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
+63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 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 15:53 — 2026-11-16 15:53(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 13:44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6,921 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:2611.14592

Multi-Step Underwater Acoustic Channel Prediction via Dual-Domain Structure Preservation and Pretrained Transformer

Mingjie Cao, Gewei Zhang, Deqing Wang, Lizhao You, Fei-Yun Wu, Liqun Fu

原文摘要

Accurate future channel state information (CSI) is essential for underwater acoustic (UWA) communication because delays associated with signal propagation, feedback, scheduling, and transceiver reconfiguration can render currently available CSI outdated. However, most existing predictors estimate only the next channel state and obtain multi-step forecasts through recursive rollout, which causes prediction errors to accumulate as the multipath structure evolves. The scarcity of sea-trial measurements further limits reliable model training. To address these challenges, we propose LLM4UACP, a dual-domain, structure-preserving framework that adapts a pretrained Transformer for few-shot multi-step UWA channel prediction. LLM4UACP extracts complementary features from the channel impulse response (CIR) and channel frequency response (CFR), aligns them through Fourier-consistent fusion, and encodes the fused representation as delay-time tokens. A pretrained Transformer with a frozen backbone is adapted through Butterfly Orthogonal Fine-tuning to jointly predict multiple future CIRs in a single forward pass, thereby avoiding the error accumulation associated with recursive prediction. Experiments on the measured SO-06 and SO-07 channels show that LLM4UACP achieves normalized mean squared error (NMSE) values of 0.0411 and 0.0399, corresponding to reductions of 88.53% and 85.15%, respectively, relative to the most recent baseline. With only 0.11M trainable parameters, LLM4UACP maintains robust performance across varying prediction horizons and observation-window lengths, limited-data settings, and cross-dataset transfer scenarios.

cs.SD · cs.AI · cs.LG · eess.SP

版本更新 · v2arXiv:2610.36298

Are Spiking Neural Networks Harder to Steal? The Role of Stochastic Encoding in Model Extraction

Ayana Moshruba, Maryam Parsa

原文摘要

Machine learning models deployed on edge devices are vulnerable to model stealing attacks, in which an adversary replicates a model using only its predictions. Existing defenses add mechanisms that are costly on resource-constrained hardware. Spiking neural networks (SNNs) offer energy-efficient inference at the edge and have been shown to leak less information about their training data than artificial neural networks (ANNs). This work investigates whether SNNs also resist model stealing and identifies the source of any such resistance. We evaluate four model stealing attacks against SNN and ANN models on three image datasets and introduce a metric that accounts for the stochastic outputs of SNNs. SNNs exhibit greater resistance than ANNs: on average, surrogate models extracted from SNNs agree with their targets 38% less often outside the training distribution, and targeted adversarial examples crafted on these surrogates transfer 54% less often. This resistance, however, arises mainly from the randomness of their input encoding rather than from their spiking computation, and an adversary who repeats each query can largely overcome it. SNNs therefore protect against model stealing without additional defense mechanisms, but this protection does not withstand adaptive adversaries.

cs.AI

新论文 · v1arXiv:2611.13732

CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation

Choo Sin Wai, Dake Zhong, Jingye Zhang, Zhifang Liu, Siyao Xiao, Zirong Ding, Yuhong Zhang, Kangjie Chen 等 13 位作者

原文摘要

Robot demonstrations contain reusable manipulation knowledge, but transferring this knowledge across embodiments requires representations that bridge differences in control interfaces. Action reconstruction alone does not ensure that similar behaviors across robots share a representation. To address this gap, we introduce CIALLO, an action codec that aligns actions, visual changes, and observation-grounded language in a shared space of short-horizon behavioral intent. An embodiment-conditioned decoder maps this intent back to robot-specific actions, allowing a shared representation to support different control interfaces. After pretraining on eight embodiments, CIALLO adapts to a new robot from one recording of at most 10 seconds by updating only its embodiment embeddings. The calibrated codec then remains frozen while a policy learns to predict intent from observations and instructions. We instantiate this policy with Qwen3.5-4B to form Qwen-CIALLO, whose backbone requires no large-scale robot-action pretraining before policy finetuning. With 20 demonstrations per task, Qwen-CIALLO achieves 76.7\% average success across real SO-101 and single-arm Piper robots, compared with 70.0\% for fully finetuned $π_0$. In simulation, we additionally finetune the action decoder, achieving 97.3\% success on LIBERO and 52.7\% on RoboTwin 2.0. The LIBERO policy also achieves 80.8\% on LIBERO-Plus without further finetuning. Together, these results support a shared action codec as a transferable control interface that separates embodiment calibration from task learning.

cs.RO

版本更新 · v3arXiv:2511.06365

Transfer the Style, Not the Semantics: Mitigating Semantic Leakage in Image-Guided Stylization

Haojun Tang, Qiwei Lin, Tongda Xu, Wenda Zhao, Yian Zhao, Yu Zhang, Lida Huang, Yan Wang

