跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+758新增论文
+578其中 AI 相关
+94已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 04:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 10:23 — 2026-11-17 10:23(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:2026-11-17 04:58最近发现新增版本:2026-11-17 04:58库内论文最新更新时间:2026-11-14 02:59

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

24,106 已收录论文20,158 AI 相关7,049 有修订112 HF 社区发现

浏览论文库

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

找到 24,106 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
新论文 · v1arXiv:2611.09161

GreyZone: Production-quality Agentic Application Threats

Ruoyu Zhou, Shuyao Jiang, Haifeng Ruan, Abhik Roychoudhury

原文摘要

Agents are increasingly deployed across domains such as coding, banking, and commerce. Their ability to invoke tools and change application state makes security testing important for reliable deployment. Although agent security has been studied through various adversarial testing approaches, benchmarks grounded in production agent environments remain limited. We introduce GreyZone, a benchmark for evaluating automated red-teaming services against real-world agent applications. Unlike benchmarks such as AgentDojo, which primarily evaluate subject agents under attack, GreyZone evaluates services' ability to generate and deliver attacks that cause verified security-policy violations. We select independently developed, open-source agent applications with security boundaries concerning access permissions, confidentiality, and action authorization. These applications expose diverse attack surfaces, including those arising from multi-agent interactions and multimodal inputs. By grounding evaluation in application environments that preserve production-relevant workflows and independently verifying outcomes, GreyZone supports research on automated agent security testing. Specifically, we present two preliminary case studies using Promptfoo on Letta Code and Clawith to examine attack delivery, agent behavior, and verified outcomes. We release the benchmark, including subject agents and attack surfaces for each application, to support further research on agent testing methods.

cs.SE

版本更新 · v3arXiv:2607.00466

ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving

Sangjin Choi, Sukmin Cho, Yifan Xiong, Ziyue Yang, Youngjin Kwon, Peng Cheng

原文摘要

Equal load does not mean equal decode latency in prefill-decode (PD) disaggregated mixture-of-experts (MoE) serving. In bandwidth-bound decode, more distinct experts mean more weight loads and higher latency. We present ELDR, a lossless, expert-locality-aware decode router. Prefill signatures predict decode expert usage. Balanced $K$-means fits per-decoder centroids with background refitting. Locality-band routing selects the least-loaded worker among close matches. A block-granular cache keeps signatures exact under prefix caching. We evaluate ELDR in vLLM on up to 40 GPUs. Across three MoE models on 12 public task benchmarks and multilingual WildChat, it reduces median time-per-output-token (TPOT) by 5.4-14.5% on average across request rates and up to 17.8% over the best of four load-balancing baselines, preserving model outputs and token-to-expert assignments.

cs.DC

版本更新 · v2arXiv:2605.18094

Learning to Solve Compositional Geometry Routing Problems

Mingfeng Fan, Jianan Zhou, Jiaqi Cheng, Yifeng Zhang, Jie Zhang, Guillaume Adrien Sartoretti

原文摘要

We study the Compositional Geometry Routing Problem (CGRP), a unified superclass of traditional routing problems that covers point-only, line-only, area-only, and arbitrary hybrid task geometries, providing a broad abstraction for real-world routing scenarios. Beyond standard point-based routing, CGRP with non-point tasks can be inherently asymmetric, tightly coupled travel routes with the intrinsic path, and enlarges the action space with numerous feasible yet often irrelevant options, thereby posing significant challenges for both representation learning and decision-making. To address these challenges, we propose DiCon, a differential attention-assisted solver with contrastive learning, as a plug-and-play framework that tackles the problem from two complementary angles. First, we introduce a differential attention mechanism that actively suppresses the probability mass on less competitive candidate actions. Second, we design a double-level contrastive learning objective to promote robust global instance representations and regularize geometry-aware task representations. Extensive experiments demonstrate that DiCon achieves strong performance, broad versatility, and superior generalization across diverse CGRP instances with different compositions.

cs.AI

版本更新 · v2arXiv:2607.15873

A Physically-Realisable Quantum Programming Language with Quantum-Controlled Quantum Channels

Kengo Hirata, Takeshi Tsukada

原文摘要

In contrast to a classical bit, which can only take the value $0$ or $1$, its quantum counterpart---a qubit---can exist in a superposition of $0$ and $1$. This is a superposition of data values, and it is then tempting to superpose programs as well. Indeed, a particular superposition of programs, known as the quantum SWITCH, has attracted considerable attention. A natural way to superpose programs is conditional branching on quantum data, and several studies have pursued this idea. However, there is a well-known semantic difficulty with this approach, and the fundamental question of whether the languages proposed in prior work can be physically realised remains open. This paper proposes a physically realisable quantum programming language with quantum branching over quantum channels. We first analyse the semantic difficulty from an implementation perspective and show that the difficulty is caused by arbitrariness in the implementation. We then design a language that is free from this arbitrariness. As expected from its implementation-oriented design, our language is physically realisable. We argue for this from two directions: first, we give a method for compiling programs into quantum circuits; and second, we show that our programs stay within the physically admissible range, namely, that they neither yield probabilities greater than one nor violate causal inequalities. The absence of such violations is established through the inclusion of our language in QC-QC, a notion of realisability studied in physics.

