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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 06:41 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 07:22 — 2026-11-22 07:22(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:2026-11-22 06:41最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 06:39(北京时间)
新论文 · v1arXiv:2611.20464

AdaModalX: Synchronization-Free MFM Inference for Distributed Multimodal Mobile Sensing via Progressive Data Orchestration

Xiangrui Xu, Sicong Liu, Zhiwen Yu, Zimu Zhou, Bin Guo

原文摘要

Multimodal foundation models (MFMs) support generalizable inference in distributed mobile sensing applications by integrating heterogeneous data streams. However, existing MFM inference pipelines typically require complete and synchronized multimodal inputs, whereas mobile sensing streams arrive asynchronously due to network variability and heterogeneous data volumes across modalities. Waiting for all modalities increases end-to-end latency, while inference with incomplete inputs can reduce accuracy. We argue that multimodal inference should depend on the utility of available information rather than modality completeness. Based on this principle, we propose AdaModalX, a progressive multimodal inference framework that decouples inference execution from modality synchronization through runtime utility-aware orchestration. At each device, importance-aware data uploading uses a lightweight probe distilled from the edge-side MFM to allow reliable samples to exit locally while uncertain samples continue uploading. At the edge, on-demand MFM activation constructs candidates from fully received samples and, when needed, imputed features derived from partially received delayed inputs. A lightweight contribution assessor built on frozen MFM encoders estimates candidate utility and activates the MFM once the candidate meets its corresponding utility threshold. Experiments on four mobile sensing applications show that AdaModalX improves the accuracy-latency trade-off, achieving up to 26.97% accuracy improvement and up to 64.75% end-to-end latency reduction.

cs.LG

版本更新 · v3arXiv:2610.24122

HAVANA: A Hierarchical Video-Action Model for Vision-Language Navigation

Dongzhihan Wang, Yi Du, Chen Wang, Xiuxian Li, Liang Xu

原文摘要

Vision-Language Navigation (VLN) requires long-horizon instruction-consistent planning and short-horizon path planning grounded in the currently observed geometry. Anticipating how future observations evolve along the instructed route provides predictive guidance beyond the current field of view, motivating video-action models (VAMs) that learn representations of future visual states. However, many existing VAMs couple future visual prediction with action generation during inference, despite their distinct temporal requirements: instruction-conditioned route guidance can be reused across multiple control steps, whereas local trajectories must continuously adapt to fresh observations. To bridge this gap, we introduce HAVANA, a dual-system VAM that decouples predictive reasoning from reactive local planning. A slow system produces a compact language-conditioned latent plan from observation history, while a fast system combines the latest plan with the current observation to generate local trajectories. Their asynchronous execution enables rapid adaptation without repeated future prediction, and no future video is generated during inference. Experiments on OmniNavBench demonstrate state-of-the-art navigation performance over prior baselines, while zero-shot real-world deployments further show robust generalization to unseen environments.

cs.CV · cs.RO

版本更新 · v3arXiv:2507.00358

Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problems

Yilie Huang, Xun Yu Zhou

原文摘要

We study reinforcement learning (RL) for a class of continuous-time stochastic linear-quadratic (LQ) control problems, where volatilities depend on both states and controls while states are scalar-valued and there are no running control rewards, the last feature also leading to the so-called indefinite LQ controls. We propose a model-free, data-driven exploration mechanism that adaptively adjusts entropy regularization by the critic and policy variance by the actor. Unlike the constant or deterministic exploration schedules employed in the existing literature, which require extensive tuning for implementations and ignore learning progress during iterations, our adaptive exploratory approach boosts learning efficiency with minimal tuning. Despite its flexibility, our method achieves a sublinear regret bound that matches the best-known model-free results for this class of LQ problems, which were previously derived only with fixed exploration schedules. Numerical experiments demonstrate that adaptive explorations accelerate convergence and improve regret performance compared to the non-adaptive model-free and model-based counterparts.

cs.LG · cs.AI · eess.SY · math.OC

版本更新 · v3arXiv:2511.01390

SEPS: Semantic-enhanced Patch Slimming Framework for fine-grained cross-modal alignment

Xinyu Mao, Junsi Li, Haoji Zhang, Yu Liang, Ming Sun

原文摘要

Fine-grained cross-modal alignment aims to establish precise local correspondences between vision and language, forming a cornerstone for visual question answering and related multimodal applications. Current approaches face challenges in addressing patch redundancy and ambiguity, which arise from the inherent information density disparities across modalities. Recently, Multimodal Large Language Models (MLLMs) have emerged as promising solutions to bridge this gap through their robust semantic generation capabilities. However, the dense textual outputs from MLLMs may introduce conflicts with the original sparse captions. Furthermore, accurately quantifying semantic relevance between rich visual patches and concise textual descriptions remains a core challenge. To overcome these limitations, we introduce the Semantic-Enhanced Patch Slimming (SEPS) framework, which systematically addresses patch redundancy and ambiguity. Our approach employs a two-stage mechanism to integrate unified semantics from both dense and sparse texts, enabling the identification of salient visual patches. Additionally, it leverages relevance-aware selection with mean value computation to highlight crucial patch-word correspondences, thereby improving cross-modal similarity assessment. Comprehensive experiments on Flickr30K and MS-COCO datasets validate that SEPS achieves superior performance, surpassing existing approaches by 23\%-86\% in rSum across diverse model architectures, with notable enhancements in text-to-image retrieval scenarios. Our implementation is available at https://github.com/Sweet4tars/seps.git.

