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 20:01 — 2026-11-16 20:01(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:2611.12310

The Optimal Rate Constant of Heavy-Ball Momentum on Smooth Strongly Convex Functions

Marcos Hernanz

原文摘要

The heavy-ball method with a constant step size and a constant momentum parameter accelerates gradient descent on quadratics, but no choice of the two parameters does so on the class of smooth strongly convex functions. We determine how much faster than gradient descent it can be made on this class. Writing the best worst-case rate over all tunings as $1-c(κ)/κ$, where $κ$ is the condition number, we prove that $c(κ)$ tends to $8$ in every dimension of two or more. The lower bound on the rate holds for every tuning, because a tuning that is faster than $1-8/κ$ on quadratics follows a slowly decaying spiral on some function of two variables. The matching upper bound comes from an explicit tuning, with nearly the momentum of Polyak's tuning and a step size about $\sqrtκ/8$ times smaller, and from a Lyapunov function whose positivity is verified in exact arithmetic. Optimally tuned heavy-ball is therefore asymptotically four times faster than gradient descent on this class.

cs.LG · math.OC

版本更新 · v2arXiv:2608.30795

Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions

Rodrigo Almeida, Noelia Otero, Jost Arndt, Simon Baur, Wojciech Samek, Jackie Ma

原文摘要

End-to-end weather forecasting systems produce skillful global gridded and station forecasts directly from raw Earth observations, replacing the numerical weather prediction pipeline, including data assimilation, at a fraction of its cost. These systems are deterministic and issue no uncertainty. Here we render the Aardvark Weather model probabilistic by attaching one stochastic mechanism to each component: learned, input-dependent noise at the observation encoder, aimed at the uncertainty inherited from the observing system, and Monte Carlo dropout in the processor, aimed at the uncertainty of the learned dynamics. The resulting nested ensemble attributes forecast spread to the two sources through a law-of-total-variance decomposition, cross-checked by withholding observation streams. Probabilistic finetuning significantly improves the mean forecast, by 11% on average across variables and lead times. The ensemble is close to calibrated against ERA5 through the medium range, is at least as accurate as the deterministic model at weather stations while beating it in relative economic value at every lead time, and remains considerably behind the operational ECMWF IFS ensemble. The encoder branch behaves as observation-driven uncertainty. Component-attributed uncertainty makes end-to-end forecasts more transparent, a step toward observation-driven digital twins of the atmosphere.

physics.ao-ph · cs.LG

版本更新 · v2arXiv:2511.10749

Effective Resistance in Simplicial Complexes: Generalizations and Properties

Inés García-Redondo, Claudia Landi, Sarah Percival, Anda Skeja, Bei Wang, Ling Zhou

原文摘要

Originally introduced in circuit theory, the notion of effective resistance has been fruitfully exploited in graph theory, where each edge in a graph is understood as a resistor in an electric network. In this context, the effective resistance between two vertices quantifies the total opposition to current flow when a unit current is injected at one vertex and extracted at the other. As such, it encodes rich structural and geometric information about the underlying graph: it satisfies a minimum-energy principle termed Thomson's principle, defines a metric on the vertex set, relates to the topology of the graph through Foster's theorem, and determines the probability of appearance of an edge in a random spanning tree. Generalizations of effective resistance to simplicial complexes have been proposed in several forms, often formulated as matrix products of standard operators associated with the complex. We introduce a novel, basis-independent bilinear form, derived from an algebraic reinterpretation of circuit theory, that extends the classical effective resistance from graphs to simplicial complexes. This bilinear form acts on chains and cochains, and in particular, simplices and cosimplices in a simplicial complex. Our framework subsumes and unifies all existing matrix-based formulations of effective resistance. Moreover, we establish higher-order analogues of several fundamental properties known in the graph case: (i) we extend Thomson's principle to our basis-free framework; (ii) we establish metric properties for the effective resistance and its square root on chains and cycles, recovering the classical graph case; (iii) we provide a generalization of Foster's theorem to simplicial complexes; and (iv) we prove a matrix-tree theorem for higher-dimensional spanning trees, linking effective resistance to the probability of appearance of a simplex in random simplicial spanning trees.

math.CO · cs.CG · cs.DM · math.AT

版本更新 · v3arXiv:2605.26358

Deep Learning-based Algebraic Reynolds Stress Closures for RANS Simulations of Turbulent Flows

Daniel Dehtyriov, Jonathan F. MacArt, Justin Sirignano

原文摘要

Turbulence is ubiquitous in engineering and science, yet direct simulation is prohibitively expensive. The Reynolds-averaged Navier-Stokes (RANS) equations provide savings exceeding ten orders of magnitude but introduce unclosed terms. Offline-trained machine-learning (ML) closures suffer distribution shift in predictive simulations, while ML methods that bypass the governing equations struggle to generalise from scarce high-fidelity data. We develop a physics-derived deep learning closure for RANS, the Deep Algebraic Reynolds Stress Model (DARSM), which can be trained on one or two flow cases and accurately generalise across an order of magnitude in Reynolds number, to unseen geometries, and across flow regimes. A neural network maps flow invariants to empirical parameters in an implicit algebraic Reynolds stress equation, derived from the Reynolds stress transport equations under the weak-equilibrium assumption, imposing physics-based structure on the ML closure. End-to-end optimisation through the governing PDEs eliminates distribution shift, but both unrolled and implicit automatic differentiation fail on the stiff coupled solver. We derive adjoint equations that exploit the solver's implicit-explicit structure for efficient optimisation. On canonical square-duct and periodic-hill benchmarks, DARSM reduces average test velocity error over baseline RANS by 2-4x across Reynolds number, geometries, and flow regimes, with peak case-level reductions of 12x. The model trained on attached, anisotropy-dominated flows (square duct) accurately generalises without retraining to separated flows (periodic hills), a regime change in the underlying physics. DARSM also outperforms established ML methods: offline training, tensor-basis neural networks, field-inversion machine learning, DeepONets, physics-informed neural networks, and an adjoint-trained source-term closure.