cs.PL · cs.LO · quant-ph

新论文 · v1arXiv:2611.09159

UniExit: A Unified Latency-Aware Early-Exit Runtime for Heterogeneous Edge AI

Yuhang Guan, Huanle Zhang, Xiaomin Ouyang, Zhidan Liu

原文摘要

Edge applications increasingly combine CNN-based perception with edge-deployable Transformer-based language models, but deploying such heterogeneous workloads on resource-constrained devices is challenging because inference latency varies with both input difficulty and runtime hardware state. Early-exit inference reduces computation by terminating at intermediate stages, yet existing methods are often model-specific and rely on static latency profiles that become stale under dynamic edge conditions. This paper presents UniExit, a unified latency-aware early-exit runtime for heterogeneous edge AI. UniExit abstracts CNN blocks and Transformer layers as ordered stages and applies a common latency-aware routing policy while retaining model-specific quality mechanisms. It predicts the cost of reaching the next exit from runtime state and inference progress to make budget-aware continue-or-exit decisions. UniExit combines runtime-state-aware latency prediction, cache-based prediction reuse, trend-aware fallback, and CNN-specific exit stabilization to provide low-overhead and robust online control. We implement UniExit on multiple edge and edge-cloud platforms and evaluate it with representative CNN and Transformer-based language-model workloads. Across single-workload, concurrent heterogeneous, and edge-cloud settings, UniExit consistently improves deadline satisfaction and latency-accuracy trade-offs over existing progressive inference baselines, while reducing redundant exit-module computation and task-level energy consumption.

cs.DC

新论文 · v1arXiv:2611.09157

Word Subtraction Games

Yusuke Inoue, Hiroki Inazu

原文摘要

This note is a self-contained text on word subtraction games, combinatorial games in which players alternately remove a nonempty suffix belonging to a prescribed subtraction set from the current word. It collects and develops basic results on these games from the viewpoints of combinatorial game theory and formal language theory. We focus on the relationship between subtraction sets and the resulting languages of winning and losing positions. The topics include finite, regular, and context-free subtraction sets, as well as several variants and further developments.

cs.FL

版本更新 · v2arXiv:2610.21613

To Think or Not to Think: Pre-Decisional Reasoning Budgets for Referring Audio-Visual Segmentation

Haojie Hu, Senda Chen, Ying Shen, Lin Zhang

原文摘要

Multimodal reasoning systems increasingly assume that longer chain-of-thought (CoT) uniformly improves downstream grounding. We show that this assumption fails in referring audio-visual segmentation (Ref-AVS): simple queries can be harmed by excessive reasoning, creating an "overthinking trap" associated with phrase and localization drift, while genuinely ambiguous queries still benefit from multi-step reasoning. To systematically study this, we construct counterfactual reasoning-budget labels under a five-fold out-of-fold evaluation protocol. Our results recast adaptive Ref-AVS reasoning as a pre-decisional representation problem: before the first generated token, the generation-onset state contains linearly decodable information predictive of whether additional reasoning will improve segmentation. A linear probe predicts binary reasoning need with 70.1% accuracy, substantially outperforming text-only features and uncertainty-based proxy signals. As a router, the onset-state controller improves over downstream confidence routing and closely matches Short-then-Decide while using far fewer tokens. Proxy comparisons show that the onset representation contains predictive information not fully recovered by the evaluated hand-crafted features. Reusing this onset state for lightweight, single forward-pass routing reduces autoregressive token consumption by 60% while retaining about 96% of always-long performance. It further provides a cost-quality trade-off on $R^2$-AVSBench without target-label tuning, rather than an accuracy improvement over always-long. Error analysis links harmful long reasoning to phrase and localization drift, illustrating the benefit of bypassing unnecessary reasoning on simple queries. Ultimately, our results support efficient adaptive reasoning in Ref-AVS through pre-decisional internal representations.

cs.MM

新论文 · v1arXiv:2611.09156

Evaluation of a Multi-Link Machine Learning Approach for Rainfall Detection Using Satellite Microwave Links

Mostafa Ftouni, Margherita Spalla, Matteo Colli, Andrea Randazzo, Christian Gianoglio

原文摘要

The impacts of climate change have increased the need for reliable real-time rainfall monitoring systems. This study investigates rainfall detection using a network of opportunistic sensors based on satellite microwave links (SMLs) combined with machine learning (ML) classifiers. Two models, a random forest (RF) and a convolutional neural network (CNN), were trained on aggregated SML data, including information from neighboring links. The results demonstrate that leveraging information from multiple links substantially enhances the detection of both wet and dry periods compared to single-link approaches. Moreover, the RF model consistently provides a more stable and reliable trade-off than CNN, improving rainfall detection and reducing misclassifications overall, with particularly strong performance during harsh weather conditions. The study spanned up to 32 rainy days between 2021 and 2024.

cs.AI · cs.LG · eess.SP

版本更新 · v2arXiv:2610.22457

Erase the Mark, Preserve the Motion: Temporally Consistent Removal of Video Watermarks

Yifan Liao, Zhen Sun, Zhicong Huang, Jiaming He, Zongmin Zhang, Xi Ai, Cheng Hong, Xinhu Zheng 等 9 位作者