原文摘要

Image-guided zero-shot style transfer enables training-free stylization of arbitrary content images using a reference style. Despite recent progress, existing methods commonly rely on self-attention manipulation to inject style information, which may transfer semantic content from the style image, leading to semantic leakage. In this work, we revisit this phenomenon from the perspective of key--value coupling in the self-attention of diffusion models. Our analysis shows that the native correspondence between style keys and values plays an important role in transferring semantic information from the style image. Motivated by this observation, we propose SuRe, a timestep-aware key--value regulation framework that mitigates semantic leakage by disrupting the native key--value correspondence while progressively restoring it for faithful style transfer. Specifically, we present value shuffle to decouple style keys and values while preserving the empirical distribution of the values, together with a progressive recoupling mechanism that gradually recouples them throughout the stylization process. Experiments against 18 representative methods demonstrate that SuRe maintains competitive style similarity while consistently improving content similarity across SD1.5, SDXL, SD3, and FLUX.1-dev, with natural generalization to multi-style transfer. The code will be publicly available at https://xinr-tang.github.io/SuRe-homepage/.

cs.CV

新论文 · v1arXiv:2611.13730

Deterministic, Reproducible Inference in Exact Integer Arithmetic, and Verifiable Distributed Inference as Its Consequence

Sayed Amir Karim

原文摘要

Optimized floating-point inference is not reproducible across environments: the same model on different hardware, compilers or thread counts can produce different bits. We present tritify, an open-source runtime that executes the forward pass of real models -- decoder-only language models, Mixture-of-Experts decoders, and the Segment Anything 2.1 image/video stack -- with the entire run-time path in exact integer arithmetic; floating point is confined to offline quantization and the float reference used for verification. We make three separate claims and verify each. (1) Cross-hardware reproducibility: the integer path produces bit-identical output run to run, across CPU instruction-set architectures, and across CPU/GPU, carried by a reproducing SHA-256 of the output. (2) Decision fidelity: the integer path reproduces the float reference's decision on the models and inputs tested, with the numeric exceptions measured; per-layer fidelity through sixteen layers of OLMoE-1B-7B and of a 106-billion-parameter MoE shows no fidelity cliff. (3) Location independence: a model's computation can be split across instruction sets, CPU and GPU, and networked machines with zero effect on the output bits. GLM-4.5-Air (106,852,251,264 parameters, 427 GB of integer codes) generated its answer across three machines, none of which can hold its integer codes in RAM, bit-identically to a single-host reference. The consequence is verifiable distributed inference: an untrusted server or a fleet of devices runs the model while an open scalar oracle re-derives the exact bytes; a guarantee against a dishonest server is future work. We do not claim a per-device speed-up, bit-equality of floating-valued intermediates, or confidentiality. Code: https://github.com/pelloran-inc/tritify

cs.LG · cs.DC · cs.SE

版本更新 · v3arXiv:2606.06145

Sliding-Window Quotas in Apache Hadoop YARN: Exact Admission and Flexible Placement

Ruize Zhao

原文摘要

A reservation in Apache Hadoop YARN can pass a quota of 600 MiB-hours even when a 24-hour window contains 720 MiB-hours of usage. YARN subtracts sampled prefixes to estimate the window total. This can also reject requests that fit, and adding demand can introduce a sample that reverses a rejection. We bound the peak error in both directions and implement an exact check that visits rate changes at either edge of the window. When the two policies see the same history in replays from two public job traces, they disagree on up to $13.3\%$ of requests. Among requests both policies admit, the 95th-percentile latency of inserting a reservation into the plan is $39$--$47\%$ of the sampled baseline. A separate linear scan finds all feasible integer starts for a single constant-demand stage. In a ResourceManager test, the default agent rejects a flexible request. The ResourceManager accepts the stage when submitted at a start found by the scan. In one replay, committing such retries reduces total admissions.

cs.DS

版本更新 · v3arXiv:2605.05980

TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering

Yuan Sui, Yulin Chen, Yibo Li, Xue Jiang, Yufei He, Yihong Dong, Xiaoxin He, Tianyu Gao 等 9 位作者

原文摘要

When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as *agent drift*. We focus on two recurring failure modes *overthinking* and *overacting*, i.e., where the agent repeatedly reasons over information it already has, and where it issues tool calls without integrating recent observations or acquiring new evidence. In this paper, we introduce TACT (Think-Act Calibration via activation Steering), to detect and mitigate agent drift in the residual stream before it surfaces as a behavioral failure. In specific, we label trajectory steps as overthinking, overacting, or calibrated, and find that their hidden states can separate linearly along two *drift axes*, pointing from calibrated behavior toward each failure mode (AUC $\approx$ 0.9). To mitigate agent drift, we project each step's activation onto these axes at test time and pull drifted ones back toward the calibrated region. Experiments show that TACT outperforms unsteered baselines across SWE-bench Verified, Terminal-Bench 2.0, and CLAW-Eval, lifting average resolve rate by $+5.8$ pp on Qwen3.5-27B and $+4.8$ pp on Gemma-4-26B-A4B-it while cutting steps-to-resolve by up to $26\%$. These gains frame agent drift as a steerable direction in the residual stream, and position TACT as a viable handle for reliable long-horizon agents.

