跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

跟进版本变化

查看已发布论文的最新修订，在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1673新增论文
+1257其中 AI 相关
+198已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-14 00:45 · 全站最近入库：2026-11-13 20:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-13 01:30 — 2026-11-14 01:30（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：2026-11-14 00:45最近发现新增版本：2026-11-13 20:44库内论文最新更新时间：2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,727 有修订112 HF 社区发现

论文修订列表

研究日报 / 周报 →按信源浏览 →

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 6,727 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-14 00:42（北京时间）
版本更新 · v2arXiv:2610.29647

Reading the Room: Scale-ambiguous Semantic Registration of Sparse VSLAM Maps to Floor Plans in Partially Built Environments

Bjorn Stragier, Emilia Szymanska, J. Micah Prendergast, Lukas Rosenberger Schmid

原文摘要

Many robotic construction applications, such as progress tracking, require registering a sensor trajectory to a prior 2D floor plan. Visual capture is attractive for its low cost and availability, but aligning a visual simultaneous localization and mapping (VSLAM) map to a floor plan is difficult; VSLAM recovers geometry only up to an unknown similarity transform, the sparse point cloud is cross-modal to the symbolic floor plan, sites are only partially built during capture, and construction sites are visually repetitive, degrading map quality while removing distinctive features. Existing methods address at most two of these challenges. We thus introduce Reading the Room(RR), a global-local approach to register scale-ambiguous, sparse, semantic VSLAM maps to partially built floor plans. Our key idea is to define a single robust, differentiable, class-balanced semantic-geometric energy function that governs all stages of the pipeline. We develop two global initialization schemes, leveraging a single inaccurate user-provided correspondence if provided, or estimating the initialization globally using a cross-modal matching network. Both schemes are designed to find initial candidates with respect to the energy function, which is then directly optimized for local refinement. We evaluate RR on 33 sequences across three active construction sites against classical and learning-based baselines, achieving a 4.5x improvement in mean absolute trajectory error over the strongest baseline in the general unconstrained setting, which increases to 7.6x when an anchor is provided.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2611.11306

ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping

Joseph Marvin Imperial, Daniel Slate, Noam Kolt

原文摘要

AI agents deployed on the open web are becoming more capable of performing actions that may breach contractual provisions and violate computer security laws. In this paper, we introduce ScrapeBench, the first agentic benchmark for empirically evaluating the legal compliance of AI agents with website scraping policies, namely terms of service (ToS) and robots$.$txt directives. Across widely used closed-weight and open-weight AI agents, we find that most agents exhibit low compliance rates (below 5%) when instructed to scrape websites in our sample of 1,626 popular websites that explicitly prohibit scraping. In addition, we observe that even where AI agents actively check the applicable ToS and robots$.$txt, they continue to exhibit low compliance rates. Conversely, in our sample of 269 websites that do not prohibit scraping, we observe that agents sometimes refuse to scrape despite it being lawful, such as Claude Opus 4.6 exhibiting an over-refusal rate of 98.5%. Our human baseline experiments (n = 180 participants) suggest that humans exhibit compliance rates comparable to AI agents but over-refuse at much higher rates.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.13504

RIGOR: Rig-Informed Geometry for Omnidirectional Reconstruction

Tingjun Huang, Dmitry Rudshin, Mathieu Meyer, Pietro Bonazzi, Marc Pollefeys, Emilia Szymanska

原文摘要

Recent developments in feed-forward 3D reconstruction resulted in models which can recover dense scene representations and camera motion solely from an image stream. However, such predictions are prone to becoming inconsistent over long trajectories, specifically in demanding environments with repetitive structures, weak textures and dynamic objects or people. One way to mitigate those challenges is to use an omnidirectional camera, which provides wide spatial coverage and captures richer visual information. Yet, the majority of models do not offer support for 360-degree imagery or require additional fine-tuning. To bridge these two aspects, we present RIGOR: a large-scale reconstruction pipeline for gravity-aligned omnidirectional videos that retains a frozen feed-forward perspective backbone and exploits each panorama as a four-view virtual rig. The rig structure is used to detect and repair locally inconsistent predictions, to retrieve loop closures through cyclic four-view consensus, and to geometrically verify candidate revisits before global optimization. Verified constraints drive a Sim(3) pose graph that corrects accumulated rotation, translation, and scale drift along the sequence. We demonstrate that the proposed consistency mechanisms improve both trajectory accuracy and reconstructed geometry over a feed-forward baseline on challenging construction-site sequences. The code is made available under this link: https://github.com/TangentH/RIGOR.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2610.26185HF 社区推荐

MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching

Yitong Li, Jiang Bian, Jingling Wang, Pan Ding, Chengying Gu, Xing Huang, Hana Song, Dong Zhang 等 26 位作者

原文摘要

Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluation benchmarks. Existing general-purpose benchmarks (e.g., MMLU and HELM) primarily assess broad knowledge and reasoning capabilities, but fail to capture critical domain requirements such as exercise safety, physiological appropriateness, personalization, and actionable coaching quality. This gap is particularly concerning in fitness and health applications, where incorrect or unsafe recommendations can lead to physical harm. To address this limitation, we introduce MoveBench, the first comprehensive benchmarking framework specifically designed for evaluating LLMs in sports and health coaching. The proposed benchmark integrates heterogeneous task formats, including multiple-choice questions (MCQs) and open-ended question answering (OpenQA), grounded in real-world user scenarios and paired with structured rubrics emphasizing safety compliance, scientific validity, and training logic. Through large-scale evaluation of 15 diverse LLMs on 809 questions with 5,012 rubric-level criteria, our results reveal substantial performance variability, particularly in safety awareness, structured program design, and personalization capability, highlighting a critical gap between knowing and doing. Our work establishes a foundational evaluation standard for sports and health LLM applications and provides a reproducible framework for advancing safe, reliable, and context-aware AI-driven coaching systems. Open resources are available at https://github.com/SatoSakula/MoveBench.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.17002

Governing Copyright Responsibly in the Era of Generative AI

D. Kochetkov

原文摘要

Large language models are trained on collections that may include scholarly works, while authors generally lack work-level information about whether and how their works were used. This paper asks how copyright governance frames and operationalises the protection of such authors, and what a responsible alternative would require. Forty legislative, judicial and soft-law instruments issued between 2019 and 2026 were coded deductively against a framework derived from Responsible Research and Innovation theory, yielding 1,337 category assignments across 835 segments. The European Union and the United States are the primary cases; the United Kingdom, China and international bodies serve as comparators. Normative orientation and the distribution of responsibility dominate the corpus, while reflexivity is the least represented category and reaches its minimum in the US sub-corpus. Both primary jurisdictions frame protection procedurally rather than as an entitlement, and no instrument in the corpus creates a general author-facing attribution duty for the use of works in AI training. From the coded gaps, the paper derives a six-instrument governance design and a capacity-based allocation of responsibility among developers, publishers, collecting societies, funders, institutions, regulators, and individual authors.

cs.CY · cs.AI · cs.DL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.21005

Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay

Xiaolong Li, Zhangchen Zhou, Zhi-Qin John Xu

原文摘要

Most explanations of training instability focus on learning-rate criticality, typically characterized by the Edge of Stability, beyond which optimization becomes unstable. We argue that, in practical deep neural network training, there is an additional and often overlooked weight-norm criticality. This criticality is induced by the interaction between normalization (which introduces scale-invariant components) and weight decay (which persistently shrinks parameter norms). As the weight decay coefficient increases, the norms of scale-invariant weights are progressively driven toward zero. Meanwhile, the sharpness of the loss landscape increases rapidly, destabilizing the optimization dynamics and resulting in abrupt loss spikes. This perspective provides a rationale for why weight penalties can improve generalization yet cannot be made arbitrarily strong: excessive decay drives scale-invariant weight norms past a critical boundary and destabilizes training. Our work provides a new mechanistic understanding of loss spikes through the lens of weight-norm criticality. Moreover, weight-norm criticality yields testable predictions that we validate empirically in networks with scale-invariant components, providing empirical support for the proposed mechanism.

