahan Bulathwela, Emine Yilmaz

原文摘要

On Web platforms for shopping and entertainment, recommendation agents under multimodal queries aim to deliver personalized recommendations that satisfy users' visually specified requirements and reflect preferences inferred from user histories. However, existing personalized recommendation benchmarks use text-only queries, while multimodal ones assess query matching without evaluating personalization based on real user histories. We introduce the Personalized Multimodal Recommendation Benchmark (PMRecBench), the first benchmark to evaluate the personalization of recommendation agents under multimodal queries. It pairs 510 quality-controlled image-text queries across clothing and movies with the corresponding users' real histories. PMRecBench features two key designs: (1) queries derived from consistent behavioral patterns in real user records, with reference images and targets linked to actual interactions; and (2) challenging diagnostic pools with candidate items rated highly by the user but violating requirements, and items satisfying requirements but never rated highly, testing requirement understanding and preference following, respectively. Extensive experiments on diagnostic pools reveal a personalization imbalance in recommendation agents: relative to personalization signals alone, adding multimodal queries weakens preference following, even though the additional information about query requirements improves overall ranking performance. Further analysis links this decline in preference following to image interpretation, where agents can prioritize resemblance to reference images over evidence from user histories, and stronger commercial backbones alone fail to resolve this imbalance. This personalization imbalance highlights a central challenge for recommendation agents: improving ranking performance while preserving preference following when responding to multimodal user queries

cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.04253

UMLoad: Fast On-Demand Model Loading on Unified Memory Architecture

Zimeng Wang, Jinrong Yang, Rong Chen

原文摘要

On-demand model loading dominates response latency for interactive on-device AI, yet unified memory architectures (UMAs), now common on edge devices, should make it cheap by placing weights in memory the GPU already sees. However, frameworks still use the loading flow built for discrete GPUs, leaving significant inefficiencies. This paper presents UMLoad, a system-level model-loading accelerator that decouples a framework's logical allocations from their physical page backing. UMLoad uses on-demand reconstruction to eliminate the weight copy while preserving copy independence, and GPU-assisted page zeroing to accelerate runtime allocation while preserving its security guarantee. Implemented on Intel, AMD, and NVIDIA UMA platforms and evaluated with llama$.$cpp, PyTorch, and vLLM across six models, UMLoad reduces average loading time by 36.6%-71.9% over vanilla and 19.9%-62.7% over pipelined loaders, and cuts mean LLM-routing time to first token (TTFT) by 51.3%-59.3% and model-backed tool completion latency by 10.2%-31.6%.

cs.OS · cs.AR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.26757

Batch-Invariant Spectral Intelligence for Robust and Explainable Insect Authentication

Majharulislam Babor, Giacomo Rossi, Annalisa Altavilla, Oliver Schlüter, Marina M. -C. Höhne

原文摘要

Edible insects offer an efficient source of alternative protein, requiring less land and water and emitting less greenhouse gas than conventional livestock. However, their successful integration into the food supply chain demands reliable species authentication to control allergen exposure, prevent adulteration, and meet regulatory standards. Near-infrared spectroscopy provides a rapid analytical tool, but its performance drops when applied to production batches unseen during training due to batch-to-batch variation in spectral measurements. We introduce the Batch-Invariant Spectral Network (BISN), an end-to-end framework that combines a learnable preprocessing module, initialised with Savitzky-Golay filtering, with an unsupervised, entropy-regularised auxiliary branch connected through a gradient reversal layer. The branch uses no batch labels and supplies opposing entropy gradients to the auxiliary head and preprocessing module. Using 2,700 spectra from three species (Acheta domesticus, Hermetia illucens, and Tenebrio molitor) collected across three independent production batches, BISN achieves a mean leave-one-batch-out accuracy of 0.93 (standard deviation 0.04), outperforming the strongest baseline by four percentage points (p=0.002). Further insights gained by using explainable AI confirm that model decisions consistently rely on the lipid and protein absorption regions across all folds, connecting predictive performance to known insect biochemistry. BISN addresses both cross-batch robustness and biochemical interpretability for automated insect species authentication in a controlled benchtop setting. The source code and dataset are publicly available at https://github.com/majharB/bisn.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.04527

Future Representation Distillation for Imagination-free World Action Models

Jaehyeong Jo, Sangwon Jang, Sihyun Yu, Seonghyeon Ye, Yekyung Nah, Hojung Jung, Kimin Lee, Sung Ju Hwang