cs.AI

新论文 · v1arXiv:2611.13726

Weighted-AoI-Driven UAV Trajectory and Reporting for Dynamic CKM Tracking

Zeyu Zhao, Yueling Che, Sheng Luo

原文摘要

Existing channel knowledge map (CKM) construction assumes quasi-static environments, failing when channels rapidly decorrelate. This paper investigates continuous online dynamic CKM tracking over an airborne 2D plane via a UAV fleet. We formulate a long-term error minimization problem under UAV mobility and reporting constraints. This problem, however, is intractable with unobservable errors for unmeasured cells. To tackle this, we propose a metric-driven scheduling approach featuring the Weighted-Age of Information (W-AoI). W-AoI evaluates cells by combining exact temporal staleness with spatial uncertainty predicted by a 2D U-Net. We prove that top-$K$ W-AoI selection maximizes the one-slot error reduction bound. Guided by this guarantee, we develop a lightweight greedy trajectory policy incorporating continuous along-path sensing. Simulations demonstrate our method reduces steady-state error by 3.8 dB$^2$ and 4.8 dB$^2$ over AoI-only and FIFO baselines, closely approaching an idealized oracle.

cs.LG

版本更新 · v2arXiv:2605.01340

Terrain Perception for Agricultural UAVs in Complex Farmland via Rotating mmWave Radar

Zhihao Zhan, Le Tao, Shaobin Li, Chenxin Fang, Xingrui Yang, Liang Li, Rui Fan, Yuhang Ming

原文摘要

Accurate terrain perception is essential for terrain-following flight of agricultural uncrewed aerial vehicles (UAVs), yet remains challenging in real-world farmland due to occlusions, complex terrain geometry, and environmental disturbances. Millimeter-wave (mmWave) radar is a promising sensing modality for this task due to its robustness to adverse conditions; however, existing UAV-mounted radar systems rely on fixed field of view (FoV) and terrain extraction methods designed for dense light detection and ranging (LiDAR) data, leading to incomplete and unreliable terrain estimation. To address these limitations, we present a low-cost rotating mmWave radar-enabled terrain perception framework for agricultural UAVs operating in complex farmland environments. Specifically, a mechanically rotating sensing design is introduced to enlarge spatial coverage and improve terrain observability beyond the limitations of fixed-view radar under dynamic low-altitude flight. Building upon this sensing capability, we further design a pose-consistent terrain reconstruction pipeline tailored for sparse, noisy, and partially observable radar data, enabling reliable ground extraction and continuous terrain surface estimation in challenging agricultural scenarios. The complete system is deployed on a real agricultural UAV platform and evaluated through extensive field experiments. Experimental results demonstrate improved terrain coverage and estimation accuracy, achieving an F1 score of 94.42% for ground segmentation, while the closest rival only achieves 90.48%.

cs.RO · eess.SP

版本更新 · v3arXiv:2503.00868

Physics-Driven Extraction of Dynamic Fluid Asset from Monocular Video with Generative 3DGS

Zhiwei Zhao, Yin Zhao, Minchen Li, Yixin Hu

原文摘要

Existing methods for dynamic 3D scene synthesis from video rely on per-frame deformation fields optimized through pixel-level reconstruction losses. While effective for closed systems such as elastic solids, these approaches face challenges with open systems like fluids where material continuously enters and exits the scene, topology changes freely, and no stable point correspondence exists across frames. We propose a simulation-driven alternative that optimizes the parameters of a fluid simulator to reproduce dynamics observed in a single-view video, rather than fitting per-point deformation to pixel values. Our framework leverages generative 3D Gaussian Splatting (3DGS) models to obtain initial fluid geometry including unseen surfaces, estimates a physically grounded velocity field from surface motions with a physics-constraint correction algorithm, and converts it into a divergence-free, grid-based representation. A differentiable Affine Particle-In-Cell (APIC) simulation then optimizes effective simulation parameters, such as viscosity, boundary conditions, and inflow/outflow velocities, to match the observed dynamics. Because the dynamics are governed by forward simulation, the output assets are inherently editable, interactive, and temporally extendable, which reconstruction-based approaches cannot readily provide. Stage-wise ablations confirm that each stage is necessary, and hyperparameter sweeps show the pipeline to be robust without sensitive per-scene tuning. Our method handles various liquid fluids, including inviscid and viscous types, demonstrating the potential for automatically creating simulation-ready 3D fluid assets from readily available internet videos.

cs.GR

版本更新 · v2arXiv:2604.14560

DVFace: Spatio-Temporal Dual-Prior Diffusion for Video Face Restoration

Zheng Chen, Bowen Chai, Rongjun Gao, Mingtao Nie, Xi Li, Bingnan Duan, Jianping Fang, Xiaohong Liu 等 10 位作者