cs.CV · cs.AI · cs.MM

版本更新 · v4arXiv:2610.03792

What Do Verifiable Rewards Teach Video-Language Models About Time? A Controlled Multi-Model Study

Avyay Sadhu, Patrick Cooper

原文摘要

Reinforcement learning from verifiable rewards (RLVR) has produced large reasoning gains in language models, and verifiable video benchmarks make the recipe directly applicable to causal-temporal video question answering. We present a controlled study of what RLVR actually teaches video-language models about temporal structure. We fine-tune four open models with group relative policy optimization (GRPO) under three data recipes using annotated synthetic questions, self-supervised real-video pretext tasks, and a one-to-one mixture, plus a targeted real-video augmentation arm. We evaluate the model-recipe grid on 105 CLEVRER questions with one correct option and on two real-video transfer sets. The 8B ordered gain is 4.8 points (95% video-bootstrap CI [-5.6, 15.1]), while blind accuracy increases 10.5 points ([0.9, 20.6]). The 4B model gains an accuracy advantage for ordered over shuffled frames. On the real-video sets, the 8B synthetic-only checkpoint loses 26.7 and 25.2 points, with smaller regressions under mixed and augmented recipes. In a separate scene-disjoint, single-gold Qwen3-VL-8B experiment, supervised fine-tuning (SFT) and GRPO each complete 1,200 updates at three fixed seeds. GRPO minus SFT is -3.89 points in ordered accuracy (nominal 97.5% video-bootstrap CI [-7.36, -0.45]) and -2.78 points in ordered-minus-shuffled accuracy ([-6.60, 0.87]). Transfer differences are sensitive to parseability. Intervals quantify test-video uncertainty conditional on the fitted runs. The results show why benchmark accuracy, transfer, and presented-order sensitivity need to be evaluated separately.

cs.CV

新论文 · v1arXiv:2611.20461

LiveView: Real-Time Camera-Controlled Re-filming of Streaming Videos

Youcan Xu, Xinjie Huang, Jiaxin Shi, Hengye Lyu, Zhen Wang, Jun Xiao, Long Chen

原文摘要

Real-time camera-controlled video re-filming aims to synthesize target views from a streaming source video under online user-specified camera trajectories. This task poses two key challenges: maintaining synchronization and content consistency across views, and achieving low-latency rendering with long-horizon stability. Existing approaches are predominantly designed for offline full-sequence processing and rely on bidirectional attention or costly depth-based geometric preprocessing, making them unsuitable for low-latency streaming scenarios. To address these limitations, we develop a teacher-to-student framework that distills a high-fidelity bidirectional re-filming teacher into a few-step causal autoregressive student. We introduce Cross-Frame Injection to interleave each incoming source frame with its synchronized target latent, thereby establishing direct cross-view correspondence and improving content consistency. To ensure stable long-horizon generation, we further propose Shared Relative RoPE, which bounds temporal indices within the pretrained range, and Cycle Streaming Tuning, which exposes the student to extended cyclic trajectories during streaming training. These designs enable low-latency online video re-filming with precise camera control and sustained spatiotemporal consistency over long streaming rollouts.

cs.CV

新论文 · v1arXiv:2611.20460

Stochastic Self-Distillation for Flow-Based Vision-Language-Action Models

Jingru Guo, Alessandra Russo, Joey Bose, Christos Ziakas

原文摘要

Flow-based vision-language-action (VLA) models achieve strong performance in robotics through imitation learning, yet fine-tuning them with on-policy reinforcement learning (RL) is limited. In group-based RL methods like Group Relative Policy Optimization (GRPO), every rollout step requires multi-step ODE integration, and the sampler's limited stochasticity leads to rollout groups with low variance. We propose VLA-SSD, which addresses both high inference latency and limited stochasticity. In particular, our method self-distills a pretrained flow-matching action head into a stochastic one-step policy by conditioning a single-jump generator on a Brownian path. We derive a conditional action density via our stochastic one-step policy, enabling efficient post-training via likelihood-ratio RL algorithms. We show that distilling VLA-SSD from the $π_0$ VLA reduces the action head's forward-pass time by a factor of 7.7, at the cost of a 5.5% relative decrease in the success rate on the LIBERO benchmark. However, by leveraging the increased sample diversity of VLA-SSD during group generation, post-training a $π_{0.5}$ VLA using GRPO yields a 20.6% relative improvement.

cs.RO

新论文 · v1arXiv:2611.20459

Designing Deceptive Model Organisms that Successfully Evade Auditing

Vasisht Duddu, Mark Wang, Lipeng He, Tim G. J. Rudner

原文摘要

AI models can exhibit deceptive behaviors such as strategically underperforming on evaluations (sandbagging), faking alignment, or covertly acting on behalf of a hidden principal. Safe deployment therefore requires auditing techniques that can reliably detect such behaviors. To develop and test these techniques, we can train model organisms (MOs): models that exhibit deceptive behaviors and serve as realistic evaluation testbeds. However, for such testbeds to be informative, MOs must actively anticipate and resist auditing---a gap in prior work that can lead to overestimation of auditing effectiveness and underestimation of safety risks. We address this gap by designing MOs that capture worst-case deceptive behavior and evade high-effort auditing. Focusing on sandbagging, we frame MO design as a security game between an auditor and a deceptive model and identify three design requirements for sandbagging MOs: (i) effectiveness (underperforming on targeted capabilities), (ii) utility preservation (maintaining performance on all other capabilities), and (iii) robustness (resisting auditing). We propose three MOs: two optimized against blackbox auditing techniques and one optimized against both blackbox and whitebox techniques. Through a comprehensive evaluation, we show that, unlike MOs from prior work, our MOs satisfy all three requirements, providing worst-case baselines for developing and evaluating future auditing techniques.