原文摘要

Recent advances in video generation have increased the demand for reliable watermarking for copyright protection, yet the robustness of video watermarks against removal attacks remains underexplored. Most watermark-removal methods originate from the image domain: signal optimization injects imperceptible pixel-domain perturbations, whereas generative resynthesis produces a visually similar instance through diffusion synthesis. When extended to videos, the former introduces temporally varying noise that causes visible flickering, while the latter regenerates fine-grained structures inconsistently across frames, leading to structural motion inconsistency. To evaluate video watermark robustness, we propose PoseRegen, a pose-consistent reconstruction framework that removes watermarks while preserving the original content and motion. PoseRegen first applies a temporally shared viewpoint transformation to disrupt watermark-bearing spatial patterns and then jointly reconstructs the transformed sequence with a pose-conditioned video model. A frozen video DiT processes the complete sequence with its reference-video latent, and full-sequence Flow Matching supervision keeps identity and background consistent across frames. To further preserve motion structure, we introduce a lightweight Pose-Conditioned Motion Consistency Adapter that adapts the frozen backbone to temporally ordered pose guidance and constrains body-part trajectories throughout reconstruction. Experiments on eleven video watermarking schemes show that PoseRegen reduces the average bit accuracy to 0.505, near random guessing, while outperforming the strongest baseline by 9.34% on motion-related VBench metrics. These results reveal a practical vulnerability of current video watermarks and highlight the need to evaluate robustness jointly with temporal and motion quality.

cs.CR · cs.CV

版本更新 · v2arXiv:2610.33798

Whispers from the Neighbors: Rethinking Caption Consensus as Inference-Time Evidence for Vision-Language Retrieval

Khang Nhat Hoang Vo, Belal Shoer, Abhirama Subramanyam Penamakuri

原文摘要

An image is rarely described only once. Retrieval benchmarks and many collections attach several captions to each picture, yet dual encoders still judge every image-caption pair in isolation. We ask what these neighboring captions contribute when a frozen encoder consults them at inference time. Fusing image similarity with similarity to an image's own captions improves text-to-image R@1 by 3.4 to 16.8 points across nine frozen encoders when the captions come from the same annotators as the queries. The gain falls to 1.9 to 7.2 points when an off-the-shelf captioner writes them, and to at most one point when they come from a different annotation source; a paraphrase-trained text encoder strengthens the text side further. A natural refinement, scoring the part of the image that the captions leave unexplained, appears to add much more under a leave-one-out evaluation. We show that this advantage arises because the correct candidate's supports are built differently from those of the negative candidates, with set size and query removal each contributing about half, and that under a fixed support index the residual reduces to a reweighting of what the captions already provide. On compositional benchmarks, the captions help by matching candidates to human descriptions of the image, without improving image-text grounding. The code is available at: https://github.com/nhatkhangcs/clip_consensus

cs.CV · cs.CL

新论文 · v1arXiv:2611.09154

Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM Reasoning

Hongbin Lin, Sizhe Zou, Juangui Xu, Xinyue Xu, Zhuoli Ouyang, Stanislav Kolchin, Chengwei Qin, Zhongxiang Dai 等 9 位作者

原文摘要

Reasoning traces improve vision-language models on complex multimodal tasks, but forcing every input to follow a long reasoning process leads to overthinking and unnecessary inference cost. We study adaptive fast/slow thinking for VLMs, where one model answers directly for simple inputs and reasons step by step when needed. Fast answers and slow traces often come from distinct behavior policies, making a single-reference offline objective misweight one mode. We propose DUAL-REFERENCE BOLT (DR-BOLT), which distinguishes the desired fast/slow mixture reference from the sampling distribution and corrects their mismatch in reward-weighted training. Fast/slow partition competition explains routing in the optimal target; an efficient source-wise correction approximates the exact objective when response formats are well separated. Matched Qwen3-VL comparisons use identical candidate banks to isolate the objective from slow-teacher quality. DR-BOLT improves score-length trade-offs over the evaluated offline and online baselines on ScienceQA and three held-out transfer benchmarks, with a 24.1% cross-benchmark slow ratio and a 2.90-fold end-to-end training speedup over reproduced GRPO. These results support adaptive reasoning in the studied two-reference setting, while broader robustness remains open. Our code is available at https://github.com/HongbinLin3589/DR-BOLT.

cs.AI

新论文 · v1arXiv:2611.09147

BMMS: Policy-Conditioned Measurement of Behavioral Compliance in Language Models

Anthony Rhodes, Gadi Singer

原文摘要

Behavioral evaluation of language models fixes its dimensions in advance: hallucination, sycophancy, toxicity, over-refusal. An operator in a regulated industry needs a different question answered: does a system do what a particular rulebook requires? We introduce the Behavioral Misalignment Metric Suite (BMMS), which measures policy-conditioned misalignment by taking a policy corpus as an argument and returning a compliance profile over it, for any published policy and any system that answers in natural language. The Compliance Attainment Score (CAS) measures severity-weighted attainment over the obligations that bind the system, and the Compliance Robustness Margin (CRM) the share of that attainment surviving graded adversarial pressure; Behavioral Invariance (BIV) and the Behavioral Disposition Index (BDI) are specified and released with the suite. Dimensions enter only by passing a published admission test whose binding criterion is attribution: a quantity that moves when the judge changes, holding the target fixed, is measuring the instrument. Applying it excluded one of the quantities the suite itself reported. Across 1,003 obligations from eleven documents in five registers, the admission criterion holds 94.4% precision against blinded human judgment on vendor specifications and 50.0% on analytical guidance, extraction fidelity is 94.6%, and re-scoring under judges from two other providers leaves target ordering invariant while the absolute score of a single target spans up to 0.22. We apply it to the two most detailed published behavioral specifications. Own-specification advantage is not resolved from zero once document difficulty is subtracted, but absolute self-compliance is another matter: GPT-4o fails 70.7% of the hard constraints binding it in the Model Spec published by OpenAI, where the two Claude models fail 0.0% and 9.1% of theirs.

