跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+64已有论文修订
+93新增 AI 导读

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

统计口径与数据新鲜度

统计 2026-11-15 23:43 — 2026-11-16 23:43(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

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

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

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

浏览论文库

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

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.02425

Finite attainment and efficient computation of regularized quantum channel relative entropy

Yiwei Xu, Kun Fang

原文摘要

Quantum channel relative entropy can be nonadditive, making its regularization essential for asymptotic analysis. We study when the regularized value is attained at finite blocklength and how efficiently it can be approximated. For the first question, we establish a sharp dichotomy: the regularized value is either attained already at the single-copy level, implying additivity at every blocklength, or is never attained at any finite blocklength. Notably, a simple two-copy additivity test distinguishes between these alternatives for qubit channels and for channel pairs in arbitrary dimensions admitting an interior optimizer. We further show that both the interiority condition and finite nonattainment are generic, holding for almost every channel pair. For the second question, we establish explicit convergence rates for approximating the regularized channel relative entropy. For fixed channel dimensions, $\widetilde O(\varepsilon^{-3/2})$ channel copies suffice to approximate the regularized value to additive accuracy $\varepsilon$. Alternatively, a semidefinite hierarchy achieves the same accuracy at level $\widetilde O(\varepsilon^{-2})$, yielding a certified polynomial-time approximation. Together, these results reveal the intriguing structure and generic behavior of regularized channel relative entropy, sharpening our understanding of both its analytical and computational aspects.

quant-ph · cs.IT

版本更新 · v3arXiv:2604.22615

GazeVLA: Learning Human Intention for Robotic Manipulation

Chengyang Li, Kaiyi Xiong, Yuan Xu, Lei Qian, Yizhou Wang, Wentao Zhu

原文摘要

Embodied foundation models have significantly propelled the advancement of artificial general intelligence, yet they rely heavily on large-scale data. Recent studies identify human behavior as one of the most scalable sources for fostering robotic physical intelligence. However, the inherent embodiment gap remains a fundamental challenge for effective human-to-robot learning. In this work, we model human intention to enable efficient learning from human demonstrations. Among human behavioral cues, gaze simultaneously encodes high-level task semantics and exhibits a synergistic coupling with low-level action. By modeling intention through gaze, we derive a mid-level representation that facilitates cross-embodiment knowledge transfer. We demonstrate that robots can internalize human intentions to enhance manipulation, even without robotic intention annotations. To capture the synergy between intention and action, we adopt a Chain-of-Thought reasoning paradigm during inference. Our approach enables the execution of long-horizon and fine-grained tasks across diverse embodiments. Extensive experiments in both simulation and real-world demonstrate that our method consistently outperforms baseline approaches and generalizes to unseen settings. Project page: https://gazevla.github.io .

cs.RO

新论文 · v1arXiv:2611.03743

EvoMemState: Evolving Memory State for Personal Agents

Zhishang Xiang, Yunbo Tang, Zhongqiao Liu, Junkai Chen, Zerui Chen, Qingguo Hu, Yuxuan Zhang, William Grant 等 10 位作者

原文摘要

Long-term memory enables large language model (LLM) agents to provide continuous personalized assistance by retaining user information across interactions. Existing systems support this process through fact extraction, organization, updating, and retrieval, but largely maintain memories as independent facts. This fact-centric paradigm may overlook how new facts update, constrain, or conflict with earlier ones, while leaving their applicability, role, and priority for the current request implicit. In this paper, we introduce EvoMemState, a state-centric framework that augments persistent facts with two complementary states: Relational States that capture how facts remain valid and relate to one another as memory evolves, and a Reasoning State that determines how these facts should be applied to the current request. Specifically, EvoMemState consists of three key components: (i) Ontology-Guided Memory State Induction extracts Persistent Facts and constructs Relational States that maintain their validity, scope, and evolving relations. (ii) RL-Based State Evolution internalizes memory-use experience into a policy through reinforcement learning to generate a request-specific Reasoning State. (iii) State-Aware Reasoning then combines the relevant facts with their Relational States and the generated Reasoning State to guide the personal agent. Extensive experiments on long-term dialogue and memory-use benchmarks demonstrate consistent improvements over existing memory systems in retrieval completeness and memory-grounded response accuracy. Our code and implementation details are available at https://github.com/XMUDeepLIT/EvoMemState.git.

cs.IR · cs.AI

新论文 · v1arXiv:2611.02419

TERA: Task-Evidence Restoration for Underwater Object Detection under Bandwidth-Constrained Transmission

Heejin Kim, Joon-Seok Song, Eunil Park

原文摘要

Underwater object detectors are typically evaluated on pre-transmission images, overlooking additional degradation from bandwidth-constrained downscaling and compression. We introduce AquaTX, a controlled benchmark built from real underwater detection datasets with seen and held-out codecs. We also propose TERA, a metadata-blind receiver-side framework combining task-guided pixel restoration and dual-state feature correction while keeping the detector frozen. Under seen compound degradation, TERA improves mean average precision (mAP50:95, averaged over IoU thresholds from 0.50 to 0.95) from 37.7 to 50.0 on DUO-TX and from 31.5 to 41.3 on RUOD-TX relative to the frozen detector without restoration. TERA also preserves clean-input performance and remains competitive with detector fine-tuning under the held-out AVIF codec. These findings support transmission-aware evaluation and task-guided restoration for underwater object detection. Code is available at https://github.com/hijinkim/TERA.