cs.CR · cs.AI

新论文 · v1arXiv:2611.20458

VISTA: A Framework for Vision-Informed Semantic Traffic Awareness

Murat Arda Onsu, Poonam Lohan, Burak Kantarci, Aisha Syed, Matthew Andrews, Sean Kennedy

原文摘要

The Internet of Things (IoT) is transforming intelligent transportation systems by connecting roadside cameras, edge computing units, vehicles, and traffic infrastructure into a shared sensing and decision-making ecosystem. However, transmitting raw traffic video over vehicle-to-everything (V2X) links is bandwidth-intensive, while deploying large multimodal models directly on resource-constrained vehicles is often impractical. To address these limitations, this article proposes VISTA (Vision-Informed Semantic Traffic Awareness), a multimodal vision-language edge-intelligence framework that combines predictive video representation learning with lightweight language-based reasoning to provide communication-efficient traffic situational awareness. In the proposed architecture, roadside surveillance units employ the Video Joint Embedding Predictive Architecture (V-JEPA) and an attentive-pooler module to convert traffic video clips into compact future-scene embeddings. These embeddings are transmitted through V2X links to vehicle-mounted systems, where a TinyLlama small language model, enhanced with a custom visual adapter, interprets the embeddings alongside natural-language (NL) traffic queries. VISTA enables vehicles to obtain interpretable traffic information, reason about upcoming scene dynamics, and identify potential collision risks without receiving raw video streams. Experimental results in a digital-twin urban traffic environment show that VISTA achieves 97.77% accuracy and an 89% F1 score for future collision prediction while reducing the communication payload by several orders of magnitude compared with raw RGB video transmission. These results demonstrate the feasibility of embedding-based multimodal intelligence for low-latency, communication-efficient, and safety-oriented IoT-enabled transportation systems.

cs.CV · cs.LG · cs.NI

新论文 · v1arXiv:2611.20455

Embeddings vs. Grep: Rethinking the Dense Advantage in Code Search

Siqiao Xue, Ziyin Zhang, Zihan Liao, Jin Qin, Yixiang Mu, Hang Yu

原文摘要

Code-search benchmarks show dense encoders well ahead of BM25, yet coding agents do well with \texttt{grep}. What does this dense advantage measure? Existing benchmarks cannot tell: they use curated queries, old code and a handicapped BM25. To find out, we build Repo-Premium, a realistic repository-level code-search benchmark. It ranks files in real repositories, with curated and raw queries in Python, JavaScript, TypeScript, Go, Rust and Java, pull requests from 2022 to 2026, and a preregistered test pool over $91$ repositories. Our experiments trace the advantage to two sources: evaluation choices that favor dense retrieval, such as splitting files into chunks for BM25 and counting edited tests as relevant, and queries that lack the code's rare identifiers. Expanding the query with LLM-written identifiers (generate-then-grep) helps BM25 far more than dense retrieval, letting it match dense retrieval in every Python pool, even on pull requests opened after the LLM was released. No method we tried predicts which retriever will win on a given query. From these results we derive three guidelines: measure dense gains against a fair lexical baseline, fuse dense retrieval with BM25, and add the code's words to queries that lack them.

cs.SE

新论文 · v1arXiv:2611.20454

KVMARK: Fragile Watermarking for KV-Cache Integrity in Latent Multi-Agent Systems

Marjan Beheshti, Ronghua Xu

原文摘要

Latent multi-agent communication directly transfers Key-Value (KV) cache tensors between transformer-based agents, bypassing text serialization entirely. While computationally efficient and reasoning accurate, this communication channel is opaque and vulnerable to man-in-the-middle tampering, a threat vector unaddressed by existing text-based or behavioral watermarks, which cannot operate on continuous internal representations. To address this vulnerability, we propose KVMark, a training-free, zero-bit KV-cache watermarking framework to verify inter-agent handoff integrity. Our framework introduces four core technical components: (1) position-dependent sign patterns that guarantee first-order statistical invisibility while preserving downstream attention survival; (2) per-head sign patterns with aligned detection to defeat head-averaging attacks; (3) a three-tier depth-aware strength schedule that equalizes detection sensitivity across transformer layers while maintaining invisibility against nine statistical profiling strategies; and (4) content-bound key derivation that cryptographically binds watermarks to input contexts, preventing replay attacks under Kerckhoffs's principle. Empirical evaluation on a four-agent latent pipeline demonstrates $100\%$ detection across $1{,}500$ handoffs with a $0.0\%$ false positive rate ($\text{AUROC}=1.0$), $100\%$ layer-level tamper localization ($17/17$ attacked layers identified with $0/19$ false positives), and no statistically significant reasoning accuracy degradation across four benchmarks ($N{=}300$--$500$). Furthermore, the framework enables multi-hop cascade verification to isolate compromised agents (500/500 detection at three hops), withstands adaptive white-box adversaries and the Out-of-Sight DiffMean attack (up to $α=8.0$), and generalizes seamlessly to Qwen3-8B without re-tuning (1,500/1,500 TPR).