cs.AI · cs.CL

版本更新 · v4arXiv:2609.24997

VideoGen-Agent: Reinforcing Video Generation Agents

Binxu Li, Haoyi Duan, Yuhui Zhang, Yaohui Zhang, Zihao Lin, Kaituo Feng, Hui Yuan, Suozhi Huang 等 13 位作者

原文摘要

Recent advances in video generative models have enabled high-fidelity, temporally coherent video generation. However, these models often struggle to satisfy prompts requiring specialized knowledge, specific identities, physical consistency, or ordered events. In this paper, we present VideoGen-Agent, a multimodal agent trained through multitask agentic reinforcement learning to use external tools for video generation. The agent coordinates augmentation, generation, and verification tools through multi-turn interactions, using the prompt and intermediate observations to guide its decisions. We train a shared policy on a category-balanced dataset spanning six tasks. Supervised fine-tuning on teacher-generated trajectories establishes tool-use behavior, which is then refined through reinforcement learning. A category-aware hybrid reward evaluates tool-call validity, task-appropriate tool use, and generated video quality. We further introduce VABench, a held-out benchmark of 600 prompts covering procedural knowledge, single- and multi-entity identity preservation, physical consistency, scene composition, and multi-shot temporal structure. On VABench, VideoGen-Agent improves over its base text-to-video generator by 19.1 points, from 56.5 to 75.6. Upgrading the generation tools further raises the score to 86.1 without additional agent training. Human raters prefer the upgraded configuration over the strongest standalone baseline in 84.3% of comparisons. These results support learning tool use across video-generation tasks and show that the trained agent can benefit from subsequent advances in generation tools. Project page: https://andyca111.github.io/VideoGen_Agent/

cs.CV

版本更新 · v2arXiv:2606.05516

Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs

Wanhao Yu, Ziyan Wang, Zheng Wang, Abeer Matar Almalky, Yihang Zuo, Shuteng Niu, Sen Lin, Adnan Siraj Rakin 等 10 位作者

原文摘要

Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models (LLMs) using only forward passes, but it remains unclear how useful adaptation is distributed across layers. In this work, we reveal a surprising phenomenon: ZO fine-tuning is sharply dominated by a single decoding layer. Across multiple LLM families and downstream tasks, fine-tuning this dominant layer alone consistently matches or even exceeds full-model ZO fine-tuning. We further show that the dominant layer is task-agnostic but model-specific, and can be identified before training through a simple inference-only analysis of activation outliers. Specifically, the dominant layer consistently aligns with the first activation-outlier layer in the pre-trained model. To explain this phenomenon, we analyze how perturbation effects propagate under ZO optimization. We find that the dominant layer combines two key properties: high perturbation sensitivity and early placement in the residual stream, allowing perturbation-induced effects to propagate and accumulate through remaining subsequent decoding layers. As a result, this layer produces disproportionately strong and stable optimization signals under forward-only updates. Extensive experiments on LLaMA2-7B and Qwen3-8B across nine benchmarks show that dominant-layer ZO fine-tuning improves average performance over full-model MeZO and LoRA-based ZO fine-tuning while achieving up to 4.52$\times$ training speedup.

cs.LG

版本更新 · v5arXiv:2605.11651

Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation

Seonghoon Yu, Dongjun Nam, Byung-Kwan Lee, Jeany Son

原文摘要

Recent think-answer approaches in VLMs, such as Qwen3-VL-Thinking, boost reasoning performance by leveraging intermediate thinking steps before the final answer, but their computational cost becomes substantial, especially for larger VLMs. To distill such capabilities into compact think-answer VLMs, a primary objective is to improve the student's ability to utilize visual evidence throughout its reasoning trace, as long think-answer traces suffer from visual forgetting issues. To this end, we introduce a novel think-answer distillation framework that encourages the student to anchor its thinking on visual information by masking the student's salient reasoning prefixes. To compensate for such masked textual cues, the student is encouraged to rely more on visual evidence as an alternative source of information during distillation. Our masking strategies include: 1) token-wise salient reasoning-prefix masking, which masks high-influence reasoning prefixes selectively for each next-token prediction, and 2) self-paced masking budget scheduling, which gradually increases the masking scale according to distillation difficulty, measured by the discrepancy between teacher--student distributions. In the distillation phase, the student is guided by our salient reasoning-prefix mask, which blocks both future tokens and salient reasoning cues, in place of the standard causal mask used for auto-regressive language modeling. Experimental results show that our approach outperforms recent open-source VLMs, VLM distillation, and self-distillation methods on multimodal reasoning benchmarks, while further analyzes confirm enhanced visual utilization along the student thinking process.