physics.flu-dyn · cs.LG

新论文 · v1arXiv:2611.12307

PACE-ECG: Patient-Aware Contrastive ECG Pretraining; Leveraging Longitudinal Structure for Transferable Representations

Riccardo Cavarra, Lupo Lovatelli, Shaheim Ogbomo-Harmitt, Jakub Grzelak, Adelaide De Vecchi, Andrew King, Oleg Aslanidi

原文摘要

Foundation models for physiological signals are commonly evaluated on in-domain interpretation tasks, but their ability to transfer to longitudinal clinical prognosis across healthcare systems remains uncertain. We developed PACE-ECG, an ECG pretraining framework that combines contrastive learning across temporally neighbouring recordings from the same patient with clinically guided multitask supervision. We evaluated frozen ECG representations for post-myocardial-infarction all-cause mortality and incident heart failure prediction across MIMIC-IV and two external HEEDB cohorts, comparing the proposed representation with DeepECG-SSL, a state-of-the-art model, and two control baselines. Across both downstream tasks, the proposed model outperformed DeepECG-SSL in-domain (AUROC +1.9% for mortality and +4.0% for heart failure) and on external populations in HEEDB-Boston (+5.6% for mortality +10.3% for heart failure) and HEEDB-Atlanta (+6.9% for mortality +11.0% for heart failure) while using an encoder 41 times smaller and a fraction of the pretraining data. A matched ablation showed that patient-temporal pairing improved external mortality and heart failure AUROC over generic self-supervision by 7.0% and 9.4% on HEEDB-Boston and 8.9% and 9.3% on HEEDB-Atlanta. These findings indicate that pretraining-objective design greatly influences downstream transfer alongside model and data scale, and that in-domain performance alone is insufficient to establish the clinical generalisability of ECG foundation representations.

cs.AI

新论文 · v1arXiv:2611.12306

ExoStack: A Modular and Reconfigurable Software Framework for Wearable Robotics Using ROS 2

Debadrata Sarkar, Upamanyu Ray, Soumen Sen, Aman Arora

原文摘要

Wearable robots depend on a software chain that links body-worn sensing to gait interpretation, assistance generation, and actuation. Personalization further requires each measured response to remain associated with the assistance parameters that generated it. This paper presents ExoStack, a modular ROS 2 framework for implementing that chain across embedded hubs and a host computer. Its Embedded Sensing and Actuation (ESA) library configures ESP32 boards as microROS sensing and actuation hubs. ExoCore supplies multi-hub synchronization, gait-event detection, profile generation, motion planning, cost evaluation, and human-in-the-loop (HIL) optimization as configuration-instantiated nodes. The PASE desktop application edits configurations, launches the processing stages, and visualizes ROS 2 topics. Hardware drivers and algorithm plugins can be added through defined interfaces without modifying the generic processing nodes. We characterize hub and planner timing on three embedded computers and demonstrate reuse on two pneumatic exosuits.

cs.RO

版本更新 · v2arXiv:2601.06666

InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs

Yuzhuo Bai, Shuzheng Si, Kangyang Luo, Qingyi Wang, Wenhao Li, Gang Chen, Fanchao Qi, Maosong Sun

原文摘要

Large language models (LLMs) often hallucinate, yet most existing fact-checking methods treat factuality evaluation as a binary classification problem, offering limited interpretability and failing to capture fine-grained error types. In this paper, we introduce InFi-Check, a framework for interpretable and fine-grained fact-checking of LLM outputs. Specifically, we first propose a controlled data synthesis pipeline that generates high-quality data featuring explicit evidence, fine-grained error type labels, justifications, and corrections. Based on this, we further construct large-scale training data and a manually verified benchmark InFi-Check-FG for fine-grained fact-checking of LLM outputs. Building on these high-quality training data, we further propose InFi-Checker, which can jointly provide supporting evidence, classify fine-grained error types, and produce justifications along with corrections. Experiments show that InFi-Checker achieves state-of-the-art performance on InFi-Check-FG and strong generalization across various downstream tasks, significantly improving the utility and trustworthiness of factuality evaluation.

cs.CL · cs.AI

新论文 · v1arXiv:2611.12300

Reconfigurable Action Theories: A Formal Foundation for Dynamically Composable Agent Harnesses

Jianmin Ji

原文摘要

Action theories typically fix their vocabulary and causal laws, whereas agent harnesses can change their tools, providers, and policies during execution. We introduce Reconfigurable Action Theories (RAT), in which actions can change the action theory itself. A theory module in RAT contains a vocabulary, causal laws, and an initializer. A RAT configuration records the active modules and the world state. Module loading and unloading are represented by actions governed by ordinary causal laws. RAT retains the standard causal action semantics of its language fragment when the active module set is fixed. We give sufficient conditions for at most one next configuration, preservation of existing behavior when a module is added, and equal results when modules are loaded in either order. We establish the computational complexity of reasoning tasks in RAT and translate finite RAT systems into nonmonotonic causal theories and Answer Set Programming (ASP), preserving bounded executions. Experiments compare finite RAT models with executions of official DeepSeek Harness, Pi, and OpenHands implementations. RAT provides a formal basis for checking how component changes affect a harness's available actions, behavior, and reachable goals.