cs.CR

新论文 · v1arXiv:2611.20452

XMimic and XSoma: Learning Humanoid Motion Tracking and Locomotion in Under a Minute

Nico Bohlinger, Jan Peters

原文摘要

We present XMimic and XSoma, which learn humanoid motion tracking and locomotion on rough terrain in under a minute of training. Both follow SuperMimic, which learns a world model of the robot and optimizes the policy with analytic gradients through short rollouts imagined in this model. Existing implementations of this method do not make use of larger GPUs, as every training iteration is a long chain of small GPU operations that run one after another. XMimic and XSoma therefore shorten this chain and run the steps of every iteration at the same time on up to four GPUs. We compile the complete training loop with JAX, including the MuJoCo Warp simulator. For locomotion, XSoma leaves only the dynamics of the robot to the world model and computes everything else exactly, including the terrain height under the feet. It learns with a horizon of one second and without a critic. On four H100 GPUs, XMimic learns to track all 40 LAFAN1 clips with the Unitree G1 in 0.86 minutes, 3.7 times faster than BlinkMimic on one GPU. XSoma reaches the tracking target that Holosoma's tests set for FastSAC in 0.77 minutes, 12.3 times faster than FastSAC on one GPU, while needing only an eighth of its environment steps.

cs.RO · cs.LG

新论文 · v1arXiv:2611.20451

Generative AI-Driven Parametric Design Optimization Framework for Vehicle Closure Systems

Dongeon Lee, Yurim Lee, Jiyong Kim, Sanghyeon Kim, Sanghyun Lee, Seungyeon Shin, Jeahong Kim, Namwoo Kang

原文摘要

This study presents a generative AI-driven parametric design optimization framework integrating performance-oriented generation with editable computer-aided design (CAD) and downstream computer-aided engineering (CAE) analysis for industrial vehicle closure systems. The framework is demonstrated on an automotive tailgate assembly with complex geometry, coupled components, and competing performance and feasibility requirements. A production-oriented CATIA model is restructured into a reference-based parametric template with a 13-dimensional design representation. An automated CAD/CAE workflow generates parametric models, performs structural analysis, and constructs a database of mass, maximum displacement, and maximum von Mises stress. Gaussian process regression surrogates predict performance, while diffusion and flow matching models generate design candidates. The design problem minimizes mass and maximum displacement, with stress assessed as an engineering feasibility constraint. Performance-guided generation using surrogate guidance and performance-aware training using a performance-aware loss incorporate engineering objectives, with sensitivity to guidance scale and loss weight evaluated. Generative search is compared with NSGA-II under matched evaluation budgets using a common surrogate model. Selected Pareto-region candidates are reconstructed in CATIA and re-evaluated through native CAE; all verified candidates are successfully regenerated and analyzed. Relative to the baseline, the knee-point design reduces mass by 7.1% and maximum displacement by 29.4%, while extreme verified solutions achieve maximum reductions of 10.3% and 37.3%, respectively. The results demonstrate performance-oriented multi-objective design exploration compatible with editable industrial CAD and native engineering verification.

cs.LG

新论文 · v1arXiv:2611.20449

MAGE: Meta-path Adaptive Graph Evidence for Transferable Multimodal Graph Learning

Haiyang Jiang, Tong Chen, Xinyi Gao, Hao Wang, Hongzhi Yin

原文摘要

Multimodal graphs integrate textual and visual attributes with relational structures, providing a rich representation of complex real-world data. To enable the broad applicability and reuse of graph models, it is crucial for models trained on source graphs to generalize to unseen graph domains. However, this is challenging because cross-modal interactions among neighbors and the neighboring information needed for prediction can vary across target nodes and graph domains. This gives rise to two key challenges: adaptive cross-modal neighborhood fusion, which captures and integrates cross-modal interactions among neighbors to accommodate variations across nodes and domains; and target-specific evidence selection, which identifies the neighboring textual and visual information needed for each target node to support LLM-based prediction. In light of these challenges, we propose MAGE (Meta-path Adaptive Graph Evidence Prompting), a framework for transferable multimodal graph learning. MAGE represents textual and visual node views separately in a heterogeneous graph and introduces two complementary components. Meta-path Adaptive Multimodal Propagation (MAMP) adaptively aggregates neighborhood information along heterogeneous meta-paths and compresses it into graph-aware soft tokens. Evidence-Guided Instruction Tuning (EGIT) selects relevant neighboring evidence for each query and incorporates its graph-aware representations into instructions for a frozen multimodal LLM. Together, these components support transfer from multiple source graphs to unseen target graphs without target-domain parameter updates. Experiments with three source graphs and four unseen target graphs demonstrate strong cross-domain transfer performance on node classification and link prediction, without requiring parameter updates on the target domains.

cs.IR

新论文 · v1arXiv:2611.20447

The Logic Chain Breaking Point: A Controlled-Variable Benchmark for Reasoning Degradation in Open-Weight Language Models