cs.CV

新论文 · v1arXiv:2611.02415

Behavior-Discriminative Reward Shaping for Reward-Robust Reinforcement Learning

Zixuan Liu, Fangzheng Wu, Brian Summa, Zizhan Zheng

原文摘要

Reward-robust RL typically models misspecification by specifying an uncertainty set that constrains the discrepancy of plausible rewards from a base reward. However, such reward space discrepancies can be behaviorally irrelevant: under potential-based reward shaping (PBRS), many distinct rewards preserve policy ordering. This can introduce substantial redundancy into standard uncertainty sets and degrade optimization performance. We propose Shaping-Aware Reward-Robust RL, which constructs uncertainty sets over PBRS equivalence classes by projecting each reward to a canonical representative, ensuring that the resulting set contains only rewards that induce behaviorally distinct policy rankings. We prove that this projection preserves the optimal robust value while shrinking the uncertainty set and improving empirical performance. Using the connection between robustness and regularization, we obtain a practical algorithm to solve the shaping-aware reward-robust RL problem and enjoy convergence guarantees under standard assumptions. Experiments on benchmarks spanning diverse task domains and levels of complexity show consistent improvements over representative robust RL baselines and exhibit improved robustness to reward perturbations.

cs.LG

版本更新 · v4arXiv:2609.25816

Exponential Quantum Advantage in Testing Fourier Dimensionality

Kenny Chen

原文摘要

A boolean function $f$ has Fourier dimension $k$ if its strings with nonzero Fourier coefficients span a subspace of dimension $k$. We first consider the property testing task of determining whether a function has Fourier dimension at most $k$, or is $ε$-far from being so. We show that there is an $O(k/\sqrtε)$-query quantum property tester for this problem, which we show to be almost optimal. Combined with Gopalan \etal's classical lower bound of $Ω(2^{k/2})$, this demonstrates an exponential quantum advantage for this task. We complement this result with a $\tilde{O}(2^{k/2}/ε)$ classical tester, giving a quadratic improvement over the previous best tester, and essentially settling the classical query complexity. We then introduce and study the tolerant version of this problem. That is, determining whether a function is $αε$-close to having Fourier dimension at most $k$, or is $ε$-far from being so. Perhaps surprisingly, we show that this tolerant version of the problem is essentially just as hard as the standard version of the problem. That is, we show this problem has a $\tilde{O}(k/ε)$ quantum tester, and a $\tilde{O}(2^{k/2}/ε)$ classical tester.

quant-ph · cs.CC · cs.DS

版本更新 · v2arXiv:2610.35252

Labference: Benchmarking the Reasoning-Action Connection in Robotic Laboratories

Shitong Liu, Xu Yang, Jingwei Zhang, Sheng Lian, Xinyu Zhuang, Kaiwen Guo, Quan Liu, Chunhai Zhao 等 21 位作者

原文摘要

Realizing Embodied AI for Science requires robots to translate experimental goals into reliable physical procedures, reducing hazardous and repetitive human work while generating evidence for scientific discovery. Although language-based planning and learned manipulation provide complementary capabilities, their integration requires robots to adapt subsequent operations to actual execution outcomes. For example, an unsuccessful placement changes what must be done next, even when the experimental goal remains unchanged. Existing benchmarks assess planning, manipulation, and laboratory workflows through task completion and reasoning or execution metrics; however, aggregate performance leaves the connection between outcome-dependent choices and physical execution unresolved. To address this evaluation gap, we introduce Labference, a benchmark for evaluating how observed physical outcomes guide subsequent choices and how those choices translate into robotic laboratory actions. Its evaluation protocol is designed to test outcome-dependent behavioral adaptation through controlled evidence variations, while independently measuring operation selection, physical execution, and task completion. Matched Oracle-assisted continuations from shared checkpoints then assess which forms of support improve subsequent choices and task completion. Initial weighing evaluations reveal target-selection errors in the tested VLA policies despite successful object transfers, whereas GPT-driven control achieves correct selection but encounters execution failures and substantial computation costs. Together, these findings highlight the need to connect task-appropriate reasoning with reliable, timely action. By making this connection measurable and diagnosable, Labference supports targeted improvements toward autonomous experimentation for Embodied AI for Science.

cs.RO

新论文 · v1arXiv:2611.02414

SGR-OPSD: Learning from Subgoal Plans with Graph-Regularized Credit Assignment for Agentic Reinforcement Learning

Shu Liu, Yang Chong, WenShi Chen, Man Lan

原文摘要

OPSD provides dense supervision for agentic reinforcement learning through privileged information feedback. However, existing privileged information often lacks explicit task-progression planning, while teacher-student log-probability gaps reflect shifts in model preference rather than true task progress. To address these limitations, we propose Subgoal-Guided Graph-Regularized OPSD (SGR-OPSD), a framework that combines subgoal supervision with interaction-derived evidence for turn-level credit assignment. Specifically, SGR-OPSD uses LLM-generated subgoal plans to provide dense action-level guidance, converting them into advantage weights via a constrained, KL-regularized objective. To ground credit in observed outcomes, we construct a Subgoal Progress Graph that estimates empirical returns from sampled transition frequencies. The graph compares empirical action returns against the state average to derive preferences that calibrate the teacher's credit weights. Evaluated on ALFWorld, WebShop, and Search-QA across two model scales (Qwen2.5-3B and 7B), SGR-OPSD consistently outperforms GRPO and strong self-distillation baselines, improving success rates over GRPO by up to 7.4 percentage points and reaching 85.8% on ALFWorld with Qwen2.5-7B. Ablation studies confirm that subgoal guidance and graph-based weight calibration are key to these performance gains.