原文摘要

Video face restoration aims to enhance degraded face videos into high-quality results with realistic facial details, stable identity, and temporal coherence. Recent diffusion-based methods have brought strong generative priors to restoration and enabled more realistic detail synthesis. However, existing approaches for face videos still rely heavily on generic diffusion priors and multi-step sampling, which limit both facial adaptation and inference efficiency. These limitations motivate the use of one-step diffusion for video face restoration, yet achieving faithful facial recovery alongside temporally stable outputs remains challenging. In this paper, we propose, DVFace, a one-step diffusion framework for real-world video face restoration. Specifically, we introduce a spatio-temporal dual-codebook design to extract complementary spatial and temporal facial priors from degraded videos. We further propose an asymmetric spatio-temporal fusion module to inject these priors into the diffusion backbone according to their distinct roles. Evaluation on various benchmarks shows that DVFace delivers superior restoration quality, temporal consistency, and identity preservation compared to recent methods. Code: https://github.com/zhengchen1999/DVFace.

cs.CV

版本更新 · v2arXiv:2611.11588

FinCutBench: A Continually Updated Benchmark for Measuring the Temporal Boundaries of LLM Financial Knowledge

Siyuan Li, Ke Wan, Boyong Hou, Yujie Deng, Zixuan Yuan

原文摘要

In financial backtesting and other point-in-time tasks, external inputs can be restricted by date, but model parameters may retain financial facts disclosed later, introducing parametric look-ahead bias. We introduce FinCutBench, a continually updated monthly financial knowledge benchmark for measuring how far a fixed model's financial knowledge extends over calendar time. The current dataset contains 9,000 Chinese and English four-option multiple-choice questions from January 2023 to September 2026, covering Chinese and U.S. markets and four categories of financial information. We construct monthly knowledge profiles using the approximate months in which the tested facts became public. After a profile passes the decline test and knot checks, we define the FinCut Boundary as the first month when the fitted profile reaches its lower level, and report the stability of the estimated date under resampling. Boundary dates and localization precision vary across models. Using the independently measured Transition Start and Boundary as fixed references for downstream sample grouping, we find significant relative declines in U.S. asset-ranking performance and in earnings recall for Sol and Luna. Downstream effects vary across markets and tasks. The FinCut Boundary thus provides an empirical reference for the temporal scope of parametric knowledge in point-in-time financial evaluation, supporting evaluation-window selection and result interpretation.

cs.AI · cs.CL

版本更新 · v3arXiv:2602.08866

ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS

Bang Xie, Senjian Zhang, Zhiyuan Peng, Wei Chen, Xin Yin, Chenhao Ying, Yuan Luo

原文摘要

Large language models have transformed code generation, enabling unprecedented automation in software development. As mobile ecosystems evolve, HarmonyOS has emerged as a critical platform requiring robust development tools. Software development for the HarmonyOS ecosystem relies heavily on ArkTS, a statically typed extension of TypeScript. Despite its growing importance, the ecosystem lacks robust tools for automated code repair, primarily due to the absence of a high-quality benchmark for evaluation. To address this gap, we present ArkEval, a unified framework for ArkTS automated repair workflow evaluation and benchmark construction. It provides the first comprehensive benchmark specifically designed for ArkTS automated program repair. We constructed this benchmark by mining issues from a large-scale official Huawei repository containing over 400 independent ArkTS applications. Through a rigorous multi-stage filtering process, we curated 502 reproducible issues. To ensure testability, we employed a novel LLM-based test generation and voting mechanism involving Claude and other models. Furthermore, we standardized problem statements to facilitate fair evaluation. Finally, we evaluated four state-of-the-art Large Language Models (LLMs) on our benchmark using a retrieval-augmented repair workflow. Our results highlight the current capabilities and limitations of LLMs in repairing ArkTS code, paving the way for future research in this low-resource language domain.

cs.SE

新论文 · v1arXiv:2611.13714

TRUER: Test-Time Reward Correction Using an Error-Aware Rectifier for Reinforcement Learning

Mingxiang Shen, Jinhao Li, Jiaming Xu, Yibo Han, Guohao Dai, Yijia Zhang, Ningyi Xu

原文摘要

Test-time reinforcement learning enables language models to adapt using rewards derived from their own answers. However, majority voting can reinforce incorrect solutions even when correct alternatives are available. Our training audit shows that false positives (incorrect responses receiving positive rewards) dominate reward errors. We focus on a practical regime where ground-truth rewards are difficult to obtain at scale, while a limited labeled source set is available. We introduce TRUER, a framework that uses limited supervision to train a reward rectifier that distinguishes correctness from consensus. To achieve this goal, we train the rectifier with an emphasis on incorrect majorities and correct minorities, targeting cases where consensus and correctness disagree. After that, we freeze the rectifier and use it to correct rewards during subsequent test-time adaptation. By improving reward accuracy and thereby model performance, TRUER consistently outperforms naive TTRL in both metrics across all evaluated configurations.