Akif Islam, Mohd. Ruhul Ameen, Md. Ekramul Hamid

原文摘要

We introduce The Logic Chain Breaking Point, a controlled-variable benchmark for deductive reasoning in open-weight language models. It spans three phases: (i) pure modus-ponens chain scaling, (ii) distractor resilience with a fixed core chain, and (iii) contradiction detection under primacy versus recency placement. Independent variables follow a powers-of-two sequence $v \in \{1,2,4,8,16,32,64,128\}$, with ground truth known by construction. We evaluate sixteen open-weight models across instruction-tuned and reasoning-tuned panels, including a small-model suite and a larger local-model extension. All models are evaluated with greedy decoding under model-appropriate context and output budgets, while context- and length-limited trials are quarantined from the valid accuracy denominator. Our results reveal a sharply non-monotonic difficulty surface: pure deductive chains up to $L=128$ remain near saturation for most models, and distractor noise causes only model-specific degradation at high $D$, while the inconsistent premise condition has the lowest accuracy. Instruction-tuned models, including larger 24B--27B baselines, score essentially zero on inconsistent premise sets, while reasoning-tuned models recover only partially and remain below reliable accuracy. Within this benchmark, inconsistent premise sets are associated with the strongest degradation under the benchmark's abstention-based scoring rule.

cs.AI

新论文 · v1arXiv:2611.20446

LEDGE: Separating Critic and Editor Failures in Text-to-Image Self-Correction

Vyom Agarwal, Mokshda Gangrade, Samet Ayhan, Giacinto Paolo Saggese

原文摘要

Text-to-image (T2I) self-correction combines a vision-language model (VLM) critic that diagnoses errors and proposes instructions with an image editor that executes them. End-to-end evaluation obscures whether failures arise from incorrect diagnoses or an editor unable to execute valid instructions. We introduce LEDGE (Learning Error Diagnosis in Generation and Editing), a framework that separates these bottlenecks. LEDGE compiles oracle edit instructions from GenEval while holding the generated images and the editor fixed, isolating the editor's correction capability from the critic's diagnostic accuracy. On Stable Diffusion 3.5 Large, oracle instructions raise GenEval from 72.0% to 81.2%, versus 74.1% for the baseline VLM critic. Yet 435 of 644 failed images remain unrepaired, exposing a substantial editor gap. We also use oracle labels from disjoint training prompts to supervise the critic. Oracle supervision raises exact diagnosis from 33.3% (the same VLM with our structured output, untrained) to 70.8%. With the same editor, the resulting critic improves GenEval from 42.2% (uncorrected) to 59.4% on Stable Diffusion 1.5, against 50.9% for the baseline critic, and from 72.0% to 76.0% on Stable Diffusion 3.5 Large, despite training only on Stable Diffusion 1.5. Improvements transfer to unseen object classes, a second editor, and independent T2I-CompBench judges and prompts. A small human evaluation confirms the ranking in estimated net corrections but suggests a smaller gain than detector-based evaluation. LEDGE thus distinguishes two limits of self-correction: knowing what to fix and being able to fix it.

cs.CV

版本更新 · v2arXiv:2609.00643

REVISE: Validity-Guided Recovery for Online Revisions in Agent Workflows

Ruoling Qi, Xuaner Wu, Penghang Liu, Jian Chen, Yirui Liu

原文摘要

Agent revisions expose a fundamental correctness--efficiency trade-off during concurrent execution. Discarding ongoing work preserves latest-version correctness but wastes progress that may remain valid, whereas reusing prior work preserves efficiency but risks propagating stale state into outputs and tool effects. Existing recovery strategies resolve this trade-off in an imbalanced way with coarse-grained policies: they either favor efficiency by allowing potentially stale work to continue, or favor correctness by restarting the workflow or recomputing a linear suffix from the earliest conflict, thereby discarding unaffected progress. We present \textsc{Revise}, a validity-guided runtime for fine-grained recovery in structured agent workflows. When a revision arrives, \textsc{Revise} first intersects its delta with recorded data and control dependencies and propagates the resulting impact through the partially executed DAG to identify affected work. It then stops invalid work, preserves validity-established progress beyond the earliest conflict, and recomputes only the affected region. Incomplete provenance conservatively expands recovery, while reused results are revalidated before commit. Analysis of real coding-agent traces show online recovery opportunities: 118 sessions retain observable work before a queued later message is delivered; across 167 overlapping assistant responses, enqueue-to-completion overlap reaches 56.55~s at p95. Across 300 challenging revision/commit executions, \textsc{Revise} matches a latest-version oracle with no stale outputs or effects. On unmodified LangGraph and LLMCompiler applications using Qwen3-14B, it reduces model calls by 40.6--56.0\% relative to full restart and by 31.3--43.6\% relative to suffix recomputation. Under serving pressure, it further reduces revision-to-correct-completion tokens by 13.26\% and improves SLO goodput by 3.07--5.43\%.