cs.AI

新论文 · v1arXiv:2611.12299

Physics-Informed Sinusoidal Representation Networks for Damage Identification in Ultrasonic Guided Wave Structural Health Monitoring

Lukas Jilke, Caspar Wasle, Norbert Hosters, Florian Raddatz, Marek Behr, Gerko Wende

原文摘要

Ultrasonic guided wave (UGW) inspection has become an effective method in structural health monitoring (SHM). While machine learning has enhanced damage detection capabilities, purely data-driven models remain constrained by extensive labeled datasets and limited physical interpretability. Standard multi-layer perceptrons (MLPs) further suffer from spectral bias (F-Principle) in high-frequency regimes, prioritizing low-frequency components while failing to resolve the high-frequency oscillations critical for UGW reconstruction. Physics-Informed Sinusoidal Representation Networks (PI-SIRENs) address these limitations by embedding governing partial differential equations directly into the training process. Building upon SIRENs, which utilize periodic activation functions to inherently capture high-frequency spectral content, the proposed framework is designed to operate effectively in sparse ultrasonic measurement regimes. This work introduces a frequency-domain PI-SIREN framework tailored for the Mindlin-Reissner plate theory to reconstruct ultrasonic wavefields without temporal discretization. The model parameters are optimized using a hybrid strategy comprising three phases: first-order Adam, residual-adaptive refinement (RAR) and quasi-Newton L-BFGS. Numerical and experimental evaluations confirm that the model serves as a physics-consistent baseline derived from sparse data, functioning as a computationally efficient surrogate for damage identification in SHM and non-destructive testing (NDT). Integrating the surrogate into a damage identification pipeline detects and localizes a milled notch from sparse experimental measurements with a localization error of 1 % of the plate diagonal. In contrast, data-driven benchmarks and MLPs with hyperbolic tangent activation functions, with and without Fourier feature embedding, are unable to identify damage due to higher reconstruction errors.

cs.CE · cs.LG

版本更新 · v2arXiv:2608.17583

Auditing Exposure to Harmful Content on TikTok using Multimodal Language Models: A Cross-National, Age-Stratified Study

Hamidreza Saffari, Francesco Pierri

原文摘要

Online video platforms can expose young users to harmful content, but independent audits remain difficult because video annotation is costly and moderation judgments vary across languages. We audit TikTok in France, Italy, and Sweden with sockpuppet accounts representing four age personas (13, 16, 19, 40), collecting 36,971 videos from passive For-You-page scrolling and active sessions that scroll, search for harm keywords, and scroll again. To scale annotation, we validate four multimodal LLMs against native-speaker labels on a 300-video reference set. Gemini 2.5 Flash with eight sampled frames plus text performs best (aggregate kappa = 0.42), at half the per-call cost of native-video upload, and we apply it to a 10% sample for approximately \$50 in total API spend across both modalities. Keyword search returns 35-56% harmful content, a 1.5-7.5x increase over the scrolling baseline in ten of twelve country-age combinations; the spike is temporary and flattens the age differences observed in France and Sweden. Under passive scrolling, Italy has the highest harm rate at every age, with Italian age-19 reaching 48.6%. Overall, MLLM-based auditing offers a scalable approach for cross-national youth-safety audits, while provider safety filters (1.1% refusal rate) under-count the most explicit harms.

cs.CL

新论文 · v1arXiv:2611.12296

RecoGEM: A Serving System for Production-Scale Generative Recommendation

Xiangrui Yang, Yunfeng Zhao, Jiawei Yang, Fangyu Zhang, Enrui Zhao, Liang Zeng, Cheng Peng, Minhui Xie 等 11 位作者

原文摘要

Generative recommendation (GR) is moving industrial recommender systems (RecSys) from scoring candidate items to autoregressively generating item identifiers. This shift promises higher recommendation quality, but makes serving substantially harder: each request executes a short sequence of dependent decoding steps that explore a large item space and select promising candidates on the latency-critical path. GR not only creates structural mismatches with conventional RecSys pipelines, but also challenges the architectural and optimization assumptions of LLM serving stacks, making direct adoption of existing systems difficult. We present RecoGEM, our production GR serving system. RecoGEM uses a runtime--engine decoupling architecture to move GR-specific serving responsibilities, such as candidate-state transitions and live artifact updates, to a dedicated runtime. Its execution engine exploits GR's short token sequences, large candidate populations, and predictable step shapes to optimize self-attention, candidate selection, and execution planning. RecoGEM has been deployed for over nine months across our production lines, serving applications with hundreds of millions of users and supporting more than ten GR model families. On our OneModel production workloads, RecoGEM reaches over 1,000 QPS per serving instance with P99 latency below 35 ms and a 2.88$\times$ throughput improvement over representative baselines.