cs.AI

新论文 · v1arXiv:2611.02413

A Scientific Claim Stability Framework for Evaluating MRI Morphometry Pipelines

Duy-Cat Can, Dang-Duat Tran, Anh-Khang Nguyen, Quoc-Bao Tran, Trung-Hieu Do, Van-Tu Nguyen, Duy-Thanh Vu, Oliver Y. Chén 等 9 位作者

原文摘要

MRI morphometry pipelines are often evaluated by measurement agreement or downstream accuracy, yet their scientific value depends on the conclusions they support. Two pipelines can produce similar feature-level results yet support different conclusions about aging, cognitive decline, or neurodegeneration. We introduce Scientific Claim Stability (SCS), a claim-centric evaluation framework that converts region-of-interest (ROI) morphometry tables into auditable claim cards and evaluates their support under changes in dataset, processing pipeline, atlas, feature family, and target. Across 10,370 MRI scans from three datasets and five cohorts, SCS generates 2,783 claim cards and evaluates 89 claim-family pairs. The evaluation distinguishes stable, transferable, and fragile claims. FreeSurfer 8-FastSurfer comparisons show high evidence concordance and low anatomical-support overlap under the primary covariate specification. Acquisition-adjusted analyses show that the magnitude of support disagreement depends on the model specification. Structured review by specialists in geriatrics, neuroscience, and radiology, alongside auxiliary ChatGPT and Gemini reviewers, assesses claim plausibility, clarity, faithfulness, usefulness, and caution. SCS provides a reproducible way to audit the evidential stability of morphometry claims without assuming a universal gold standard.

cs.LG · q-bio.QM · stat.ME

新论文 · v1arXiv:2611.02412

A Novel Federated Learning Framework for Defending Against Gradient Inversion Attacks

Pengxin Guo, Ziying Huang, Shuang Zeng, Xiaodan Zhang, Weihong Ren, Yuyin Zhou, Liangqiong Qu

原文摘要

Federated Learning (FL) offers a paradigm for collaborative machine learning model training among clients, preserving data privacy by avoiding direct data sharing. However, the gradient information exchanged in FL has been shown to be vulnerable to Gradient Inversion Attacks (GIA), which can reconstruct sensitive user data. To counter these threats, various privacy-enhancing technologies like Secure Multi-party Computing (SMC), Homomorphic Encryption (HE), and Differential Privacy (DP) have been integrated into FL. While effective, these methods often introduce significant trade-offs between privacy and model utility. By revisiting the key to privacy exposure in FL under GIA, which lies in the frequent sharing of model gradients that contain private data, we take a new perspective by designing a novel privacy-preserving FL framework that effectively ``breaks the direct connection'' between the shared parameters and the local private data to defend against GIA. Our proposed framework, HyperFL++, leverages hypernetworks to generate local model parameters, where only the hypernetwork parameters are aggregated by the server. To ensure practicality, HyperFL++ incorporates a Row-wise Kronecker Decomposition (RKD) to mitigate the memory and communication overhead from the hypernetwork. Comprehensive theoretical analysis and extensive experiments validate our method's effectiveness in protecting data privacy while maintaining high model utility. Our code is available at https://github.com/Pengxin-Guo/HyperFL/tree/hyperfl%2B%2B.

cs.LG

版本更新 · v3arXiv:2609.36672

Human-inspired, Task-Dimension-Guided Exploration for Efficient Learning in High Dimensions

Fanyu Zhu, Jiahui An, Ni Ji

原文摘要

Efficient exploration in high-dimensional decision spaces remains a central challenge for decision-making systems. Humans, in contrast, can navigate large decision spaces with remarkable efficiency. Recent behavioral studies suggest that humans reduce dimensionality in large decision spaces by probing candidate feature dimensions, identifying reward-relevant ones, and restricting the effective decision space. Inspired by this mechanism, we propose TDGE (Task-Dimension-Guided Exploration), a human-inspired, model-agnostic algorithm with an automatically constructed task-dimension--feature--item hierarchy. TDGE follows a top-down exploration strategy: it first selects task-relevant feature dimensions, then identifies informative features within those dimensions, and finally recommends concrete items based on the selected features. Experiments on MovieLens-20M, LastFM, and Amazon recommendation datasets show that TDGE substantially improves exploration efficiency and cold-start adaptation over baseline algorithms. Comparisons with other structured algorithms and ablation studies attribute these gains to TDGE's hierarchical structure and semantic feature-space exploration, with robust results across clustering methods and hierarchy depths. Recommendation-trajectory visualizations also show exploration patterns similar to human dimension-guided behavior.

cs.LG

新论文 · v1arXiv:2611.02410

Spatial Organization Is Accessibility Structure: Hierarchical Screen Reading of Mobile UIs