cs.LG

版本更新 · v3arXiv:2605.00496

Effect of Temporal Resolution on Zero-Shot Semantic Understanding of Rapid Human Actions

Yongpeng Cao, Yuji Yamakawa

原文摘要

Understanding human actions from visual observations is essential for human-robot interaction, particularly when semantic interpretation of unfamiliar or hard-to-annotate actions is required. For rapid or less common activities, collecting sufficient labeled data for supervised learning is challenging, making zero-shot approaches a practical alternative for semantic understanding without task-specific training. While recent advances in large-scale pre-trained models enable such zero-shot reasoning, the impact of temporal resolution, especially for rapid and fine-grained motions, remains underexplored. In this study, we investigate temporal-resolution conditions for zero-shot semantic understanding of high-speed human actions. Using kendo as a representative case of rapid and subtle motion patterns, we propose a training-free pipeline that combines a pre-trained video-language model for semantic representation with large language model-based reasoning for pairwise action comparison. Our primary experiment evaluates full-observation raw videos from 10 to 120 Hz in 10-Hz increments. Nearest class prototype (NCP) accuracy is highest at 120 Hz, and the mean over 70-120 Hz is higher than that over 10-60 Hz. The corresponding mean prototype margin changes from -5.74 to +2.52 similarity-score points between these two halves and is also highest at 120 Hz. Secondary experiments show that tracking overlays reduce mean full-observation performance but improve mean partial-observation performance. These findings provide preliminary evidence that retaining high-temporal-resolution visual information can benefit training-free semantic understanding of rapid human actions.

cs.CV · cs.RO

新论文 · v1arXiv:2611.13713

Toward Autonomous RTL and Synthesis Optimization: Benchmarking and Self-Improving Agents

Wenji Fang, Yao Lu, Jinghua Wang, Zhiyao Xie

原文摘要

Recent advances in large language models (LLMs) and autonomous agents are creating new opportunities for hardware design optimization. This paper examines three connected directions toward autonomous RTL and synthesis optimization: (1) Realistic benchmarking. We discuss reference-based and open-ended RTL optimization benchmarks that evaluate optimization opportunities under realistic EDA workflows. (2) Tool-grounded RTL optimization. We present Dr. RTL, a multi-agent framework that automates critical-path analysis, RTL rewriting, and implementation-level evaluation, while continuously improving through reusable optimization skills. Evaluated on 20 real-world RTL designs, Dr.~RTL achieves average WNS/TNS improvements of 21\%/17\% with a 6\% area reduction over commercial synthesis. (3) Design-specific synthesis optimization. We explore agent-driven synthesis script tuning and the discovery of executable synthesis algorithms across intermediate representations, technology-independent optimization, and technology mapping. Finally, we envision AI-native design automation that jointly explores architectural, RTL, and EDA algorithm design spaces, guided by verification constraints and implementation feedback.

cs.AI · cs.AR

新论文 · v1arXiv:2611.13712

Broad-Persistent Advising in Interactive Reinforcement Learning via Latent State Encoding

Zhuoran Liang, Francisco Cruz

原文摘要

Deep Interactive Reinforcement Learning (Deep IntRL) accelerates reinforcement learning training by incorporating external advice. However, conventional Deep IntRL uses each piece of advice only in the current step and discards it after a single interaction. Persistent Advising and Broad-Persistent Advising (BPA) extend this process by storing advice in persistent memory and reusing it in similar states through state generalisation based on K-means clustering. This research proposes Encoder BPA, which employs a latent encoder to retrieve and reuse advice. In this framework, a trained encoder is used to map a state sequence into a latent representation at every time step. Advice can be retrieved through latent comparison, together with a top-(k) aggregation and a consistency condition to improve reuse stability. Experimental results show that Encoder BPA improves learning efficiency and advice utilisation at an early stage of training compared with different Deep IntRL approaches, especially in complex and partially observable environments.

cs.AI

版本更新 · v3arXiv:2402.04251

Linear-time Minimum Bayes Risk Decoding with Reference Aggregation

Jannis Vamvas, Rico Sennrich

原文摘要

Minimum Bayes Risk (MBR) decoding is a text generation technique that has been shown to improve the quality of machine translations, but is expensive, even if a sampling-based approximation is used. Besides requiring a large number of sampled sequences, it requires the pairwise calculation of a utility metric, which has quadratic complexity. In this paper, we propose to approximate pairwise metric scores with scores calculated against aggregated reference representations. This changes the complexity of utility estimation from $O(n^2)$ to $O(n)$, while empirically preserving most of the quality gains of MBR decoding. We release our source code at https://github.com/ZurichNLP/mbr

cs.CL

新论文 · v1arXiv:2611.13709

Do They Do as They Are Told? Investigating Coding Agents' Adherence to Explicit Instructions in Context Files