cs.DC · cs.AI · cs.IR

新论文 · v1arXiv:2611.12295

Be My Eye: Learning to See Beyond a Robot's Own Perspective

Baifu Huang, Shilin Fang, Jianan Wang

原文摘要

Robots operating in the real world are inherently subject to partial observability, particularly in multi-robot collaboration, where individual observations may be insufficient for effective task execution. A key challenge is leveraging complementary observations from partner robots to support collaborative decision-making. We argue that information sharing should go beyond passively transmitting raw observations or generic visual features. Instead, robots should selectively encode task-relevant information according to task objectives and execution progress. To this end, we propose a task-oriented active context sharing framework that transforms robot observations into compact representations, preserving critical information under constrained communication budgets. The framework adopts a two-stage training paradigm. In the first stage, onboard observations and task instructions are jointly encoded into compact context representations. Task-oriented future prediction and soft task-progress correspondence learning guide this collaboration-agnostic compression, preserving information about task objectives and execution progress. In the second stage, the learned representations are integrated into a pretrained Vision-Language-Action (VLA) policy, enabling bidirectional context exchange. Each robot combines complementary partner information with local observations to guide action generation. Action supervision jointly refines the context representations and policy, aligning information sharing with collaborative decision-making. Controlled experiments demonstrate substantial performance gains under constrained communication budgets, while three real-world experiments validate the framework in complex dual-robot tasks. These results highlight a shift from passive visual transmission toward active, task-oriented context sharing that directly supports collaborative decision-making.

cs.RO · cs.AI

版本更新 · v2arXiv:2602.11914

When Everyone Can Submit: Designing Contests with Transparent Pre-Selection

Hanbing Liu, Ningyuan Li, Weian Li, Qi Qi, Changyuan Yu

原文摘要

Shortlisting is a common and effective method for pre-selecting participants in competitive settings. To ensure fairness, a cut-off score is typically announced, allowing only contestants who exceed it to enter the contest, while others are eliminated. In this paper, we study rank-order contests with shortlisting and cut-off score disclosure. We fully characterize the equilibrium behavior of shortlisted contestants for any given prize structure and shortlist size. We examine two objective functions: the highest individual performance and total performance. Under linear performance costs, for both objectives, the optimal contest is in a winner-take-all format. For the highest individual performance, the optimal shortlist size is exactly two contestants, but, in contrast, for total performance, the shortlist size does not affect the outcome, i.e., any size yields the same total performance. Furthermore, we compare the highest individual performance achieved with and without shortlisting, and show that the former is 4/3 of the latter.

cs.GT

新论文 · v1arXiv:2611.12293

Depth as a Candidate Source: Portfolio Allocation for Recurrent Test-Time Scaling in Large Language Models

Chaoyuan Hao, Wentao Yue, Yanyan Wu, Boyuan Gao, Tianyou Lai, Maolin Wang, Yongxin Ni, Hanwen Du 等 9 位作者

原文摘要

Recurrent latent reasoning in large lanugage models (LLMs) scales test-time computation by increasing recurrent depth, naturally framing inference as a problem of deciding when to stop. We identify a previously overlooked limitation of this single-depth view through systematic preliminary analysis: deeper recurrence can lose correct solutions found at shallower depths, while depth-specific success sets remain broadly non-nested even after controlling for marginal accuracy. This suggests that depth determines not only computation cost, but also access to distinct candidate solutions. Motivated by this finding, we propose Depth Portfolio Allocation (DPA), which reformulates recurrent test-time scaling as budgeted allocation across depth-specific candidate sources. DPA supports both fixed portfolios and feedback-guided sequential allocation under a shared inference budget. Experiments on GSM8K, SVAMP, MultiArith, and MBPP show that mixed-depth portfolios expand oracle coverage under matched candidate counts and nominal costs, while feedback-guided allocation generally matches or improves uniform allocation and can reduce computation in high-budget settings. Code and data are avaible at : https://anonymous.4open.science/r/LLM-latent-B7BC/.

cs.AI

版本更新 · v2arXiv:2611.08865

Rethinking Agent Trajectory Compression: A Workflow-Aware Perspective

Qijia Zhuang, Rui Liu, Wenqi Hu, Yuxiang Ren

原文摘要

As long-horizon agents increasingly rely on multi-step tool interactions to accomplish complex tasks, their execution trajectories continuously accumulate structured outputs and intermediate artifacts, leading to growing context overhead. Existing compression methods primarily rely on text importance or fixed truncation rules, often overlooking cross-step dependencies within workflows and potentially discarding critical information required for subsequent task execution. To address this challenge, we propose WAAC, a workflow-aware framework for agent trajectory compression. WAAC structurally models successful historical trajectories to extract reusable workflow compression experience and incorporates online backward dependency analysis to dynamically identify information retention requirements. By combining current dependency constraints with historical experience, WAAC selects appropriate compression strategies for different types of historical information. Experiments on PinchBench and Odysseys demonstrate that WAAC achieves an overall score of 87.6 and a perfect completion rate of 19.0%, respectively, while reducing execution costs by 19.7% and 29.1% compared with the strongest baseline methods. These results demonstrate the effectiveness of workflow-aware trajectory compression in improving task performance and cost efficiency for long-horizon agents. Code and resources are available at https://anonymous.4open.science/r/waac-6527/.