Yongxiang Hu, Xuan Wang, Qingyang Qiu, Yingjie Liu, Chun Kang, Ruiying Zeng, Xin Wang, Yangfan Zhou

原文摘要

Screen readers for blind and low-vision (BLV) users flatten mobile UIs into a linear sequence. Modern mobile UIs, however, contain dozens of elements grouped by spatial layout. Such linear access is ill-suited for BLV users, who must infer each element's meaning and which elements form a functional unit. Drawing on a quantitative TalkBack audit and formative interviews, we present Spatial Screen Reader (SeeR), which builds a function-aware hierarchy from accessibility metadata and provides unit summaries with hierarchical navigation. Compared with TalkBack, SeeR reduces non-informative focus stops by 82.1% and navigation steps by 52.7%. With ten BLV participants, summaries helped them connect controls to their functions and skip nonessential elements, especially on unfamiliar pages, though extra navigation levels added effort when the target was already known. These findings recast spatial organization as accessibility information: apps and platforms should expose it, rather than leaving screen readers to infer it post hoc.

cs.HC

新论文 · v1arXiv:2611.02408

Deployment-constrained key estimation with a DSP-guided transformer reranker

Pardis Noorzad

原文摘要

Local music applications estimate key during library import and benefit from an analyzer that is small, fast, and runs in-process. We start from a compact chroma-template key analyzer that fits this budget but lags behind learned references. Learned systems reach higher accuracy, but their installed model and runtime dependencies can occupy tens to hundreds of megabytes. We present key lime, a 21.5k-parameter DSP-guided transformer reranker with a 115 KB model artifact and a 76.7 MB installed footprint, including the extracted ONNX Runtime. It adds 0.32 ms per track to deterministic DSP scoring. Trained from labels on 4,040 FMAK tracks, with 449 tracks for validation and 1,000 disjoint FMAKv2 tracks held out for evaluation, it improves MIREX from 61.08 to 73.55 +/- 0.46 and exact accuracy from 52.30 to 67.07 +/- 0.65 over three seeds (mean +/- population SD). It approaches a same-manifest local madmom KeyCNN reference at 74.16 MIREX. A 12-parameter circular input stage matches the accuracy range of a 468-parameter linear input projection.

cs.SD · cs.LG · eess.AS

新论文 · v1arXiv:2611.02407

Networked Synthetic Social Engineering on the Web

Bryan C. Boots

原文摘要

Several genuine AI services may repeat one unsupported source, and correcting that source may leave later reports unchanged. We examine these networked consequences of synthetic social engineering (SSE), deliberately misleading influence intended to redirect AI recipients from authorized objectives. Our framework connects social influence, information aggregation, and misinformation correction research to observable evidence and permission boundaries. It separates originating attempts from legitimate intermediaries' work and distinguishes identity, evidentiary support, and authorization. We test four relationships using Qwen3-4B and two briefing tasks across 1,080 research units in our Agent Service Exchange and Evidence Commons (ASE-EC). Multiple dependent publishers produced no supported increase in unsupported verification (78.3% versus 75.0%); publication availability left downstream violation reach at 40.0% in both arms. These comparisons direct attention to weaknesses already present in the reference workflows. High reference error rates and retained private handoffs preclude claims of immunity to social pressure. Without scope revalidation, corrections identifying dependent reports reduced residual invalid decisions from 14.4% to 8.1% at equal notification coverage and increased successful report repairs from 16/63 to 36/63. Scope revalidation added no demonstrated protection, and clearing dialogue offered no established recovery advantage. Unapproved requests persisted, all blocked by an external gateway. For designers, the findings caution against treating publisher count as independent evidence, notification as repair, or cleared histories as recovery. They support targeting corrections at reused reports, assessing factual and permission recovery separately, and enforcing authorization at execution.

cs.CR · cs.AI · cs.CY

版本更新 · v2arXiv:2506.12230

Statistical Machine Learning for Astronomy -- A Textbook

Yuan-Sen Ting

原文摘要

This textbook gives a systematic treatment of statistical machine learning for astronomical research, based on Bayesian inference. It shows how modern data analysis techniques connect to classical statistical methods and follow from familiar statistical principles. The Bayesian perspective, used throughout, gives priority to uncertainty quantification and statistical rigor, which scientific inference in astronomy needs. The textbook progresses from probability theory and Bayesian inference through supervised learning, including linear regression with measurement uncertainties, logistic regression and classification. Unsupervised learning topics cover Principal Component Analysis and clustering methods. We then introduce sampling and Markov Chain Monte Carlo, followed by Gaussian Processes as probabilistic nonparametric methods and neural networks in the broader statistical context. Our theory-focused approach derives each method from first principles with complete mathematical development and then shows its astronomical applications. We put statistical insight first and explain why algorithms work, when they are appropriate, and how they connect to broader statistical principles. From a solid grounding in classical methods and their theory, the treatment leads to modern techniques such as neural networks. With this grounding, readers can apply the methods to astronomical research with proper attention to assumptions, limits and uncertainty propagation, as large astronomical surveys require. The 22 companion tutorials apply the methods to astronomical data in Jupyter notebooks.