Gianmario Voria, Yutaro Kashiwa, Gemma Catolino, Fabio Palomba

原文摘要

Developers increasingly rely on agent context files (ACFs), persistent, project-scoped artifacts such as AGENTS.md, to steer the behavior of autonomous coding agents without renegotiating expectations at every interaction. Yet this governance mechanism rests on an untested assumption: that instructions written into an ACF are actually carried out, rather than ignored or loosely followed. Existing studies describe what ACFs contain, but not whether individual instructions are followed, leaving open which guidance can be trusted. We address this gap through an empirical study of real-world ACF snapshots and their linked agent-generated commits: characterizing the explicit, actionable instructions ACFs encode, operationalizing them into executable measurement scripts, and using these scripts to assess instruction-level compliance. We find that most observable instructions can be operationalized and that agents follow ACF guidance more often than not, but adherence splits sharply between instructions followed consistently and those never respected, with differences across instruction categories and coding agents. This split shows where ACF guidance works and where it does not, pointing to instruction types that may need rewriting and to agents that may need enforcement beyond the ACF. These findings lay the groundwork for systematic approaches to specifying, verifying, and enforcing project-specific instructions in autonomous software development.

cs.SE

新论文 · v1arXiv:2611.13708

FedVP: Federated Learning across Heterogeneous Models by Pooling Locally Trained Verifiers

Yifan Li, Xi Chen

原文摘要

Conventional federated learning relies on the shared model backbone to aggregate client updates, limiting collaboration among institutions that deploy large language models (LLMs) from different families and at different scales. We propose Federated Verifier Pool (FEDVP), a new federated learning paradigm that enables heterogeneous clients to collaborate through shared verification rather than parameter aggregation. Each client trains a verifier using local data and responses generated by its chosen LLM backbone. The server pools these independently trained verifiers and combines their judgments to select answers without merging model parameters. This allows both LLM backbones and verifiers to differ in architecture and size, while keeping the LLM backbones frozen and deriving collaborative gains from improved answer selection. We evaluate FEDVP across five public medical question-answering datasets treated as federated clients, using Qwen and LLaMA backbones ranging from 3B to 14B parameters. FEDVP consistently improves performance across all five clients and outperforms the strongest conventional federated baselines by 1.46-5.79 percentage points in mean accuracy.

cs.LG

新论文 · v1arXiv:2611.13707

Joint Activation and Weight Quantization for Learned Image Compression

Yile Tu, Heming Sun

原文摘要

Learned image compression (LIC) models achieve competitive rate-distortion performance with increasingly large networks, making network quantization important for efficient deployment. Directly quantizing LIC models remains difficult in post-training quantization (PTQ) because compression performance is highly sensitive to quantization noise. Existing methods typically focus on optimizing either the weights or the activations, resulting in substantial rate-distortion degradation. To address this limitation, we introduce a two-stage pipeline that uses SmoothQuant to balance activation and weight ranges, followed by GPTQ to adapt the transformed weights. The proposed joint search framework optimizes the balancing transformation and adapted weights under the rate-distortion objective, accounting for the coupling between the two stages. Experiments across multiple LIC architectures and activation quantization configurations show that the joint search strategy consistently reduces rate-distortion degradation after quantization.

eess.IV · cs.MM

版本更新 · v2arXiv:2605.19291

Factor Augmented High-Dimensional SGD

Shubo Li, Yuefeng Han, Xiufan Yu

原文摘要

Stochastic gradient descent (SGD) is a fundamental optimization algorithm widely used in modern machine learning. In this paper, we propose Factor-Augmented SGD (FSGD), a new optimization method that leverages latent factor representations in high-dimensional learning tasks. Unlike standard two-stage dimension reduction approaches that rely on offline representation learning and full data storage, a key novelty of FSGD is that it operates purely on streaming data, making it scalable to large-scale and high-dimensional problems. Furthermore, we establish the first theoretical framework that explicitly incorporates latent factor estimation error into the analysis of SGD, and provide moment convergence in $\ell^s$ norm under decaying step sizes and mini-batch updates. Our results provide a new foundation for employing SGD reliably and scalably in high-dimensional machine learning systems.

stat.ML · cs.LG · math.ST

版本更新 · v2arXiv:2609.24150

Acceptance-Aware Draft Model Training for Speculative Decoding

Tianhua Xia, Mugilan Ganesan, Yifei Feng, Haiyu Wang, Maximilian Egger, Sai Qian Zhang

原文摘要

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to generate multiple candidate tokens that are verified by the target model in a single forward pass. Its speedup is largely determined by the acceptance length, yet existing draft-model training methods mainly optimize cross-entropy or Kullback-Leibler (KL) divergence as proxies. These objectives encourage distribution matching but do not directly optimize acceptance length, and the acceptance mechanism also differs between greedy and sampling-based decoding. In this work, we propose acceptance-length-aware training losses that directly optimize the expected number of accepted tokens within a speculative window. For greedy verification, we derive an expected accepted length (EAL) loss that explicitly maximizes expected acceptance length. For sampling-based decoding, we introduce a window total variation (WTV) loss that optimizes the overlap between temperature-scaled draft and target distributions while accounting for sequential acceptance dependencies. Both objectives can be further combined with a group-relative reinforcement learning stage (GRPO) using simulated acceptance length as the reward. Experiments across different target and draft models, tasks, and decoding settings show that our losses consistently improve acceptance length over KL-based training. WTV provides particularly strong gains under sampling-based decoding, while EAL better matches greedy verification. These results show that directly optimizing the acceptance objective, with losses tailored to the decoding mode, is more effective than conventional distribution-matching objectives.