cs.AI

新论文 · v1arXiv:2611.20445

Explainable Federated Learning via Global-Local Attribution Alignment

Dawood Wasif, Terrence J. Moore, Chang-Tien Lu, Jin-Hee Cho

原文摘要

Federated learning enables on-device training without centralizing data, yet existing systems still struggle to provide explanations that are both locally faithful and globally consistent under strict privacy and bandwidth constraints. Prior approaches either keep explanations siloed across clients, transmit heavy or sensitive artifacts, or replace expressive task models with interpretable surrogates that sacrifice accuracy. We propose xFedAlign, a model-agnostic framework that decouples task optimization in parameter space from explanation coordination in a compact group space. Each client distills a lightweight surrogate to produce private, per-class top-k attribution artifacts, which are robustly aggregated by the server into a Global Explanation Prior that softly aligns client explanations without constraining task learning. Across image, text, and tabular benchmarks with IID and non-IID partitions, xFedAlign matches FedAvg accuracy while consistently reducing explanation drift and improving deletion and insertion AUC relative to Local-XAI, FedAttr-Agg, and Fed-XAI, with only a few kilobytes of additional communication per round. Privacy and robustness evaluations further demonstrate reduced membership inference advantage and increased resistance to attribution poisoning, enabling consistent and trustworthy explanations in federated learning.

cs.LG · cs.AI

新论文 · v1arXiv:2611.20443

Overview of the Plagiarism Detection Task at PAN 2026

André Greiner-Petter, Yun-Ang Wu, Yuka Kitamura, Kon Woo Kim, Maik Fröbe, Bela Gipp, Akiko Aizawa, Martin Potthast

原文摘要

The generative plagiarism detection task at PAN 2026 aims at retrieving the original scientific sources for given automatically generated textual plagiarism. We created two novel datasets of synthetically generated plagiarism following the premise of a malicious actor trying to generate papers with minimal effort while evading detection of undisclosed re-use. We utilized four widely available LLMs: GPT-OSS 120B, Llama 3.1 8B, Qwen 3.5 27B FP8, and DeepSeek-R1 Distill Llama 8B. In this task overview paper, we outline the creation of this dataset and summarize and compare the results of all participants with three baselines. For this year's task, we received 26 submissions from six teams that significantly outperformed our baselines.

cs.IR

版本更新 · v4arXiv:2511.19699

A Layered Protocol Architecture for the Internet of Agents

Charles Fleming, Luca Muscariello, Vijoy Pandey, Ramana Kompella

原文摘要

Large Language Models (LLMs) can learn domain-specific languages such as APIs and tool interfaces, enabling agents that act through standardized protocols like MCP. But LLM context windows cannot grow indefinitely, so scaling beyond individual capacity requires agent collaboration: the "Internet of Agents" (IoA). Current network stacks (OSI, TCP/IP) were designed for data delivery, not semantic coordination, so we propose two new layers: an Agent Communication Layer (L8) that standardizes message envelopes, speech-act performatives, and interaction patterns; and an Agent Semantic Layer (L9) that negotiates a shared context, grounds and disambiguates content against it, and provides consensus primitives for population-scale coordination. On two real datasets and two LLMs, L9's schema-grounded disambiguation improves accuracy on ambiguous requests by 13--72 percentage points over blind guessing, at no added cost when disambiguation is not needed; an ablation shows this gain is schema-specific for open-domain QA but not for structured slot-filling, where the protocol's round-trip structure alone already suffices.

cs.NI · cs.AI · cs.MA

版本更新 · v2arXiv:2606.30968

PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising

Koorosh Roohi, Javad Rajabi, Andrew Fleet, Babak Taati

原文摘要

Photomosaics are large images whose local regions are seen as independent tiles while their overall arrangement forms a coherent scene. Generating them at high resolution, with every tile convincing in its own right, is computationally expensive, since the canvas must hold many detailed tiles at once. We present PhotoQuilt, a training-free framework that generates photomosaics at arbitrary resolution. Diffusion models struggle to satisfy both scales at once, as direct high-resolution generation is costly and tends toward one smooth image rather than a mosaic, while patch-based tiling keeps local detail but loses global structure. PhotoQuilt resolves this with a bootstrapped tiled denoising procedure. We first produce a global composition at low resolution to fix the layout, then upscale it in latent space and re-inject noise to restore generative capacity. Denoising proceeds within fixed tiles, so each forms its own image while the shared global structure holds them in one layout. Because tile generation is handled separately, PhotoQuilt scales to large canvases without quadratic attention cost. Experiments show that PhotoQuilt outperforms current baselines on both global structure and local realism.

cs.CV

版本更新 · v4arXiv:2609.36413

One from Infinity: Actualizing Futures from Pretrained World Models into Robot Actions

Bang Du, Yichen Xie, Shuqi Zhao, Yuxin Chen, Menglin Wu, Masayoshi Tomizuka

原文摘要

A pretrained video world model admits many plausible futures for a scene, but a robot must realize the exact task-conditioned one. To turn world models into executable robot policies, existing methods fine-tune the heavy world model backbone using large-scale robot data and computational resources. Challenging this status quo, we argue that the expensive part has already been paid in the world model pretraining since the representation space of a video world model encoder lays out the diverse potential futures. In this case, what remains is to determine the future that accomplishes the task and to read out the actions that realize it. We formalize this task as actualization, which learns a task-conditioned realization on top of a prior supplied by a frozen world model encoder. This can be solved by a tiny actualizer model. We implement RoboActualizer with as few as 60M parameters on top of a frozen world model encoder. The actualizer is composed of two lightweight DiT experts that jointly predict future latents and actions by flow matching. The model can be trained entirely on a single GPU with 32 GB peak memory. With up to 100x fewer trainable parameters than existing WAMs and VLAs, RoboActualizer reaches great performance on simulation benchmarks including LIBERO, LIBERO-Plus, RoboTwin 2.0 and five tasks on two real-world platforms, with a low latency of 39 ms that allows real-time control.