cs.LG · cs.NE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.09995

Structural Guidance for Unified Joint Demosaicing and Denoising

Qixin Zheng, Ping Chen, Qiangqiang Shen, Haijin Zeng

原文摘要

Joint demosaicing and denoising is a fundamental step in camera image signal processing, yet remains challenging because different Bayer-like color filter arrays (CFAs) and sensor noise jointly corrupt both color sampling and image content. Existing unified restoration networks explicitly model CFA geometry but are still driven primarily by pixel-level supervision, making them prone to structural degradation around edges, repetitive textures, and moiré patterns where local evidence is unreliable. We attribute this limitation partly to the absence of explicit structural guidance beyond pixel-level reconstruction supervision. Motivated by this observation, we propose a structural-guided unified restoration framework that injects pretrained structural knowledge into CFA-aware image restoration. Our model receives a unified five-channel observation consisting of the raw mosaic, CFA masks, and a noise-level map. A SwinIR restoration branch reconstructs pixel details under CFA-conditioned modulation, while a parallel structural reasoning branch extracts complementary structural cues from a sparse pseudo-RGB observation. To bridge the substantial domain gap between sparse noisy sensor data and the natural-image pretraining domain of the structural encoder, we introduce a lightweight trainable adapter before residually fusing structural and restoration features. A shared decoder jointly predicts the restored RGB image and an auxiliary clean mosaic, providing supervision in both image and sensor domains. Extensive experiments across multiple CFA patterns and noise levels demonstrate consistent improvements over state-of-the-art unified and CFA-specific methods, indicating that adapted structural priors can enhance robust camera image restoration. The source codes and dataset are provided in the supplementary material.

eess.IV · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.32222

Geometry-Preserving Blind Watermarking for Raw 3D Point Clouds

Rungui Zhou, Chuanzhi Zhou, Ruihuan Wang, Peng-Shuai Wang

原文摘要

Raw 3D point clouds are a core geometric representation. Establishing their ownership is challenging because point sets are irregular, unstructured, and frequently altered by resampling and geometric preprocessing. We present a blind watermarking framework that operates directly on xyz coordinates and supports both object-level shapes and scene-scale scans. At verification time, the embedded message is recovered from the observed point cloud alone, without access to the original point cloud, color, normals, or mesh connectivity. The method jointly learns watermark embedding and extraction through a feed-forward octree-based architecture, enabling efficient multi-scale geometric reasoning on large point sets. During training, a stochastic transformation layer exposes the decoder to common geometric perturbations, while progressive pose alignment improves robustness to pose changes. Experiments on object-level and scene-level benchmarks demonstrate reliable message recovery under common geometric processing while maintaining low geometric distortion. Qualitative comparisons further show that the learned perturbations are less visually conspicuous and less spatially structured than those of handcrafted alternatives.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2506.11148

LLM-to-Phy3D: Physically Conform Online 3D Object Generation with LLMs

Melvin Wong, Yueming Lyu, Thiago Rios, Stefan Menzel, Yew-Soon Ong

原文摘要

The emergence of generative artificial intelligence (GenAI) and large language models (LLMs) has revolutionized the landscape of digital content creation in different modalities. However, its potential use in Physical AI for engineering design, where the production of physically viable artifacts is paramount, remains vastly underexplored. The absence of physical knowledge in existing LLM-to-3D models often results in outputs detached from real-world physical constraints. To address this gap, we introduce LLM-to-Phy3D, a physically conform online 3D object generation that enables existing LLM-to-3D models to produce physically conforming 3D objects on the fly. LLM-to-Phy3D introduces a novel online black-box refinement loop that empowers large language models (LLMs) through synergistic visual and physics-based evaluations. By delivering directional feedback in an iterative refinement process, LLM-to-Phy3D actively drives the discovery of prompts that yield 3D artifacts with enhanced physical performance and greater geometric novelty relative to reference objects, marking a substantial contribution to AI-driven generative design. Systematic evaluations of LLM-to-Phy3D, supported by ablation studies in vehicle design optimization, reveal various LLM improvements gained by 4.5% to 106.7% in producing physically conform target domain 3D designs over conventional LLM-to-3D models. The encouraging results suggest the potential general use of LLM-to-Phy3D in Physical AI for scientific and engineering applications.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.13772