astro-ph.IM · cs.LG · stat.AP · stat.ML

新论文 · v1arXiv:2611.02405

MirrorComm: A Communication-Efficient Cooperative Perception Framework via Mirrored World Models

Shenghan Luo, Yin Xu, Cixiao Zhang, Yang Wang, Yujie Cao, Zhuoran Xiao, Wenjun Zhang

原文摘要

Cooperative perception (CP) requires substantial communication bandwidth to exchange sensing information among connected agents. A variety of compression techniques have been proposed to reduce transmission costs while retaining task-relevant information. However, most existing methods follow a frame-wise compression paradigm, overlooking temporal predictability and repeatedly transmitting information that could be inferred from historical context. To address these limitations, we propose MirrorComm, the first world model-based communication-efficient CP framework. Specifically, mirrored world models at the transmitter and receiver predict the transmitter's current observation from a shared history of its reconstructed observations. The transmitter compares this prediction with its current observation and selectively transmits observation updates to correct prediction errors, reducing repeated transmission of predictable information. Experiments on the OPV2V dataset across two downstream tasks including object detection and semantic segmentation show that MirrorComm reduces communication bandwidth requirements by up to approximately 66-fold while maintaining comparable performance to a state-of-the-art (SOTA) method. Ablation studies further demonstrate the effectiveness of the individual components.

eess.SP · cs.CV

版本更新 · v2arXiv:2608.15550

Adoption of Generative AI in the Workplace: Increasing and Shifting the Balance of Productivity and Communication Activity

Yulin Yu, Yan Chen, Rui Hu, Siddharth Suri, Scott Counts

原文摘要

Generative AI is transforming the workplace by augmenting and automating cognitive tasks, reshaping how organizations work and innovate while raising questions about workplace inequality and the future of work. Despite rapid adoption, empirical evidence on how these tools alter work practices and generate productivity gains remains limited. We examine how AI use affects the quantity and nature of information work using digital trace data from the Microsoft M365 application suite across multiple large international companies. Specifically, we study how generative AI adoption shifts the balance between communication and productivity-oriented activities, such as content creation in Word. Difference-in-Differences analyses show that AI adoption is associated with significant increases in both productivity (21.2%) and communication (7.1%) application actions among users who used the AI system more than 100 times over a 20-week post-adoption period. Among users with 100-500 AI use instances, higher AI usage is also associated with continued increases in both types of activity. The smaller increase in communication represents an overall shift toward individual, documentation-focused work and reflects mixed changes in communication, including decreases in reading and organizing email, compared with more uniform increases in productivity actions. These findings suggest potential efficiency gains and reductions in information overload, while highlighting the need to ensure that AI adoption does not weaken interpersonal communication and the diffusion of diverse information that supports innovation.

cs.HC

新论文 · v1arXiv:2611.02404

When Rewards Depend on the Group, GRPO Plays a Tournament

Junyi Gao, Yu Shi, Pingzhao Hu, Ewen M Harrison

原文摘要

Rewards for diversity, coverage and distribution matching make the reward of each sampled response depend on the rest of its group, and they are now routinely optimized with GRPO and RLOO. We prove that in this setting the group-relative baseline changes the objective. The expected update equals each response's own reward gradient plus $α$ times its effect on its groupmates' rewards, with $α=-1/(K-1)$ for groups of size $K$, so GRPO trains every response to beat its groupmates in a zero-sum tournament. It cannot see a pairwise diversity bonus when K=2, sees less than half of it at any K, and often does worse than using no baseline at all. Setting $α=+1$ gives Team-GRPO, an unbiased estimator for any group-dependent reward that works with two samples per prompt and requires no extra model calls for pairwise rewards. The theory predicts training quantitatively. It locates the fixed points of a 9B policy to within 0.02 in $\ell_1$ and predicts how concentrated trained policies become with Pearson r=0.995. On GlobalOpinionQA, GRPO collapses onto the majority answer and ends further from human opinion than the untrained model, while Team-GRPO cuts the error from $0.20$ to $0.08$. On NoveltyBench, Team-GRPO avoids the diversity collapse of GRPO and significantly improves set utility.

cs.LG · cs.CL

版本更新 · v3arXiv:2605.18599

Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling

Yihang Wu, Yihang Sun, Shaofeng Zhang, Zuxuan Wu, Junchi Yan, Xiaosong Jia, Yu-gang Jiang

原文摘要

Transformer-based models have advanced feedforward novel view synthesis (NVS). Current architectures such as GS-LRM and LVSM mix semantic information (e.g., RGB) and spatial information (e.g., Plücker rays) into a shared feature space. Since Plücker rays naturally carry lattice-like spatial structure, these designs can make the spatial bias interfere with appearance representation and degrade rendering fidelity. To this end, we propose to decouple the representation of feedforward NVS transformers into separate semantic and spatial tokens. The decoupled design keeps semantic and spatial information explicit in their branches while preserving cross-branch interaction through shared attention routing. Built on this design, we introduce optional categorized supervision and bidirectional modulation: the former provides branch-specific training signals, while the latter improves interaction between the two branches. Notably, the base decoupled design introduces virtually zero additional inference latency due to its architectural design. The proposed designs achieve consistent improvements, demonstrating effectiveness across decoder-only and encoder-decoder feedforward NVS models.