cs.AI

版本更新 · v2arXiv:2602.02634

A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees

Alexander Ryabchenko, Idan Attias, Daniel M. Roy

原文摘要

This paper develops a reduction-based framework for online learning with delayed feedback that recovers and improves upon existing results for first-order and bandit convex optimization. We introduce a continuous-time model that enables an observation-centric rather than prediction-centric analysis. Under this model, regret decomposes into a delay-independent learning term and a delay-induced drift term, yielding a delay-adaptive reduction that converts any online linear optimization algorithm into one that handles round-dependent delays. For bandit convex optimization, we significantly improve existing regret bounds, with delay-dependent terms matching optimal first-order rates. For first-order feedback, we recover optimal regret bounds via a simpler, unified analysis. Quantitatively, for bandit convex optimization we obtain $O(\sqrt{d_{\text{tot}}} + T^{\frac{3}{4}}\sqrt{k})$ regret, improving the delay-dependent term from $O(\min\{\sqrt{T d_{\text{max}}},(Td_{\text{tot}})^{\frac{1}{3}}\})$ in prior work to $O(\sqrt{d_{\text{tot}}})$. Here, $k$, $T$, $d_{\text{max}}$, and $d_{\text{tot}}$ denote the dimension, time horizon, maximum and total delay, respectively. Under strong convexity, we achieve $O(\min\{σ_{\text{max}} \ln T, \sqrt{d_{\text{tot}}}\} + (T^2\ln T)^{\frac{1}{3}} {k}^{\frac{2}{3}})$, improving the delay-dependent term from $O(d_{\text{max}} \ln T)$ to $O(\min\{σ_{\text{max}} \ln T, \sqrt{d_{\text{tot}}}\})$, where $σ_{\text{max}}$ denotes the maximum number of outstanding observations and may be considerably smaller than $d_{\text{max}}$.

cs.LG

新论文 · v1arXiv:2611.12291

Representational Alignment between Deep Neural Networks and Human Brain in Speech Processing under Audiovisual Noise

Cheng Luo, Jian Zhu, Zhoujian Sun, Yunyi Qi, Yu Qi, Wenhui Sun, Wenyuan Yu

原文摘要

Speech comprehension in the human brain is an incremental process that begins with acoustic processing and advances to linguistic processing. While recent studies have revealed that the hierarchy of deep neural networks (DNNs) correlates with the ascending auditory pathway, the exact nature of this DNN-brain alignment remains underexplored. In this study, we investigate how DNN representations align with the brain's acoustic-to-linguistic processing. Specifically, we employed neural encoding models to simulate neural responses to acoustic (i.e., speech and noise envelope) and linguistic features (i.e., word onset and surprisal). By applying representational similarity analysis (RSA), we quantified the similarity between these neural responses and the DNN embeddings generated by a pre-trained automatic speech recognition (ASR) model, both before and after fine-tuning on audiovisual noisy data. Our results demonstrate significant DNN-brain alignment: embeddings from shallow layers exhibit higher similarity to neural responses associated with acoustic features, while those from deeper layers align more closely with neural responses related to linguistic features. Importantly, the fine-tuning process enhances this alignment by improving noise processing in shallower layers and refining linguistic representations in deeper layers. These results suggest that fine-tuned DNN models can naturally develop human-like processing patterns in noisy environments, highlighting a functional alignment between the human brain and DNNs in speech representation.

cs.AI

版本更新 · v2arXiv:2610.31228

Lightweight Frame Compensation for Real-Time Polyp Segmentation under Frame Skipping

Weihao Gao

原文摘要

Real-time polyp segmentation in computer-assisted colonoscopy is hampered by the difficulty of deploying high-accuracy models under strict latency budgets. Frame skipping, which performs inference every K frames and reuses or interpolates the rest, improves throughput but introduces motion blur and lesion misalignment that degrade temporal consistency. To close this gap, we propose the Lightweight Frame Compensator (LFC), a 77K-parameter plug-and-play module inserted before a frozen segmentation backbone. Operating on a three-frame window, LFC fuses consecutive frames via spatio-temporal attention into a single compensated frame, and is trained only on pseudo-labels generated by a differently seeded model, without any expert annotation. Experiments on three polyp video benchmarks show that LFC recovers most of the accuracy degraded by direct frame skipping and, in several settings, reaches the accuracy of frame-by-frame inference, while retaining a 2.05X--2.55X throughput gain. We further evaluate the temporal stability of three backbones spanning CNN, pyramid Transformer, and global-attention Transformer architectures, revealing a spectrum of sensitivity to frame skipping that arises from how locally or globally each architecture aggregates misaligned input. The compensation gain of LFC follows this spectrum: it is largest for high-capacity Transformer backbones, which achieve the best static accuracy but suffer the most under skip-frame inference. LFC thus offers a lightweight, pluggable, and deployment-friendly route to real-time polyp segmentation.

cs.CV

新论文 · v1arXiv:2611.12288

ForgeSystem: An Architecture for Demand-Specific Artefact Production with AI Agents

Qingfeng He, Zhui Zhu, Yaojian Chen, Shangzhan Li, Leshan Li, Tingjian Zhang, Qian Xie, Yuxuan Li 等 10 位作者

原文摘要

General-purpose software serves many different demands, but this flexibility costs performance and efficiency on any specific demand. Software tailored to a specific demand avoids these losses, yet developing it requires substantial time and effort from human experts. AI agents offer an alternative: they can design, implement and test artefacts tailored to individual demands. We call this production paradigm Forge. Forging for a demand is economically justified when the cumulative benefit of specialisation exceeds the total cost of construction, verification and maintenance. To make Forge a repeatable production process, we propose ForgeSystem, which consists of a control layer, a forge loop and a recursive self-improvement (RSI) loop. The control layer selects which artefact serves each demand and decides which demands to forge, when to forge them and from which starting point; the forge loop iterates between production and verification until a candidate artefact passes verification; and the RSI loop draws on accumulated production records to supply starting points, refine the harness and train models. We implement ForgeSystem for training frameworks, decoding megakernels and individual computational kernels. Forged training engines reach 1.047-1.332x the model-FLOPs utilisation of their reference frameworks, forged megakernels achieve a geometric-mean decoding speedup of 1.21x over SGLang across thirteen configurations, and forged kernels match or exceed expert libraries in eighteen of twenty-two configurations, while satisfying task-specific quality requirements. Controlled comparisons show that explicit quality requirements steer agents towards optimisations that preserve training quality. We also discuss a gradual transition to Forge through service routing, and how demand-specific production may shift value accumulation and trust towards production systems.