原文摘要

World Action Models (WAMs) use the predictive knowledge of pretrained video diffusion models for robot control through future video prediction. However, iterative video denoising is costly, and inaccurate visual predictions can compromise action prediction. Our key idea is to make this predictive knowledge available through visual representations computed from the current observation, enabling action prediction without generating future videos. We introduce DreamFree, a WAM that repurposes a pretrained video diffusion model as a predictive visual encoder through representation distillation. The visual encoder learns to predict a frozen video diffusion model's representation using only the current observation. An action module is then trained to predict actions by extracting action-relevant information from the visual encoder. Across real-world and simulated tasks, DreamFree achieves higher success rates than state-of-the-art VLAs and WAMs, while performing real-time closed-loop control at 11Hz with a 14B video diffusion backbone. Experiments show that DreamFree can translate stronger video priors and additional video data into better robot control and enable learning new robot tasks from video demonstrations, including videos from a different embodiment, without action annotation for the new tasks.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.16725

Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models

SeungWon Seo, DongHeun Han, SeongRae Noh, HyeongYeop Kang

原文摘要

Executable world models can be read, edited, executed, and reused for planning, but only if the program captures the environment's transition law rather than semantic shortcuts in its surface vocabulary. We study online executable world-model learning under prior misalignment, where an agent must induce state-dependent dynamics from interaction evidence alone, without rule descriptions, reward signals, or trustworthy lexical priors. We introduce Alice, a closed-loop system that treats failed candidate updates as structural signal: when a candidate explains a new transition but loses previously explained ones, the preservation conflict reveals dynamics that the current program had conflated. Alice refines these conflicts into hypothesis classes that both provide a few broken examples, one per affected class, for update and guide frontier exploration toward transitions that are novel and underrepresented with respect to the current program. We evaluate Alice on Baba in Wonderland, a prior-misaligned variant of Baba Is You that preserves simulator dynamics while replacing semantically meaningful rule-property labels with unrelated words. Experiments show that Alice substantially improves executable world-model learning under prior misalignment, and five-run ablations support overall improvement trends as class structure and exploration signals are added. Project page: https://ssw03270.github.io/BABAinWonderland_NeurIPS-26_Page/.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06338

Learning to Tune with Biased Gradients: Iterative Feedback Tuning of Model-Free Control on Throttle Valves

Félix Martinez-Jiménez, Sander Miller-Murphy, Tobie Ondoa-Essomba, Emmanuel Witrant

原文摘要

Iterative feedback tuning (IFT) learns the parameters of a fixed-structure controller by stochastic gradient descent. At each iteration, two closed-loop experiments are run on the plant: the first one measures the tracking error, and the second one, driven by this error, provides the sensitivities from which the gradient of the cost is estimated. This estimate is unbiased for linear plants only. We study the biased case on automotive electronic throttle valves, whose friction and stiction vary between valves and runs, controlled by an intelligent proportional (model-free) controller, which is an incremental PI controller. We show that the mismatch of the controller state at the start of the two experiments, which stiction makes unavoidable, adds an error inversely proportional to the amplitude of the second experiment. On digital twins of ten valves, the IFT gradient is a descent direction in only 69\% of the low-cost region, friction being the cause, and all update rules plateau and then drift. On two hardware valves, the best update rule depends on the noise structure of the gradient. On the first valve, where one gradient component is buried in noise, Adam outperforms Gauss--Newton, its normalisation and its momentum each improving one parameter. On the second valve, where both components are consistent, the same normalisation amplifies a direction that Gauss--Newton rightly discounts, and Adam drifts to a controller worse than the initial one. The twins reproduce the mechanism but not this ranking.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2606.10829

Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models

Yusuf Sahin, Ahmed Rockey Saikia, Volkan Cevher, Paolo Favaro

原文摘要

Masked diffusion language models can reduce inference steps by revealing multiple tokens per denoising iteration, but this parallelism is fragile: positions that are individually confident may be unsafe to commit together when their predictions are coupled. Existing training-free samplers such as Top-$k$, Fast-dLLM, and EB-Sampler mainly control how many tokens to reveal, while often ranking candidates by token-wise scores that ignore interactions within the selected set. We propose ADAS, a training-free reranking rule that leaves the base sampler's stopping rule unchanged and greedily discounts each token-wise confidence score according to its attention to already selected positions, weighted by their prediction uncertainty. Across LLaDA-8B-Base and Dream-7B-Base on the reasoning benchmarks GSM8K and MATH500 and the code benchmarks HumanEval and MBPP, plugging ADAS into all three samplers improves low-NFE performance at matched denoiser evaluations by $9.11$ and $10.46$ percentage points on average, respectively, with $3.1\%$ per-forward runtime overhead. Code is available at https://github.com/yusufsahin99/ADAS.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06328