cs.LG

新论文 · v1arXiv:2611.13705

Agentic AI Meets Formal Verification in the Era of Agentic Hardware Development

Wenji Fang, Yuchao Wu, Jing Wang, Zhiyao Xie

原文摘要

As AI agents become increasingly capable of generating and optimizing hardware circuits, ensuring the correctness of AI-generated designs becomes more important. Meanwhile, advances in AI lower the barriers to developing and applying formal methods, creating new opportunities to automate and improve hardware verification. This invited paper presents an overview of the methodologies and applications of hardware formal methods in the AI era. First, we examine how agentic AI advances hardware formal methods across three levels: specification, proof construction, and reasoning engines. Second, we discuss how formal methods support reliable AI-driven hardware development through RTL generation, debugging, and correctness-preserving optimization. We review representative research alongside our recent contributions, highlighting key technical advances and insights from experimental results. Finally, we discuss future research opportunities toward proof-native hardware development, where formal reasoning could become an integral part of autonomous hardware design.

cs.AI · cs.AR

新论文 · v1arXiv:2611.14590

An Asynchronous Federated Learning Platform for Lung Adenocarcinoma Grading via Foundation Models and Structural Pruning

Moon-Il Joo, Md Ariful Islam Mozumder, Hee-Cheol Kim

原文摘要

Classification of lung adenocarcinoma into poorly differentiated (PD) and well-to-moderately differentiated (WMD) subtypes plays an important role in patient survival; however, consistent classification is difficult due to inter-observer variability among pathologists. Collecting data from multiple hospitals is also challenging due to patient privacy concerns. This study proposes a web-based federated learning system that shares only locally trained model weights without sharing patient data between institutions. The UNI2 foundation model and CLAM-SB were used to classify pathological whole slide images. A four-client federated learning system was constructed, and the NLST cohort was reserved exclusively for external validation. In centralized evaluation, joint training with CPTAC and TCGA outperformed single-institution training on external validation, confirming the necessity of multi-institutional data integration. FedAvg, FedProx, FedBN, and FedNova were compared as federated learning algorithms under identical experimental conditions. Test AUC ranked as FedBN, FedProx, FedNova, and FedAvg. FedNova showed the most balanced classification performance between PD and WMD. L1-norm structural pruning at 20%, 30%, and 40% sparsity was applied to reduce model transmission size. FedAvg, FedProx, and FedBN showed a tendency of decreasing Test AUC under pruning, while FedNova achieved improved Test AUC across all sparsity levels. A web-based application was developed supporting slide upload, local training, AI classification, and attention heatmap-based visualization. The combination of FedNova and 40% pruning was confirmed as a practical approach that improves communication efficiency and classification performance while protecting patient privacy.

cs.LG

版本更新 · v3arXiv:2610.05651

Distributed Hybrid Quantum-Classical Optimization for Robust AoII Minimization in Satellite-Ground Integrated Edge Networks

Mohammad Arif Hossain, Tanzimul Alam Fahim, Weiqi Liu, Nirwan Ansari

原文摘要

Edge servers acting on monitored processes need estimates that are correct, not just recent. In satellite-ground integrated networks (SGINs), handover and shadowing interrupt links long enough for the process to change state several times, motivating the age of incorrect information (AoII). We formulate VANGUARD, a robust problem that jointly sets update rates, association, and bandwidth to minimize the worst-case AoII across disruption scenarios, and we solve it with SENTINEL, a distributed hybrid quantum-classical procedure. A renewal-interval decomposition yields a closed-form cost per delivery interval for AoII. The minimax is dualized into classically updated scenario weights, so each domain solves a linear assignment encoded as a compact quadratic unconstrained binary optimization (QUBO) problem with XY-mixer-enforced one-hot constraints; domains are coordinated by the alternating direction method of multipliers (ADMM), and every schedule is certified by its exact worst-case AoII. Under Starlink passes and the 3GPP TR 38.811 channel, the certificate held in 98.7\% of epochs, and the robust one was 2 to 7\% below the nominal one at no cost in realized AoII. The compact encoding uses four to six times fewer qubits than an epigraph encoding; thirteen domains, each 8 to 38 qubits, run on IBM Heron processors and are decoded to the exact optimum.

cs.NI

新论文 · v1arXiv:2611.13704

SeqFold: Timestamp-Addressable Compressed States for User Action Sequence Backbones