cs.SE

版本更新 · v3arXiv:2609.37311

ReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents

Haohao Qu, Yongcheng Jing, Chun Hin Chan, Shanru Lin, Wenqi Fan, Dacheng Tao

原文摘要

Recent Recommendation Agents (RecAgents) offer a promising alternative by shifting recommendation to an active, user-side paradigm, where generative agents autonomously perceive web platforms, reason over user preferences, and execute decisions. However, existing RecAgents still suffer from two critical limitations: brittle item perception based on noisy item pages, and inefficient long-context reasoning over extended user histories and multi-step interaction traces. To address these challenges, we propose a recommendation-agent framework, termed ReMem, that combines OCR-based multimodal perception with time-evolving dynamic memory. Instead of parsing raw HTML, ReMem observes item-page screenshots and uses an OCR tool to produce structured textual evidence for the reasoning backbone. To support long-horizon preference modeling, ReMem further introduces a chunk-wise sequential update strategy that maintains a bounded textual memory while processing histories longer than the backbone context window; with fixed chunk and memory budgets, the number of update calls grows linearly with history length. This design allows the agent to preserve evolving user preferences without relying on external memory modules or disrupting the standard autoregressive generation process. To train the dynamic memory updater, we further develop a multi-memory GRPO variant whose reward combines recommendation-specific information with final-task metrics. Experiments on three Amazon-derived datasets and a controlled post-retrieval protocol show an average relative improvement of 7.58% over the strongest reported baseline across searching, ranking, and judging tasks.

cs.AI · cs.IR

版本更新 · v2arXiv:2611.03555

MCP Tool Poisoning in Agentic AI Frameworks: A Cross-Framework Measurement Study

Farooq Shaikh, Biagio Montaruli

原文摘要

The Model Context Protocol (MCP) lets agentic AI frameworks connect language models to external tool providers, but it carries attacker-controlled content (tool descriptions, schema fields, and response data) into model context without validation. Prior benchmarks measure model compliance with poisoned instructions without confirming real execution. We present the first cross-framework measurement of MCP tool poisoning with real tool execution. A 25-class root-cause taxonomy unifies prior classifications, and the open-source tool mcpvenom drives a 9,720-cell susceptibility matrix across 12 frameworks, 18 models, and 45 attack scenarios, with a dual oracle that confirms exfiltration via canary HTTP receipt. The overall attack success rate is 22.9% (2,113 vulnerable cells). Of these, 64.9% dispatch an attacker tool call, 23.0% contact the attacker endpoint, and 12.1% verifiably exfiltrate a secret. Resistance is model-level: nine core frameworks cluster within 23 to 26% (chi-squared = 3.30, p = 0.91), and no framework implements intentional defense. Incidental framework properties mitigate in specific cases, and a regex description scanner rejects 20 of 45 scenarios at a 7.2% false-positive rate, so metadata scanning alone is a partial control. Model ASR ranges from 0.4% to 49.7%. Claude Opus 4.8 is vulnerable in 8 of 530 cells while issuing 223 explicit refusals. A code-level audit finds no intentional defense across twelve frameworks, and all five coordinated disclosures across four vendors were rejected.

cs.CR · cs.AI

版本更新 · v2arXiv:2610.35110

Understanding and Repairing Cooperative Perception under Adverse Weather

Mengxu Ma, Linshan Yan, Kailong Zhang, Ruiyang Guo, Dagang Shen, Yichen Fan, Hongping Gan

原文摘要

A cooperative detector can lose a correct vehicle detection when surrounding LiDAR measurements change, even if the returns on the vehicle remain unchanged. We study this failure as Weather-Induced Context Interference. On our CoInfra development set, controlled removal outside annotated object boxes turns 22.1% of V2X-ViT's previously correct detections into misses. Restoring network features around the objects to their values before removal recovers 98.6% of these misses. The same restoration in each of three equally sized regions excluding the objects recovers none. Candidate analysis finds accurate boxes that are not selected, while other targets lack well-localized candidates. With paired reference features unavailable at inference, Adverse-Weather Cooperative Repair (AWCR) repairs candidates from current observations. A lightweight Local Correction head generates bounded alternatives, and Quality Selection ranks them alongside original boxes with a correction weight. In V2X-R simulation, AWCR also filters peer returns before detection using Point Classifier trained on generated-point labels. Candidate repair improves mean car BEV AP@0.7 by 4.22 points across three fits on natural adverse-weather CoInfra development inputs and vehicle AP@0.7 by 5.00 points on a rain-affected public recording. It also improves released HEAL, FadeLead, and V2X-DGW detectors with their pretrained weights fixed. On the full V2X-Radar-C validation benchmark, HEAL with AWCR achieves state-of-the-art LiDAR-only cooperative detection performance of 68.22 vehicle BEV AP@0.7.

cs.CV

新论文 · v1arXiv:2611.12286

VLA-MOPD: On-Policy Distillation for Multi-Task VLA Policy Consolidation

Yongxuan Lv, Zhen Fang, Lichen Man, Hao Li, Pu Li, Hengyi Wang, Langfeng Cao, Lin Chen 等 13 位作者