EvoCodeAgent: Project-Level Code Generation via Architecture-Code Co-Evolution and Experience-Guided Repair

Qianhui Zhao, Li Zhang, Fang Liu

原文摘要

Project-level code generation aims to automatically synthesize complete software repositories from high-level requirements, producing coherent multi-file systems with well-structured modules and consistent cross-file dependencies. Despite the strong capabilities of large language models (LLMs) in specification understanding and code synthesis, existing approaches still exhibit several critical limitations. First, many methods rely on static architectural designs that cannot adapt during iterative generation, leading to a growing misalignment between architecture and implementation. Second, they lack mechanisms to accumulate and reuse experience across iterations, resulting in recurring errors and reduced efficiency. Third, they often depend on standalone LLM-based evaluation of intermediate artifacts, which suffer from limited transparency and potential unreliability under long-context reasoning. To address these challenges, we propose EvoCodeAgent, a state-centric framework for project-level code generation. EvoCodeAgent maintains an evolving architectural state initialized from structured project specifications and continuously reconciles predicted relations from architecture and skeletons with realized relations extracted from generated code. It further uses tool-grounded verification evidence to support reliable state updates and abstracts reusable repair experiences from previous revision attempts to guide subsequent generation. Extensive experiments on project-level benchmarks of different scales, including DevBench and CodeProjectEval, demonstrate that EvoCodeAgent consistently outperforms baseline approaches. Under the GPT-5 setting, it achieves unit test pass rates of 60.48% and 27.73%, respectively, yielding up to a 53.5% improvement over the strongest baseline.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06324

Mass Producing Training Data with Surprising Side Effects

Yaowen Ye, Jacob Steinhardt, Sarah Schwettmann, Cassidy Laidlaw

原文摘要

Training data can have unexpected side effects on language model behavior outside the training domain: insecure code data can induce broad misalignment, and outdated bird names can induce a 19th-century persona. Understanding such generalization is hard because only dozens of isolated examples exist, each constructed by hand or discovered by accident. We propose automatically discovering such datasets with surprising side effects (DSSEs). We define three objectives for DSSEs: they should (1) elicit a target behavior, (2) read like ordinary post-training data, and (3) be surprising to human auditors reading the data. We operationalize each with LLM judges, and search for high-scoring datasets via evolution, reinforcement learning, and subliminal learning approaches. After re-scoring and filtering with held-out metrics, our pipeline produces a collection of 6,575 DSSEs across 8 behaviors, many of which generalize across model families and sizes. We find our automated metrics track ML researchers' judgments, and frontier models outperform humans at predicting side effects. These datasets form a testbed for studying generalization and lay the groundwork for predicting training side effects before model deployment. Explore them at https://dsse.transluce.org.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06319

Verified Implementation of the Next-gen Borrow Checking Algorithm for Rust via Abstract Interpretation

Jinhua Wu, Yuting Wang, Zhemin Chen

原文摘要

Borrow checking is a central mechanism for Rust to ensure temporal memory safety. Its correctness is based on the intuition that the Aliasing XOR Mutability discipline guarantees that programs without borrow errors inherently could not access invalid references (i.e., pointers). However, existing work on formalizing borrow checking treats it either as a component of type systems or as symbolic execution describing resource transfer. None provides a direct explanation of the correctness of borrow checking algorithms such as Non-Lexical Lifetimes (NLL) or Polonius in the official Rust compiler that function more like static pointer analysis. We take a first step toward solving this problem by formalizing Polonius, the next-generation borrow- checking algorithm for the Rust compiler, on a core subset of Rust. We prove its correctness by showing that any program accepted by Polonius does not access invalid references at runtime. The key observation is that, when borrow checking is performed lazily, Polonius could be treated as a forward abstract interpretation on abstract domains recording pointer aliasing (borrowing) relations. By providing a concrete semantics that formally describes the Aliasing XOR Mutability discipline, we prove the soundness of this abstract interpretation, from which we derive memory safety of checked programs. This formulation of Polonius is implemented and formally verified in the abstract interpretation framework of CompCert. The correctness proofs are generated by an agentic AI under human guidance using paper proofs as proof outline. To the best of our knowledge, this is the first comprehensive formalization and verification of a borrow checking algorithm as manifested in the Rust compiler.

cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06315

Exact certification for conic optimization over quadratic modules: partitions of unity and recession directions

Didier Henrion, Alaa Ibrahim, Victor Magron

原文摘要

We consider linear conic problems whose cone is a product of truncated quadratic modules, the sum-of-squares (SOS) side of the moment-SOS hierarchy. A floating-point solution is turned into an exact rational certificate in three steps: rounding, repair of each block residual by a constant, and absorption of the constants along a recession direction of the problem. The repair relies on strict partitions of unity in the quadratic modules. We characterize their existence, relate the canonical one to the analytic center of the dual pseudo-moment cone, Christoffel-Darboux polynomials and Pell equations, and we derive closed-form rational partitions for balls and boxes. The loss incurred by the certification is the optimal value of a recession problem, equal to a support function of the masses of the dual feasible pseudomoments. The method is illustrated on polynomial optimization, volume computation and positivity of polynomials along D-finite trajectories.

cs.SC · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.04108

Separating Common and Unique Directions for Model Merging

Shiting Wang, Yingjie Zou, Ke Li

原文摘要

Model merging combines multiple fine-tuned models without additional training, and arithmetic methods have emerged as a simple yet effective way to merge models without data. However, existing arithmetic methods treat task vectors in parameter space and apply a single element-wise rule to directions that can differ in mergeability. In a shared directional basis, we find a consistent two-regime structure: a low-dispersion common bulk shared across tasks and a high-dispersion task-dominated tail that carries disproportionate energy. These findings motivate Common--Unique Subspace Decomposition (CUSD), a data-free pre-merging method that separates task vectors into common and unique directional components, merges the common components with a downstream arithmetic operator, and retains unique residuals separately. Experiments across $11$ base models, four model families, and four arithmetic-based merging operators show that CUSD improves 42 of 44 model--operator combinations and achieves up to 22.5% improvement over the corresponding baselines. Our code is publicly available at https://github.com/stwang666/CUSD

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06311

The Exact Memory-Rate Tradeoff for Three-User Secure Coded Caching

Han Fang, Nan Liu, Wei Kang

原文摘要

We determine the exact zero-error memory-rate tradeoff for secure coded caching with three users and any number $N\ge2$ of independent files. Each user recovers its requested file, while its cache and the broadcast jointly reveal no information about the complete tuple of unrequested files. For $N\ge4$, two converse inequalities establish the optimality of the known achievable points and the memory-sharing segments between them. For $N=3$, two additional bounds identify a new corner at $(M,R)=(3/2,2)$, where memory and rate are measured in file units. An explicit linear code over $\mathbb{F}_3$ attains this corner and reduces the rate by one quarter of a file relative to memory sharing between the known points. The converse links the information held by cache pairs and triples to delivery under repeated and distinct requests. Its equality conditions guide the construction: users cancel the keys to recover their requested files, while uniform masking protects the complete tuple of unrequested files.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v7arXiv:2310.19385

Gradient-free online learning of subgrid-scale dynamics with neural emulators

Hugo Frezat, Ronan Fablet, Guillaume Balarac, Julien Le Sommer

原文摘要

In this paper, we propose a generic algorithm to train machine learning-based subgrid parametrizations online, i.e., with $\textit{a posteriori}$ loss functions, but for non-differentiable numerical solvers. The proposed approach leverages a neural emulator to approximate the reduced state-space solver, which is then used to allow gradient propagation through temporal integration steps. We apply this methodology on a chaotic two-timescales Lorenz-96 system and a single layer quasi-geostrophic system with zonal dynamics, known to be highly unstable with offline strategies. Using our algorithm, we are able to train a parametrization that recovers most of the benefits of online strategies without having to compute the gradient of the original solver. We found that training the neural emulator and parametrization components separately with different loss quantities is necessary in order to minimize the propagation of approximation biases. Experiments on emulator architectures with different complexities also indicates that emulator performance is key in order to learn an accurate parametrization. This work is a step towards learning parametrization with online strategies for climate models.

physics.comp-ph · cs.LG · physics.flu-dyn

查看论文
arXiv ↗PDF ↗