cs.CV · cs.AI · cs.CL

新论文 · v1arXiv:2611.09145

Augmentron: Scalable Multi-View Visual Augmentation for Robot Learning

Tanay Tandon, Aseem Doriwala, Jade Choghari, Catherine Weaver, Pragna Mannam

原文摘要

Robot policies trained on visually narrow demonstrations can become sensitive to environmental features that are unrelated to the task. Existing generative augmentation methods can introduce visual diversity, but processing every frame and camera view independently is computationally expensive and may produce inconsistent observations across cameras and timestamps. We introduce Augmentron, a geometry-aware pipeline that generates reusable scene representations and renders them through recorded camera poses. This produces temporally and multi-view consistent environ- ment and workspace variations while preserving the robot, task objects, actions, and annotations. Across three physical manipulation tasks, replacing half of the real world training dataset with Augmentron data improves model success across three tasks for both in out-of-distribution distractor objects, and out-of-distribution workspace variation evaluations. In a separate comparison against alternate augmentation techniques, Augmentron achieves the highest pooled success in all three conditions. The results show that introducing augmented data to a data training recipe can help policies generalize to dynamic real-world settings.

cs.LG · cs.RO

新论文 · v1arXiv:2611.09142

Learning Generative Dynamics for 3D Molecule Generation via Sequential Neuro-Symbolic Constraints

Zhuoran Li, Xu Sun, Chang Wen Chen, Wanyu Lin

原文摘要

Diffusion models have recently emerged as a powerful paradigm for generating 3D molecules. Despite showing remarkable promise, they learn atomic distributions implicitly from data, without explicitly encoding physicochemical rules into their generative dynamics. Consequently, generated samples can be statistically plausible yet chemically invalid. To address this problem, we propose Sequential Neuro-Symbolic Constrained Diffusion (SensDiff), a framework that integrates symbolic rules into generative modeling, enabling the model to internalize scientific priors during training. Central to SensDiff is the observation that the diffusion trajectory of 3D molecule generation exhibits a coarse-to-fine evolution: valid molecules arise by first mitigating macroscopic geometric conflicts and then refining structures toward microscopic chemical consistency through iterative denoising. Accordingly, SensDiff mirrors this dynamic by sequentially enforcing constraints with adaptive weighting during training, progressively steering generation toward valid molecular geometries. Moreover, SensDiff translates domain knowledge into interpretable generative controls, grounding opaque neural denoising in scientific principles. Experiments on molecular benchmarks and real-world constrained generation tasks confirm that SensDiff consistently improves chemical validity while adhering to physicochemical rules and user-specified targets. The code is publicly available at https://github.com/WanyuGroup/NeurIPS2026_SensDiff.

cs.LG · cs.AI

版本更新 · v5arXiv:2511.21638

Iterative Policy Optimization: Batch-Online Multi-Turn RL via Single-Turn RL

Daniel R. Jiang, Ankur Samanta, Yukai Yang, Jalaj Bhandari, Rémi Munos, Tyler Lu

原文摘要

Practical LLM agents often operate over multi-turn conversations where success is determined only after the full interaction ends. Most multi-turn RL methods train via on-policy rollouts, but unlike in single-turn RL, the policy cannot produce a trajectory alone, since an external environment must respond after each agent turn. For conversational agents, this environment is a user, but real users are generally unavailable inside the training loop and simulated users are difficult to build faithfully. Separately, real-world deployment is rarely fully online or fully offline. The common production pattern is called batch online, where the current policy is deployed to collect a batch of interaction data, then retrained on that batch and redeployed. We show that this batch-online setting creates an opportunity for applying the classical approximate policy iteration algorithm. Our central observation is that running standard token-level, single-turn GRPO with a learned turn-level $Q$-function as the reward model is a policy improvement step for the multi-turn problem. Building on this, we present Iterative Policy Optimization (IterPO), which alternates between fitting $Q^π$ from logged Monte Carlo returns via standard reward modeling (policy evaluation) and running single-turn GRPO against $Q^π$ (policy improvement). During policy improvement, the learned $Q^π$ scores candidate responses by their expected downstream return, avoiding the need for simulator rollouts of the remaining conversation. Overall, this allows us to do principled multi-turn RL using only single-turn RL methods without an interactive environment or user simulator inside the training loop. We demonstrate the effectiveness of IterPO on six multi-turn negotiation environments.

cs.LG

版本更新 · v3arXiv:2605.00020

AirFM-DDA: Air-Interface Foundation Model in the Delay-Doppler-Angle Domain for AI-Native 6G

Kejia Bian, Meixia Tao, Jianhua Mo, Zhiyong Chen, Leyan Chen

原文摘要

The success of large foundation models is catalyzing a new paradigm for AI-native 6G network design: wireless foundation models for physical-layer design. However, existing models often operate on channel state information (CSI) in the spatial-temporal-frequency (STF) domain, where multipath components are superimposed and structurally entangled. This hinders the learning of a universal channel representation. Their reliance on global attention also incurs prohibitive overhead. In this paper, we propose AirFM-DDA, an Air-interface Foundation Model in the Delay-Doppler-Angle (DDA) domain. AirFM-DDA reparameterizes CSI into the DDA domain to resolve multipath components along physically meaningful axes and employs window-based attention with frame-structure-aware positional encoding. Extensive experiments demonstrate transferability across scenarios, tasks, datasets, and antenna configurations. For channel prediction and estimation, AirFM-DDA generalizes zero-shot to unseen cities, achieving average normalized mean-square error (NMSE) gains of 4.9-8.5 dB over the strongest baselines. With only 10% labeled data, it achieves average gains of 12.0 percentage points in Top-1 accuracy for beam prediction and 3.4 percentage points in F1 score for line-of-sight (LoS) identification. It further transfers across simulated datasets and adapts to measured data and different antenna arrays. Compared with global attention, window-based attention reduces training and inference costs by nearly an order of magnitude.