cs.CV

版本更新 · v2arXiv:2607.05849

CoPiT: Cognitive Pivot Translation for Digraphic Low-Resource Mongolian in the Traditional Script

Burte Bayarsaikhan, Serynn Kim, Buru Chang

原文摘要

Low-resource languages remain challenging for machine translation, and Mongolian is a representative case. As a digraphic language, Mongolian is written in both Cyrillic and Traditional scripts, which exhibit a severe imbalance in data availability. While the Cyrillic script is relatively well-resourced, the Traditional script remains extremely data-scarce and orthographically ambiguous, leading to substantial performance degradation in direct translation. We propose CoPiT, a cognitively motivated pivot-based translation pipeline that exploits this internal resource hierarchy by routing translation through the Cyrillic script. The pipeline explicitly resolves script-induced ambiguity in the Traditional script before translation, enabling more stable and accurate meaning transfer. Across multiple backbone models and target languages, CoPiT generally improves over direct translation, with substantial absolute BLEU improvements and up to 1.5-1.6x gains in COMET. These gains allow strong open-source models to match or outperform GPT-4.1 under comparable evaluation settings. Beyond inference-time improvements, CoPiT enables the construction of synthetic parallel data directly from Traditional-script text, mitigating data scarcity in realistic low-resource scenarios. We release a new multi-script parallel dataset covering Mongolian in both scripts alongside English, Korean, and Russian.

cs.CL

新论文 · v1arXiv:2611.02401

Accelerating LLM Decoding with In-DRAM Parallelism

Kevin Xu, Tatsuya Kubo, Daichi Tokuda, Shinya Takamaeda-Yamazaki, Issei Sato

原文摘要

Autoregressive decoding of large language models (LLMs) on edge devices is dominated by memory-bound general matrix--vector multiplication (GeMV) operations. Processing-using-DRAM (PUD) is a promising computing paradigm that can alleviate this bottleneck by reducing processor--memory data transfers and enabling massively parallel computation within DRAM (e.g., across 65,536 columns). However, weight matrices in individual LLM layers (e.g., a QKV matrix in Llama3 8B with 6,144 rows) are typically too small to fully utilize parallelism in PUD. To address this challenge, we propose an algorithm--system co-design for PUD-based LLM inference. At the algorithm level, we enable a subsequent projection to be packed with the current projection by reformulating it as a computation on the current residual state plus a correction for the residual update. Layer redundancy allows this correction to be approximated using fewer bit-serial steps. At the system level, we tailor data mapping and execution to improve utilization of either columns within DRAM subarrays (SIMD) or independently controlled banks (MIMD). Overall, we achieves up to $1.41\times$ end-to-end decoding speedup over the PUD baseline, corresponding to a $2.45\times$ speedup over processor-based execution.

cs.AR

新论文 · v1arXiv:2611.02400

Inverse Design of Finite-State Channels by Dynamic Measure Matching

Lav R. Varshney

原文摘要

Inspired by the optimization approach to biology, we formulate an inverse problem for communication with memory: construct a finite-state channel for which a given signaling behavior supports capacity-achieving codes. Dynamic measure matching is introduced to turn a directed-information converse into conditions on the channel dynamics. These conditions lead to a new notion of dynamic surprise: the log ratio of physical to test output probabilities with a continuation correction for future signaling opportunities. The matching inequalities bound its conditional mean. For fixed architecture, test law, and potential, channel row synthesis under convex physical restrictions is convex. For every signaling constraint represented by a finite irreducible constrained graph of positive entropy, we construct a channel law under which undesired inputs remain available and behaviorally distinct while incurring a strict information penalty. A noisy refractory family has an exact capacity plateau, followed by an interval in which Shannon and zero-error feedback capacities differ. Explicit zero-error codes attain capacity in the graph construction and on the plateau. In this family, a Gibbs choice maximizes the penalty and makes dynamic surprise equal its conditional mean on every transition, yielding an exact trajectory-wise likelihood identity, a finite-block bound on successful decoding with premature requests, and an exponential strong converse. An exact gap decomposition into action residuals and output-law divergence constrains every reliable capacity-approaching code. Within the strict plateau, positive discrimination exponents for unused dynamics require a positive rate loss, while sparse probing permits consistent estimation at asymptotic capacity. A chemical channel illustrates how premature stimulation can alter future responsiveness while leaving the immediate output law unchanged.

cs.IT

版本更新 · v2arXiv:2606.23321

Tmax: A simple recipe for terminal agents

Hamish Ivison, Junjie Oscar Yin, Rulin Shao, Teng Xiao, Nathan Lambert, Hannaneh Hajishirzi

原文摘要

Terminal-using agents have quickly become a popular and important downstream application of language models (LMs). Despite their prevalence, relatively little academic work has examined RL-based training of these models, due to difficult benchmarks, a lack of data, and a lack of simple baseline recipes. We present TMax, an open RL recipe for terminal agents that brings small open models closer to the frontier. While simple, our recipe achieves 33% on Terminal-Bench 2.0 with only 9B parameters, outperforming much larger models from prior work. Our recipe first involves generating data using a novel taxonomy, combining difficulty control, personas, and verifier diversification, which allows us to cheaply generate large amounts of terminal environments for RL and SFT training. We then train open-weight models using RL with our data, using a simple, outcome-only recipe, with small adjustments to improve stability. Our recipe works for models from 2B to 27B and across model families, dominating the Pareto curve for open terminal-agent performance at smaller sizes. We release our data, models, and code as a strong baseline for future open academic work on terminal agents at https://github.com/hamishivi/tmax.