Mianwei Zhou, Duo Zhang, Henry Tsai, Yuqi Zheng, Jian Li, Juexin Lin, Sujay Khandagale, Vijay Rajaram 等 10 位作者

原文摘要

Existing sequential user modeling methods mainly focus on improving the backbone encoder or learning task-specific user representations for a single prediction objective. We instead study how to export the multi-layer user states of a frozen long-history backbone as compact, timestamp-addressable representations for downstream training backfill and serving. In this setting, the user state at a given timestamp summarizes the user's actions before that time, so downstream systems need only the state aligned to each target timestamp rather than the full hidden-state timeline. To this end, we present \texttt{SeqFold}, a compressed-state interface that combines learned multi-channel fusion, channel-specific temporal decay, and Lookup-Free Quantization (LFQ) to produce compact discrete codes from frozen backbone states. Task-specific decoders then map these shared codes into flexible embedding spaces for downstream models. To make timestamp-addressable export practical at scale, we further develop a fused streaming implementation that updates the fusion recurrence after every action while materializing states only at target timestamps. On large-scale proprietary datasets, SeqFold reduces per-state representation storage by $3{,}400\times$ while preserving most of the downstream ranking performance of the uncompressed model, showing that SeqFold is an effective interface for reusing long-history sequence backbones in downstream models.

cs.AI · cs.SI

版本更新 · v2arXiv:2611.10602

Agentic discrete-event simulation for manufacturing system design: an open 3D simulator, a benchmark and an industrial case

Javier Pernas-Álvarez, Diego Crespo-Pereira

原文摘要

The design of manufacturing systems relies on discrete-event simulation (DES) models that experts still build in tool-specific interfaces. AI agents can now write simulation code, but every model they write from scratch is new, unverified software. We present SimuLean, an open-source 3D DES simulator on the Unity engine designed to be programmed by AI agents: its modelling semantics are verified once, in the platform, and the agent builds and studies one model through domain-level commands, in the 3D scene or headless; physically simulated durations are calibrated for fast headless studies. We evaluated it on 18 manufacturing modelling tasks, from single machines to published production lines. A frontier agent built valid models in 93 of 108 attempts (86%), in about two minutes each; on the benchmark's interface version, two frontier agents built 105 of 108 models through domain commands alone, so that each comes with a record of how it was built. Every residual failure was silent - a model that builds and runs but answers wrongly - and only comparison with reference models revealed them all. In an industrial case, one agent working alone rebuilt, verified and studied a robotised welding workshop from a published study, in SimuLean and in SimPy. Comparing them with the published, expert-built model exposed an error in it; against the corrected model, the agent-built models agree within 1%. One agent can already build complete, realistic and traceable models for the design of manufacturing systems; independent reference models are what make them trustworthy.

cs.AI

版本更新 · v3arXiv:2604.15319

Explainable Iterative Data Visualization Refinement via an LLM Agent

Burak Susam, Tingting Mu

原文摘要

Exploratory analysis of high-dimensional data relies on embedding the data into a low-dimensional space, based on which a visualization plot is produced to uncover meaningful structures and to communicate geometric and distributional data characteristics. Finding a suitable embedding algorithm configuration, particularly the hyperparameter setting, to produce a visualization plot that faithfully represents the underlying reality and encourages pattern discovery is labor-intensive and requires domain knowledge. To ease this burden, we propose an agentic AI pipeline that integrates rigorous quantitative assessment with large language model (LLM) based approximation of qualitative human judgment and insight. By treating visualization evaluation and hyperparameter optimization as a semantic task, our system generates a multi-faceted report that contextualizes quantitative metrics with descriptive summaries, and suggests actionable recommendations of algorithm configuration for refining data visualization. Through an iterative refinement loop, the system rapidly produces a high-quality visualization plot in full automation.

cs.HC · cs.AI

版本更新 · v3arXiv:2607.00033

Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration

Xinghao Zhu, Zixi Liu, Shalin Jain, Chenran Li, Milad Noori, Michael Andres Lin, Huihua Zhao, John Welsh 等 21 位作者

原文摘要

Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging. We present Contact Wrench Guidance from Human Demonstration in Robotic Dexterous Manipulation (CHORD), a framework for long-horizon manipulation of rigid and articulated objects with reinforcement learning. The key idea is object-centric contact wrench space guidance: we represent human and robot motions by the forces and torques they can induce on the object, enabling similarity to be measured by the induced instantaneous motions. This guidance makes reinforcement learning more scalable for contact-rich dexterous manipulation. We further introduce a large-scale simulation benchmark with 4,739 bimanual dexterous manipulation tasks, constructed from motion-capture datasets and reconstructed in-house videos. Evaluated on 1,831 benchmark tasks, CHORD achieves an average success rate of 82.12%, demonstrating strong scalability. CHORD also generalizes to whole-body manipulation from hand-only and third-person demonstrations, achieving a 90.77% success rate, and the learned policies transfer to the real world in both open-loop and closed-loop settings.

cs.RO · cs.AI · cs.CV