cs.LG · cs.AI · cs.IT · eess.SP

新论文 · v1arXiv:2611.09141

Circuit Theory-Informed AI for Condition Monitoring in Power Electronics

Yubo Song, Pascal A. Schirmer, Subham Sahoo

原文摘要

Artificial intelligence for power electronics is evolving toward a deeper comprehension of system intrinsic behaviors and dynamics. As a novel integration of neural computation and electric circuits, spike-based neuromorphic computing offers promising potential in high energy efficiency and adaptability for data-driven applications. Building on the latency-coding principles, this article proposes a framework for data-light condition monitoring that relies solely on three-phase AC current measurements. The AC current signals are encoded as membrane potentials of RC-based spiking neurons, which are inherently compatible with spiking neural networks that can effectively facilitate the estimation of device parameters. Case studies are presented to validate the performances, while constraints and further optimizations are also evaluated and discussed, and future extensions of the methodology are provided.

cs.ET · cs.AI · cs.LG · cs.NE · eess.SY

新论文 · v1arXiv:2611.10062

REFORM-3D: A Representation-Centric Evaluation Framework for 3D Medical Vision Foundation Models

Maregu Assefa, Muzammal Naseer, Divya Velayudhan, Gedamu Alemu Kumie, Naoufel Werghi

原文摘要

Evaluation of 3D medical foundation models is typically dominated by downstream task scores, which entangle representation quality with adaptation choices. This is especially critical in volumetric imaging, where spacing and anisotropy can substantially alter image statistics while the anatomy itself remains unchanged. We therefore introduce \textbf{REFORM-3D}, a \textbf{R}epresentation-centric \textbf{E}valuation \textbf{F}ramew\textbf{OR}k for benchmarking frozen 3D medical vision foundation \textbf{M}odels across three questions: Acquisition Robustness, asking whether features remain stable when spacing varies while anatomy is fixed; Cross-Modal Anatomical Alignment, asking whether labeled anatomical structures remain recoverable across modalities under balanced bidirectional retrieval; and Anatomical Transfer, asking whether organ identity remains recoverable from limited labeled support under case-disjoint evaluation. These are also pretraining questions, because what a 3D encoder learns depends on how volumes are geometrically presented during self-supervised pretraining. We further introduce Med3DINO encoder family, pretrained on $62.6$K unlabeled MR, CT, PET, CTA, and CBCT volumes under three explicit geometric assumptions: isotropic normalization, voxel-relative sampling, and spacing-aware resampling. Across Med3DINO and heterogeneous external encoders, REFORM-3D reveals module-specific strengths rather than a single model ordering. Within the controlled Med3DINO comparison, voxel-relative sampling yields lower embedding drift, whereas spacing-aware resampling favors anatomical transfer; semantic-transfer advantages depend on the dataset and feature type. Project link: \href{https://endarzboy.github.io/reform3d-website/}{\highlightLR{REFORM-3D}}.

cs.CV

版本更新 · v2arXiv:2609.30967

MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens

Subhojyoti Mukherjee, Md Mehrab Tanjim

原文摘要

Most work on improving large language models treats accuracy as the sole objective. We argue that the harness, the Python code surrounding the model that constructs prompts, routes calls, and parses outputs, is a first-class design surface whose quality is inherently multi-objective: an accurate harness that refuses no unsafe request, or that consumes an order of magnitude more tokens, is not a good harness. We present Meta-Harness, a system that casts harness design as search over three per-domain objectives (accuracy, behavioural safety, and token cost) solved by an agentic proposer (Claude Code) with full filesystem access to prior harness source, execution traces, and scoring artifacts. Our central finding is that a singlephase joint-reward proposer (MoMHa) outperforms every alternative, including a two-phase "accuracy then tokens" ablation, scalar-only feedback, and an accuracy-only baseline. We evaluate on seventeen domains: seven synthetic capability suites, seven real-world public benchmarks (HumanEval, MBPP, Spider, FEVER, MMLU-Pro, LawBench, NuminaMath), and three U-SafeBench-derived user-specific safety domains, using a 12-model fleet spanning four families. On the synthetic track MoMHa achieves a joint mean of 0.482 versus 0.198-0.422 for ten baselines, winning $7 / 10$ per-domain columns; on the real-world track it scores 0.461 versus 0.377 for the strongest baseline (DSPy), winning 5/7 columns, demonstrating that harness strategies transfer to unseen benchmarks without retraining on 8 of 12 target models. MoMHa attains the highest measured behavioral safety composite (U-SafeBench, 0.781) and uses 95 fewer tokens per example than the two-phase alternative. We will release all harness code, evaluation infrastructure, and crossmodel logs.