cs.RO

版本更新 · v5arXiv:2610.24865

Self-organizing recruitment cascades couple Levy search to a clustered maximum-entropy resource field

Galen J. Wilkerson

原文摘要

Foraging recruitment is modeled as a contagion: an agent finding a resource triggers a linear-threshold cascade on the group's communication network. Because activation is degree-normalized, crowding shuts the cascade off, causing the swarm to aggregate on a resource and then disperse to explore again. Acting on the cascade moves agents in space, rewiring the network; recruitment and exploration are thus one coupled process, and removing this coupling alone abolishes self-limitation. Recruitment spreads only within a connectivity window bounded below by percolation onset and above by degree-blocking. The swarm self-organizes to the near-critical edge of this window--self-organized quasi-criticality--hovering near but below the critical point without settling onto a size-invariant critical state, with a finite-correlation-time activity spectrum (Lorentzian-like, not 1/f) consistent with local criticality. Recruitment raises harvest up to 2.7x over solitary search on sparse, clustered fields and loses (down to 0.37x) on abundant or uniform ones; because resources generically aggregate, the favourable regime is the common one. The Levy search and resource field are both least-committal: a maximum-caliber walk coupled to a maximum-entropy point process whose generic sign is clustered, with the optimal search exponent tracking the field's fractal dimension. Heavy-tailed Levy exploration crosses sparse voids while recruitment cascades exploit clusters by switching agents to short local steps, binding exploration and recruitment into a single self-organizing cycle.

physics.soc-ph · cs.DC · cs.SI · math-ph · physics.bio-ph

版本更新 · v2arXiv:2603.27850

Automated Code Efficiency Optimization via Agent Skill Mining

Zimu Wang, Yuling Shi, Mengfan Li, Zijun Liu, Jie M. Zhang, Chengcheng Wan, Xiaodong Gu

原文摘要

Code efficiency is a fundamental aspect of software quality, yet how to use large language models (LLMs) to optimize correct programs remains challenging. Prior approaches rely on one-shot rewriting, retrieved exemplars or instructions, fine-tuning, or candidate search. In this paper, we present EffiSkill, a two-stage framework that models recurring slow-to-fast transformations as Operator Skills: persistent cards that record a transformation's intent, applicability, procedure, expected effect, and risks. Stage I distills frozen, language-specific skill libraries from slow/fast program pairs. Stage II diagnoses a new program, retrieves relevant skills, composes alternative plans, and generates up to eight candidates. These steps finish without candidate-execution feedback; public tests then filter and rank candidates, and held-out private tests determine reported correctness and speedup. Across 623 EffiBench-X tasks per language, two backbones, and separate Python and C++ evaluations, EffiSkill achieves the highest observed OPT@1 and OPT@8 among the compared methods in all four settings. Its OPT@8 margins over the strongest baselines range from 4.98 to 12.52 percentage points. These results support broader successful optimization coverage for the complete skill-guided pipeline under a shared output budget.

cs.SE · cs.CL

版本更新 · v2arXiv:2607.20817

Spectrogram-Based Joint Detection, Localization, and Classification of Events in Continuously Recorded IBR Waveforms

Shivanshu Tripathi, Maziar Raissi, Hamed Mohsenian-Rad

原文摘要

Continuously recorded high-resolution power system waveforms capture fast dynamics and transient events. However, extracting actionable insights from these large volumes of data requires automated event detection, temporal localization, and classification. This paper proposes a spectrogram-based framework that jointly detects, localizes, and classifies events in voltage and current waveforms at the terminal of an inverter-based resource (IBR). We recast this problem as a temporal object detection problem using time-frequency representations that explicitly reveal transient and harmonic signatures. The short-time Fourier transform is applied to each waveform channel, and the resulting log-spectrograms are stacked into a multi-channel tensor and processed by a U-Net architecture to jointly estimate event occurrence, temporal boundaries, and event type. A network of the same depth and width operating on raw waveform samples serves as a baseline. Experiments on synthetic single-phase disturbances and three-phase faults in IBR terminal recordings demonstrate that the proposed approach substantially improves event detection and temporal localization compared with the raw-waveform baseline, particularly at finer time-frequency resolutions, while also improving classification accuracy.

cs.SD · eess.SY

新论文 · v1arXiv:2611.20435

iEEG Can Help EEG: Improving Clinical Scalp EEG Analysis through Intracranial Priors