原文摘要

Physical intelligence requires embodied agents to ground language in observations and execute actions while retaining useful skills. Vision-language-action (VLA) policies offer a shared interface, but task-specific post-training often produces separate specialists. Consolidation is difficult: mixed-task reinforcement learning provides sparse trajectory-level credit, while offline distillation may miss student-visited observations and endpoint distillation does not supervise intermediate action-generation states. We introduce VLA Multi-teacher On-Policy Distillation (VLA-MOPD), a protocol for consolidating flow-matching VLA specialists. After acquiring task or suite experts, a shared student collects robot rollouts and queries the instruction-routed frozen teacher at each visited observation and intermediate ordinary differential equation (ODE) state. Detached per-flow-step transition targets supervise valid action chunks through a masked local matching loss; an optional reference-policy term supports retention on other tasks. Starting from one trajectory per LIBERO task, VLA-MOPD raises mean success-once from 75.4% to 98.9%, compared with 98.15% for endpoint action distillation. It improves mean RoboTwin 2.0 success from 73.0% to 89.3%; on a Piper robot, two consolidation rounds improve average success from 70.0% to 90.0%. In a near-matched Spatial-adaptation study, reference matching limits the Object suite decrease to 3.0 points, versus 13.2 without the reference term.

cs.RO · cs.CV

新论文 · v1arXiv:2611.12285

Learning Evidence-Grounded Reasoning for Context-Aware Time Series Forecasting

Xingpeng Gao, Mingyue Cheng, Daoyu Wang, Huajian Zhang, Xiaoyu Tao

原文摘要

LLM-driven time series forecasting has become increasingly promising by leveraging contextual features to generate future values directly or refine forecast priors. However, incorporating contextual features alone does not ensure that models can identify which features matter for forecasting and understand what they suggest about future dynamics. We argue that the fundamental challenge is how to extract predictive evidence from contextual features and when and how to leverage it to guide forecasting decisions. In this paper, we propose CastReasoner, an evidence-grounded reasoning model for context-aware time series forecasting. Specifically, CastReasoner uses a structured chain of thought (CoT) to extract predictive evidence from contextual features, infer the future dynamics suggested by this evidence, and assess these dynamics against the forecast prior to guide adaptive forecasting decisions. To enable this capability, we design a reasoning-centric two-stage post-training framework including supervised fine-tuning (SFT) and reinforcement learning (RL). First, we synthesize reasoning trajectories through controllable multi-teacher guidance and select high-quality ones using a novel student-aware difficulty metric. Second, we design fine-grained multi-objective rewards to further improve reasoning and forecasting. To address heterogeneous learning needs across domains in both stages, we introduce a convergence-guided data balancing strategy. Through this two-stage training, CastReasoner improves both reasoning quality and predictive accuracy. Extensive experiments across multi-domain forecasting benchmarks demonstrate that CastReasoner achieves superior forecasting performance.

cs.LG

版本更新 · v2arXiv:2607.14817

Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning

Jakub Paplhám, Willem Waegeman, Eyke Hüllermeier, Vojtěch Franc

原文摘要

Current evaluation of epistemic uncertainty relies on tasks such as out-of-distribution detection, active learning and selective prediction. However, common epistemic uncertainty scores, such as mutual information or the variance of the predictions, estimate the regret, the excess error of a predictor over the Bayes-optimal predictor. Building on the epistemic reject-option framework, we evaluate epistemic uncertainty using its ability to identify regret, and compare this evaluation with the other tasks. Benchmarking standard methods on datasets with repeated human labels reveals that the tasks rank the methods differently, including pairwise rank inversions between methods that are top-ranked on one criterion and bottom-ranked on another. The disagreement is present already at the optimum, where each task calls for a different score. Formulating selective prediction as a constrained optimization over coverage, expected risk, and regret, we prove that the optimal score is a convex combination of the ground-truth aleatoric and epistemic uncertainties, so that selective prediction and the regret task are the two endpoints of one family of tasks. Out-of-distribution detection, active learning and the regret task thus disagree, theoretically as well as empirically, on which method is a good estimator of epistemic uncertainty, while selective prediction departs from the regret task where the true risk and the regret order the inputs differently. Researchers must therefore state the downstream decision that an epistemic uncertainty estimate is meant to support, instead of relying on a general notion of model ignorance.

cs.LG · cs.AI

新论文 · v1arXiv:2611.12275

SimpFlow: Transferable Pretraining for Fluid Dynamics via Simplified Physics

Ruijie Li, Tianbai Xiao

原文摘要

Neural surrogates enable rapid fluid simulation, but learning across diverse three-dimensional (3D) geometries requires costly computational fluid dynamics (CFD) labels. We introduce SimpFlow, a pretraining approach that generates supervision from simplified physics on unlabeled geometry libraries. A source-panel potential-flow solver generates velocity and pressure fields for approximately 9,000 3D geometries, capturing geometry-induced acceleration, stagnation, and suction while omitting viscosity and separated wakes. The solver imports only a surface mesh and reuses precomputed velocity fields across inflow directions, enabling inexpensive label generation. In our benchmark, amortized labeling takes 0.111 s per example using four CPU threads. We pretrain a neural surrogate on these labels and fine-tune it on independent CFD datasets. Across five flow tasks, SimpFlow improves over training from scratch in all 24 task-budget settings. With fine-tuning fixed at 200 epochs, interpolation indicates that SimpFlow requires 35-68% fewer CFD training cases to match the error of scratch models trained at each task's largest data budget. These results demonstrate that simplified physical solutions can provide transferable supervision, offering a practical way to reduce the high-fidelity data requirements of fluid surrogates.

cs.CE

版本更新 · v2arXiv:2508.03469

IKOD: Image-Attention-Guided Key-Value Merging against Object Hallucination in the Decoding of Large Vision-Language Models