cs.AI

新论文 · v1arXiv:2611.09140

SPDMX: Large-Scale Open Stem Audio From Symbolic Music

Phillip Long, Eduardo Escoto, Julian McAuley, Zachary Novack

原文摘要

Large public datasets have driven recent progress in machine learning, from text and vision to speech and general audio. Music remains an outlier, as copyright blocks redistribution of training audio, while many modern tasks need individual stems rather than mixtures. Existing multitrack resources trade off realism, scale, and licensing, while synthetic alternatives rely on proprietary VSTs or naive open rendering that yields weak stems. We introduce SPDMX, a listening-guided rendering of public-domain PDMX scores into an openly-licensed stem corpus with aligned scores and an open render pipeline: $253{,}982$ songs, $490{,}159$ mono stems, and $5{,}469$ song-hours at $44.1$ kHz under CC BY 4.0, with paired MIDI and identifiers linking to PDMX metadata. $88{,}403$ songs ($34.8\%$; $2{,}734$ song-hours) provide multitrack supervision. To our knowledge, this is the largest openly-licensed synthetic multitrack subset by song-hours, enabling source separation, stem-conditioned synthesis, MIDI-to-audio, transcription, and joint symbolic-audio modeling. We release the corpus, metadata, and open pipeline for reuse on other symbolic collections. Demos and experimental notes are on the project page.

cs.SD · cs.AI · cs.LG · cs.MM · eess.AS

新论文 · v1arXiv:2611.09139

CARGO: Causal Attribution and Responsibility-Guided Preventive Safe Multi-Agent Reinforcement Learning for Cooperative Driving

Jingjia Teng, Yang Li, Wenjie Huang

原文摘要

This study presents Causal Attribution and Responsibility-Guided Optimization (CARGO), a multi-agent reinforcement learning framework for cooperative on-ramp merging in mixed traffic. A shared latent-context posterior and an action-conditioned response model estimate directed behavioral influence, with posterior uncertainty propagated into interaction-edge selection. Complementary attribution mechanisms couple signed influence with marginal team utility for cooperative reward shaping and assign responsibility from positive excess tail risk relative to a safe reference policy. Conditional diffusion generates future responses for action-dependent risk estimation. Responsibility-guided preventive optimization calibrates agent-specific risk-reduction requirements to local capacity within a policy trust region, using reserved safety margins, adaptive requirement scaling, and joint feasibility verification. Theoretical analysis establishes risk monotonicity and sufficient local conditions for non-decreasing environmental return under explicit assumptions. Experiments in highway-env across three traffic densities, together with controlled graph-recovery and attribution studies, support the effectiveness of the framework. Under high-density traffic, CARGO increases the success rate by 66.04\% and reduces the crash rate by 56.23\% relative to the best evaluated baseline for each metric.

cs.AI

新论文 · v1arXiv:2611.09138

Deep Learning Theory through the Lens of Statistical Physics: A Topical Review

Wei Huang, Youjin Deng

原文摘要

The recent success of foundation models and deep learning has far outpaced our theoretical understanding of how large-scale neural networks learn and generalize. Statistical physics provides a natural language for describing such high-dimensional, nonlinear, and strongly coupled systems, offering concepts such as mean-field theory, phase transitions, energy landscapes, and stochastic dynamics. In this topical review, we adopt a statistical-physics way of thinking -- from concepts including phases and criticality, and free-energy viewpoints, to methods such as kernel and Gaussian-process limits, mean-field and dynamical mean-field theories, random-matrix tools, and Fokker-Planck formalisms, and to a mindset emphasizing universality, scaling, and tractable limits with explicit validity regimes. We survey recent progress on understanding modern deep learning through this lens, including mean-field analyses of wide networks, spectral and geometric perspectives on loss landscapes, stochastic-gradient-based training viewed as a dynamical process, and phase-transition analogies that organize phenomena such as overparameterization, generalization, and representation change. Our goal is to synthesize these threads into a coherent framework that clarifies what each approximation explains, when it is expected to hold, and how apparently competing narratives relate or diverge. Together, these perspectives form a unified physical framework that views representation learning as a collective phenomenon in high-dimensional systems, bridging deterministic and stochastic regimes of gradient-based optimization.

cs.LG · cond-mat.stat-mech

新论文 · v1arXiv:2611.09136

Shortest Synchronizing Words on Product Automata

Henning Fernau, Igor Rystsov

原文摘要

We consider some operations on finite automata graphs, in particular various product, union and merge operations, and investigate how they relate to the parameter~$\mathrm{rt}$, the \emph{length of a shortest synchronizing word}. We derive some lower and upper bounds for the operations that we study. We also examine several classes of automata (for instance, partially ordered, commutative or idempotent automata) that are preserved under these operations and show in which way the parameter $\mathrm{rt}$ behaves in these automata classes. Also, we consider automata classes that can be constructed by combining automata from better known classes; in particular, these new classes of automata will also satisfy the bound of the famous Černý conjecture. This also motivates us to study even more closure properties. In particular, we show that certain automata classes related to synchronization form pseudo-varieties. We also commence a similar study concerning the length of shortest homing sequences of Mealy automata.

cs.FL

新论文 · v1arXiv:2611.09133

DINO-Nucleus: Multi-Level Self-Supervised Features for Nucleus Instance Segmentation