cs.CL

版本更新 · v2arXiv:2610.04368

A multi-stage probabilistic framework to estimate gas-fired generator performance during extreme winter weather

Sajjad Uddin Mahmud, Anamika Dubey

原文摘要

Extreme winter weather has repeatedly disrupted gas-fired power generation in the United States, yet the plant-level data needed to systematically quantify outage risk remain proprietary. Using publicly available weather and electricity demand data together with anonymized generator contingency records from the North American Electric Reliability Corporation (NERC), we develop a three-stage Bayesian probabilistic framework for estimating winter-driven generator performance. Applied to New York State (2013--2022), the framework sequentially estimates: the hourly probability of a generator contingency event, the expected net available capacity conditioned on an event occurring, and the event duration. Colder conditions and higher electricity demand are associated with higher failure probability, lower retained capacity, and longer event duration. Under the most severe observed stress conditions, estimated mean hourly event probability reaches 24\% , while expected mean net available capacity falls to 13\% of nameplate rating. Full outage events have a median duration of 12.7 hours, while partial derating event duration increases from 2.4 to 7.1 hours with capacity loss severity. The proposed framework establishes a transferable baseline that utilities with access to plant-level records can directly extend to obtain more precise reliability estimates for operational planning and resource adequacy assessment.

cs.LG · stat.ML

新论文 · v1arXiv:2611.03742

Fixed Detectors, Moving Code: How Well Do Static Security Analyzers Hold Up over a Decade of C/C++ Evolution?

Junhua Tang, Zhengsong Zhang. Haipeng Cai

原文摘要

Static application security testing (SAST) tools are often deployed on the assumption that detectors configured today will remain effective on future code, including previously unknown vulnerabilities. We test this assumption using 20,000 vulnerable and fixed C/C++ cases from 1,116 open-source projects (2016-2025), evaluated with three CodeQL releases, three Infer releases, and one Semgrep configuration. To distinguish temporal effects from shifts in code composition, we compare yearly populations, project- and label-matched year pairs, and within-project trajectories. We investigate the largest within-project declines through repair diffs, detection predicates, alert locations, and execution logs, while accounting for failed, degraded, and costly analyses. Under changed-file case-label scoring, overall F1 ranges from 0.066 to 0.478, but count-based AUROC stays near chance (0.495-0.526). Newer CodeQL releases attain higher F1 alongside nearly parallel rises in recall and false-positive rate, not stronger separation of vulnerable from fixed cases. In project-matched year pairs, CodeQL R2024 has negative mean later-minus-earlier F1 at every source-year gap, whereas Infer v1.1 and v1.3 have positive means throughout. Among selected drops, only 6 of 39 CodeQL and 2 of 620 Infer findings overlap a changed repair line. For Semgrep, 78.96% of cases show parser or timeout diagnostics even though every run reports success. These results suggest that apparent changes in temporal SAST effectiveness can arise from broader alerting, changing analysis coverage, and incidental findings, not solely from losses in vulnerability detection. Evaluations of temporal sustainability should fix detector conditions, control for projects, inspect repair-level evidence, and report failed or degraded analyses.

cs.CR · cs.SE

新论文 · v1arXiv:2611.02395

Solver-Like Behavior in Large Language Models as Formalizers

Rikhil Amonkar, Stuti Mohan, Kevin Nguyen, Ceyhun Efe Kayan, Ronan Le Bras, Li Zhang

原文摘要

In the LLM-as-formalizer paradigm, a large language model translates a problem into a formal program and leaves the search to a solver, gaining the solver's guarantees. Formalizers are now often reasoning models that write a long reasoning trace before the program, yet they are judged only by the program's output. We find that the trace routinely does the solver's job, assigning, testing and ruling out values until it often reaches the full answer; we call this solver-like behavior (SLB). We define an ontology of SLB over the trace, the program and its output, and use LLM judges, checked against human labels, to label 2,000 generations from three reasoning models on four constraint satisfaction datasets, each formalized in a declarative and an imperative formal language. SLB appears in 85% of traces and takes 24% of reasoning tokens, yet the program usually recomputes the answer, so the effort is redundant. The 9% of programs that inherit the trace's answer also inherit its errors, and pass output-based evaluation whenever that answer is correct. The amount of SLB is not associated with accuracy, and SLB is more common in imperative Python than in declarative Z3 or PDDL. Cautionary prompts reduce it by only a quarter, but hiding the problem's values behind placeholders, which the program receives only at run time, removes 97% of it without loss of accuracy. Formalizers should therefore be evaluated by how their programs are reached, not only by what they output.

cs.CL · cs.AI

版本更新 · v3arXiv:2605.11442

Mobius Injection: From One-Shot Prompt Injection to Sustained Resource Exhaustion in AI Agent Infrastructure