Jiabing Yang, Chenhang Cui, Yixiang Chen, Tao Yu, Yan Huang, Liang Wang

原文摘要

Large vision-language models (LVLMs) exhibit strong visual understanding and language generation capabilities yet remain prone to object hallucination, producing plausible descriptions unsupported by the input image. Analyzing generation dynamics across eight diverse LVLMs, we observe that cross-modal visual attention steadily decays as generation unfolds because appended text tokens continuously expand the softmax denominator; consequently, hallucinated objects consistently appear later and under lower image attention than grounded mentions. Unlike existing training-free remedies that rely on input perturbations or external models, we propose IKOD (Image-attention-guided Key-value merging against Object hallucination in Decoding), a collaborative decoder that directly compresses the competing text context within the native key-value (KV) cache. At each step, IKOD keeps visual tokens intact and merges low-attention text entries into a compact auxiliary cache, fusing the resulting image-focused distribution with the base branch to correct ungrounded predictions while preserving linguistic fluency. An adaptive variant (IKOD-A) further schedules collaboration strength online from the measured attention decay under a single universal configuration. Extensive experiments across hallucination and general multimodal benchmarks on eight diverse LVLMs demonstrate that IKOD and IKOD-A consistently mitigate object hallucination while preserving object recall and general multimodal capabilities at minimal inference cost. Code is available at https://github.com/jiabingyang01/IKOD.

cs.CV

版本更新 · v3arXiv:2512.04562

LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models

Siddharth Betala, Samuel P. Gleason, Ali Ramlaoui, Andy Xu, Georgia Channing, Daniel Levy, Clémentine Fourrier, Nikita Kazeev 等 15 位作者

原文摘要

Generative machine learning (ML) models hold great promise for accelerating materials discovery through the inverse design of inorganic crystals, enabling an unprecedented exploration of chemical space. Yet, the lack of standardized evaluation frameworks makes it challenging to evaluate, compare, and further develop these ML models meaningfully. In this work, we introduce LeMat-GenBench, a unified benchmark for generative models of crystalline materials, supported by a set of evaluation metrics designed to better inform model development and downstream applications. We release both an open-source evaluation suite and a public leaderboard on Hugging Face, and benchmark 12 recent generative models. Results reveal that an increase in stability is accompanied by lower novelty and diversity on average, with no model excelling across all dimensions. Altogether, LeMat-GenBench establishes a reproducible and extensible foundation for fair model comparison and aims to guide the development of more reliable, discovery-oriented generative models for crystalline materials.

cs.LG

版本更新 · v2arXiv:2611.07425

BRIDGE: Bridging the Semantic Quantization Gap for Generative Recommendation

Yatong Xiao, Mingjie Sun, Peng Wang, Wenjin Wu, Peng Jiang

原文摘要

Generative recommendation retrieves items by autoregressively generating Semantic IDs(SIDs), where an RQ-VAE quantizes each item into a hierarchical SID sequence that the decoder generates level by level. We identify an overlooked bottleneck in this paradigm: the Semantic Quantization Gap(SQG). Quantization derives SIDs from rich continuous signals, including codebook centroids, local neighborhood geometry, and level-wise entropy. However, the decoder receives only discrete identifiers and loses the semantic structure that shaped them. This mismatch manifests in three ways: a grounding gap, where the decoder lacks semantic anchors when target-side information is limited; a neighborhood gap, where token-level supervision discards inter-item similarity and exacerbates exposure bias; and a difficulty gap, where computation is allocated uniformly despite generation difficulty diminishing with depth. To bridge the SQG, we propose BRIDGE. Codebook-grounded latent reasoning injects frozen quantizer centroids as semantic anchors before SID generation. Privileged EMA self-distillation transfers neighborhood-aware knowledge from a teacher to an on-policy student, preserving inter-item geometry while mitigating exposure bias. Effort-aware recurrence allocates more computation to the challenging early levels and progressively reduces it with depth. Across three Amazon benchmarks, BRIDGE improves Recall@10 and NDCG@10 by 10.9% and 9.7% on average over the strongest baseline (up to 12.6% and 10.7%). In a one-week online A/B experiment on a large-scale e-commerce advertising platform with 5% traffic, BRIDGE improves eCPM by 0.65%.

cs.IR

版本更新 · v2arXiv:2606.04853

Teaching Robots to Say 'I Don't Know' : SENTINEL for Uncertainty-Aware SLAM

Abhishek Seetharamu, Badrikanath Praharaj, Sreeram MV

原文摘要

Low-cost 2D LiDARs lack the intensity channel that higher-end sensors use to diagnose measurement failures, yet they are widely used on educational and budget robotics platforms. We present SENTINEL, a training - free, label - free reliability estimation framework that gives range - only LiDAR an effective diagnostic signal. SENTINEL combines geometry-based scan statistics with cross - modal depth consistency between LiDAR and an RGB - D camera to compute a per - scan reliability score between 0 and 1. When the score falls below a threshold, corrupted scans are rejected and the robot falls back to calibrated wheel odometry, preventing silent SLAM corruption. We evaluate SENTINEL on a GEFIER R1 four - wheel skid-steer robot equipped with an RPLidar A2M12 and an Intel RealSense D435i in a 185 cm by 245 cm arena containing controlled transparent and reflective failure elements on a central obstacle. Spatial reliability maps across five surface conditions, including glass, mirror, shiny paper, and a mixed mirror and shiny-paper condition, show clear separation between clean and failure cases, allowing affected regions to be identified as reject or noise. Because these failure modes are absent in simulation, validation is performed entirely on real hardware.

cs.RO