Mohammad Sarhangzadeh, Elyar Esmaeilzadeh, Doruk Oner

原文摘要

Nucleus instance segmentation and counting are essential for quantitative microscopy, enabling reliable analysis of cell populations, tissue organization, and disease-related changes. However, accurately separating touching nuclei remains difficult, and many existing approaches rely on complex models or sensitive post-processing procedures. We present DINO-Nucleus, a parameter-efficient framework that leverages multi-level self-supervised DINOv2 representations for nucleus instance segmentation and counting. The model jointly predicts nucleus regions, pixel-wise instance flows, and explicit nucleus centers, while a consistency objective encourages the predicted flows to converge toward their corresponding centers. Multi-level transformer features provide complementary spatial and semantic information, and the pretrained backbone is adapted using lightweight LoRA modules to reduce fine-tuning cost. Experimental results show that DINO-Nucleus achieves strong segmentation and counting performance with parameter-efficient backbone adaptation. These findings demonstrate that parameter-efficient adaptation of multi-level self-supervised features can provide an effective solution for nucleus instance segmentation in microscopy images.

cs.CV

新论文 · v1arXiv:2611.09130

Auditing Grasp Feasibility Predictors with Planner-Verified Counterfactuals

Sajid Ansari, Antony Thomas, Girish Varma

原文摘要

Grasp-feasibility predictors report near-perfect accuracy on Task and Motion Planning benchmarks, but high accuracy on these benchmarks does not verify that a predictor uses the collision geometry that the motion planner checks. We propose a planner-verified counterfactual (CF) test: holding the grasp pose fixed, we insert a solid obstacle into the approach corridor, add its points to the model input, and let a planner re-derive the label, which flips from feasible to infeasible. Across eight predictors spanning point clouds, voxels, depth, and object tokens, CF-pair AUROC falls from high natural AUROC (0.920-0.996) to chance (0.470-0.504), and the flip holds across four planners, two arms, and a real-object obstacle. Predictors fail at different resolutions, from a bounding box to a 12.5 cm voxel. In the point-cloud models we dissect, the obstacle either moves the representation in a direction unrelated to whether it blocks the grasp or is not registered at all. A clearance-aware read of the corridor points, trained on the unmodified benchmark with no counterfactual scenes, reaches 0.983 CF-pair AUROC, but it remains bound to its trained obstacle placements; a placement-invariant clearance representation is still open. We release the counterfactual labels, metrics, datasheet, and relabeling pipeline at https://github.com/codewithsajid/graspfc-cf.

cs.RO

新论文 · v1arXiv:2611.09129

TouchAnnotator: Multi-Source Tactile Supervision with Privileged-View Distillation

Ao Li, Zhihao Yuan, Chubin Zhang, Kunrui Huang, Sheng Xu, Zengjue Chen, Junjie Wang, Jiawei Li 等 9 位作者

原文摘要

Egocentric video captures human-object interaction at scale but rarely includes tactile labels for hidden contact and pressure. We introduce TouchAnnotator, an ego-only bimanual tactile annotator trained with multi-source tactile supervision and privileged-view distillation. A canonical hand field unifies glove pressure, geometry-derived human contact, and robot fingertip deformation from six datasets and three embodiments, while source-aware masks preserve valid targets. During training, an EMA teacher observes synchronized ego and wrist views and distills hand-local representations and tactile predictions into a student that uses only ego video and estimated pose at inference. Compact past-clip memory supplies temporal context. We evaluate on EgoTouch, zero-shot FPHA transfer, and 860 synchronized glove recordings. The model transfers to bare-hand contact and produces qualitatively coherent tactile responses across bare-hand, gloved-hand, and robot embodiments. On measured recordings, it improves temporal accuracy by 5.38 points and Volumetric IoU by 5.02 points under a shared protocol. These results show that heterogeneous human--robot supervision and privileged training views can turn egocentric video into dense tactile annotations.

cs.CV

新论文 · v1arXiv:2611.09126

PAGSL: Path-Augmenting Graph Structure Learning for explainable scholar recommendation

Jiale Xu, Mingshu Ai, Junjie Huang, Tao Jia

原文摘要

Explainable scholar recommendation aims to identify potential scholars of interest and provide reasonable explanations for the recommendations. However, existing frameworks struggle with optimization-induced noise and "hub node bias", yielding trivial explanations that lack hierarchical depth and personalization. To this end, we propose a novel explainable scholar recommendation model, Path-Augmenting Graph Structure Learning (named PAGSL). PAGSL combines representation learning and semantic path knowledge to ensure recommendation performance while providing interpretable results from two perspectives. Specifically, it activates latent academic paths among entities through graph augmentation and employs a path-based neural network to encode these paths for recommendation. A masking mechanism with path score optimization is designed to generate concise and informative explanations. We evaluate PAGSL on three academic datasets (Scholat, AMiner, and ResearchGate), comprising approximately 49,000 authors and over 330,000 interaction records. Experimental evaluations validate that PAGSL outperforms state-of-the-art baselines, achieving significant improvements of 6.31\% in F1-score, 6.29\% in Accuracy and 5.95\% in AUC for recommendation. Crucially, in terms of explainability, we provide quantitative results and visualization effects. Furthermore, ablation studies validate the effectiveness of our heterogeneous convolution and path representation learning. PAGSL achieves strong performance in both recommendation accuracy and explainability.

cs.IR · cs.SI