Xianglong Bao, Yi Ding, Zengxiang Li, Nan Liu, Kewen Wang, Zhe Wang, Ming Jin

原文摘要

Scalp electroencephalography (EEG) is a cornerstone of clinical brain monitoring, making the quality of its signal fundamental to downstream tasks and models. However, that signal is heavily contaminated by non-neural interference and blurred by volume conduction. Existing methods operate almost exclusively within the scalp modality, so they inherit the contamination they would need to overcome. In practice, intracranial EEG (iEEG) observes the neural activity with far higher fidelity, yet it is invasive and therefore scarce, and the two modalities are rarely recorded as pairs at scale, share no common channel space, and offer no clean ground truth to directly supervise a mapping. Motivated by the neuronal synchronization mechanism shared by the two modalities, we propose a reprogramming approach that fits a signal-to-signal model on iEEG alone and freezes it as a cross-modal prior. We introduce ReBrain, a framework to transfer an iEEG-learned prior to scalp EEG, which re-expresses any scalp signal through that prior and can be inserted upstream of any downstream model with no pairing or fine-tuning. ReBrain consistently improves host models across recordings from multiple hospitals and across architecture families, and our analysis traces this gain to genuine neural structure carried by iEEG rather than to the architecture itself. This work provides evidence that a scarce clean modality can serve as a transferable prior for an abundant noisy one, offering a general recipe for cross-modal transfer among biosignals. Our code is available at https://github.com/Xianglong-Bao/ReBrain.

cs.LG · eess.SP · q-bio.NC

新论文 · v1arXiv:2611.20431

UrbanTwin Sim2Real LiDAR Challenge 2026: Site-Calibrated Synthetic Data and Multi-Detector Fusion for Roadside 3D Detection

Arnav Kumar, Brijesh Soni

原文摘要

This report summarizes the work submitted by team arnav007 (submission ID 1054222) for the UrbanTwin Sim2Real LiDAR Challenge (V2X-Real track) at the IEEE BigData Cup 2026. The primary objective is to train 3D detectors for vehicles, pedestrians, and trucks using only synthetic roadside LiDAR data, and to generate synthetic scans that are realistic enough to be indistinguishable from real ones. A CARLA based pipeline is developed and calibrated to the fixed sensor site, accurately modeling the range image, including no-return beams, based on unlabelled real development scans. A combined inference detector, using multiple 3D detectors (VoxelNeXt, PV-RCNN, and SECOND) trained exclusively on synthetic data, is also proposed. Each scan is aligned to the synthetic ground plane and processed through the detectors at multiple ground heights. The resulting bounding boxes are fused using bird's-eye view (BEV) clustering, followed by class-specific post-processing to refine heading, box size, and filter low-confidence detections. The final submission achieved a combined score of 0.8947. The ablation study shows that per-scan ground leveling more than doubled the real-scan mAP, while fusing boxes across different heights and models further improved performance.

cs.CV · eess.SP

新论文 · v1arXiv:2611.20430

TrainExplorer: Autonomous LLM Post-Training via Plan-and-Decouple Exploration

Xuannan Liu, Tian Lan, Zekun Li, Xing Cui, Zhengfeng Yu, Feihu Jiang, Qianghuai Jia, Longyue Wang 等 12 位作者

原文摘要

LLM-based agents can automate model post-training, accelerating progress toward recursive self-improvement. Despite their promise, existing approaches remain under-explored and face two main challenges: (1) strategy lock-in that limits exploration beyond the initial strategy; and (2) coupled execution that obscures the effects of individual modifications. To address these challanges, we propose TrainExplorer, a multi-agent framework for autonomous post-training, that incorporates strategy planning and execution decoupling, to achieve broaden strategy exploration. First, strategy planning draws on scientific literature to construct a candidate search space of training strategies. Then, decoupled execution enables single-component interventions and attribution to guide strategy exploration. Extensive experiments on PostTrainBench demonstrate that TrainExplorer achieves a weighted aggregate score of 39.02, outperforming Claude Code using the same LLM by 7.32 and surpassing GPT-5.6 Sol-powered Codex, which scores 36.23. Code will be available.

cs.LG · cs.CL

版本更新 · v2arXiv:2609.06635

From JPEG to CUDA Batch: Measuring RGB Input Pipeline Throughput

Vladimir Iglovikov

原文摘要

We measure how many ready batches per second eight image input pipelines deliver to an NVIDIA L4. Each pipeline starts with RGB JPEG files and delivers synchronized CUDA float16 batches of 256 images. The benchmark contains 1314 measurements across 73 recipes. On the 34 recipes shared by all eight paths, DALI delivered a median of 19.7 batches/s and AlbumentationsX (AX) delivered 17.1. DALI was fastest on 34 of those recipes. Median peak process GPU memory was 1,872 MiB for DALI and 404 MiB for AX.

cs.PF · cs.CV

版本更新 · v2arXiv:2604.13511

Phase transition in compressed sensing using log-sum penalty and adaptive smoothing

Keisuke Morita, Federico Ricci-Tersenghi, Masayuki Ohzeki

原文摘要

In many real-world problems, recovering sparse signals from underdetermined linear systems remains a fundamental challenge. Although $\ell_1$ norm minimization is widely used, it suffers from estimation bias that prevents it from reaching the Bayes-optimal reconstruction limit. Nonconvex alternatives, such as the log-sum penalty, have been proposed to promote stronger sparsity. However, maintaining their algorithmic stability is challenging. To address this challenge, we introduce an adaptive smoothing strategy within an approximate message passing framework to mitigate algorithmic instability. Furthermore, we evaluate the typical exact-recovery threshold for Gaussian measurement matrices using the replica method and state evolution. The results indicate that the adaptive method achieves exact recovery over a broader region than $\ell_1$-norm minimization, although metastable states hinder the attainment of the information-theoretic limit.

cs.IT · cond-mat.dis-nn