Zi Liang, Ronghua Li, Yanyun Wang, Qingqing Ye, Haibo Hu

原文摘要

Large Language Model (LLM) agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services and LLM infrastructures. While prior research has extensively examined the security of LLMs and agents in isolation, the systemic risk of the agent acting as a disruptive "hub" within the user-agent-service chain remains largely overlooked. In this work, we expose a novel threat paradigm by introducing Mobius Injection, a sophisticated attack that weaponizes autonomous agents into zombie nodes to launch what we define as Agent-based and -Oriented DDoS (AbO-DDoS) attacks. Mobius Injection composes known indirect prompt injection and persistent agent components through a distinct structural mechanism named Semantic Closure, which induces sustained recursive execution of agent components through a single injection event. We demonstrate that this attack is lightweight for the adversary, can evade traditional volumetric DDoS monitors and input filters calibrated for low false-positive rates, and is highly configurable, allowing for surgical targeting of specific environments or model providers. To evaluate the real-world impact, we conduct extensive experiments across three representative claw-style agents and three mainstream coding agents, integrated with 12 frontier proprietary or open-weight LLMs. Our results demonstrate that Mobius Injection achieves substantial attack success across diverse tasks, driving single-node call amplification up to 51.0x. Under coordinated multi-node pressure, each infected node still drains about 123k--127k tokens on a shared five-GPU backend; benign request latency rises by abou 23x--24x, and coordinated infections eventually saturate shared capacity until benign traffic is effectively denied service.

cs.CR · cs.AI · cs.CL

新论文 · v1arXiv:2611.02393

IMUdrape: Generating Garment-Mounted Virtual IMU Data from Text through Physics-Based Cloth Simulation

Zikang Leng, Thomas Plötz

原文摘要

Inertial sensors are moving into clothing, from sensorized sportswear to garments instrumented with hundreds of IMUs. Sewn into clothing, a sensor no longer moves rigidly with the body: loose fabric slides, twists and swings, so a garment-mounted sensor records the motion of the fabric as well as that of the body, and this extra motion differs from one garment to the next. Models for such sensors need training data recorded with the deployed garment, yet labeled data are scarce. Virtual IMU data generated from videos or text have eased this scarcity for body-attached sensors, but existing generators attach their virtual sensors rigidly to the body. We present IMUdrape, which generates garment-mounted virtual IMU data from text through physics-based cloth simulation. IMUdrape synthesizes motion from activity descriptions, reconstructs the target garment as a sewing pattern from photographs, places virtual IMUs at the deployment's real sensor positions, and simulates the garment with an intersection-free contact solver, so that every simulation yields paired garment and body signals. On four real datasets with clothing-mounted sensors, IMUdrape improves on existing virtual-data approaches for both activity recognition and full-body pose estimation. With one real subject, its data improve recognition macro-F1 by 7% to 46% over real data alone and by 2% to 11% over body-mounted virtual data from the same motion. When the garment is simulated on recorded motion, the pose error without any real training data falls by 30% to 33% relative to generated motion, and garment data remain 12% more accurate than body data. IMUdrape thus reduces the amount of real data that garment-mounted sensing requires.

cs.CV · cs.HC

新论文 · v1arXiv:2611.02392

A Sharp Mutual Information Bound for Binary Pairs

Qianmian Guo

原文摘要

We prove a sharp upper bound on the mutual information between two binary random variables in terms of their distribution-dependent KL contraction coefficient. This resolves the binary-pair conjecture of Anantharam, Gohari, Kamath, and Nair. Equality holds if and only if the variables are independent or form a doubly symmetric binary source. The proof uses supporting tangents of an entropy curve to vary the input distribution and the channel while preserving the contraction coefficient. Together with tensorization and data processing, the result also bounds the mutual information between binary outputs obtained separately from two correlated observation sequences. When the observation pairs are independent copies of a finite-alphabet pair, this bound depends only on the law of one pair and not on the number of observations.

cs.IT

新论文 · v1arXiv:2611.02391

Late Autumn: LLM Agents Specialize a General Multi-Robot Planner for One Warehouse

Yimin Tang, Han Zhang, Shao-Hung Chan, Erdem Bıyık, Sven Koenig, Jingkai Chen

原文摘要

No algorithm is best on all problems, but a real warehouse is a narrow problem: its layout and processes rarely change. Operators still run one general multi-robot planner at many sites, because experts cannot tune it for each one. In this work, which we call Late Autumn, we explore whether LLM coding agents running autonomous research can specialize a general planner for one site, trading generality for throughput, much as post-training adapts a pretrained LLM to one task. We study six campaigns on a lifelong planner that combines task assignment with multi-agent path finding, on a floor modeled on an existing automated warehouse. We find that (1) the agents raise throughput by 22--60%, and the gains hold on unseen seeds; (2) they rediscover known MAPF mechanisms, such as corridor-exit priorities, local guidance, and rollouts, and independent campaigns find the same bottleneck; (3) the gains largely carry over to another layout, a larger fleet, and other service times, shrink with a smaller fleet, and mostly vanish under an outbound-heavy demand mix; and (4) each final patch (0.7k--2.4k lines) is a chain of scored commits with a median step of 27 lines, so experts can review it, and review finds problems that the score misses; some patches multiply planner compute by over 100x. LLM agents can therefore turn each site's bias into extra throughput at little engineering cost, with reviewable patches; we expect experts to shift toward designing insightful metrics and fast simulators that mirror the real problem.

cs.RO · cs.AI