RF3DGS: Reflection-Free 3D Gaussian Splatting with Self-Priors

Qiang Wen, Guotao Meng, Junhong Ruan, Hongyu Liu, Chenyang Lei, Qifeng Chen

原文摘要

3D reflection removal is crucial in applications demanding high-fidelity visualization, such as museum exhibitions. In this work, we propose Reflection-Free 3D Gaussian Splatting (RF3DGS), a novel method for superior reflection removal. RF3DGS exclusively leverages a widely-adopted photometric prior for reflection removal: that the minimum pixel intensity across multi-view images corresponding to the same 3D point strongly correlates with reflection-free information. However, generalizing this principle to a 3D Gaussian Splatting within a multi-view context is non-trivial. To address this, RF3DGS first optimizes a vanilla 3DGS model using a geometric prior to estimate a coarse, reflection-free depth map for each view. Leveraging these depth maps and photometric prior, a 3D warping process aggregates reflection-free information from auxiliary views to construct a clean transmission pseudo-label for a given reference view. This pseudo-label provides a robust self-supervised signal for optimization. We further introduce an Adaptive Twin Rendering (ATR) loss to synergistically utilize this pseudo-label while preserving high-frequency details from the original, reflection-degraded images. By adeptly fusing these internal 3D self-priors with the ATR loss, RF3DGS demonstrates state-of-the-art reflection removal performance across both synthetic and real-world scenarios. Furthermore, we establish the first 3D reflection removal benchmark, based on the Unity rendering engine, for rigorous quantitative evaluation.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.01870

ArcticSwarm: Deferring Early Consensus in Long-Horizon Multi-Agent Research

Soyoung Yoon, Boyi Liu, Yite Wang, Ruofan Wu, Canwen Xu, Nikki Lijing Kuang, Seung-won Hwang, Yuxiong He 等 9 位作者

原文摘要

Multi-agent systems have shown strong performance in domains with reliable verifiers such as coding, where a verifier can select among candidates generated in parallel. Long-horizon web search has no such verifier. Majority voting over independent runs cannot add an answer that none of the runs reaches. Agents that instead read each other's findings adopt an early candidate before alternatives are tested, a failure we call early consensus. We present ArcticSwarm, a multi-agent research architecture that separates evidence gathering from evidence integration. A gathering gate lets selected search tasks post findings to a shared board without reading it. An integration gate checks a candidate at three steps, and a failed check reopens search instead of only rejecting the candidate. On all 830 BrowseComp-Plus questions with the open-weight Qwen 3.5-27B, ArcticSwarm reaches 82.6%. MiroFlow reaches 70.6% under the same model, tools, and limits, and majority voting reaches 62.5% at the same token budget. Without the gathering gate, teams keep a wrong first candidate in 32.2% of runs instead of 22.3%, and accuracy drops by 3.8 points. Removing the integration gate lowers accuracy by 5.9 points. With GPT-5 on live-web BrowseComp, ArcticSwarm reaches 73.6%, above the published scores of GPT-5 (54.9%) and MiroFlow (63.4%). These results show that multi-agent search without a verifier benefits from deferring consensus until candidates are checked, instead of voting after search ends.

cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.05722

$\mathcal{B}^{3}$-Net: Controlled Posterior Bridge Learning for Multi-Task Dense Prediction

Meihua Zhou, Li Yang

原文摘要

Multi-task dense prediction solves complementary pixel-level tasks in a unified model, such as semantic segmentation, depth estimation, surface normal estimation, and edge detection. Existing decoder-side interactions use attention, prompts, routing, diffusion, Mamba, or bridge features to exchange task evidence, but most of them organize this evidence implicitly. They usually fuse task features by similarity or affinity, without explicitly modeling that evidence reliability varies across tasks and spatial locations. As a result, unreliable evidence may contaminate the shared representation and intensify negative transfer. We propose $\mathcal{B}^{3}$-Net, a controlled posterior bridge learning framework for multi-task dense prediction. Our method decomposes decoder-side interaction into reliability estimation, posterior bridge construction, and bounded redistribution. The Precision Field Estimator estimates patch-wise evidence precision from task-reference alignment and local variation. The Posterior Bridge Operator builds a precision-weighted posterior bridge through heteroscedastic evidence fusion, yielding a shared state more reliable than uniform or heuristic mixtures. The Contractive Dispatch Operator redistributes the bridge to each task branch through a bounded update, reducing uncontrolled feature injection. Experiments on NYUD-v2, PASCAL-Context, and Cityscapes show that $\mathcal{B}^{3}$-Net achieves competitive or superior trade-offs over representative CNN-, Transformer-, diffusion-, Mamba-, and bridge-feature-based methods. Backbone-matched comparisons and extensive analyses further verify that the gains arise from controlled posterior bridge learning rather than backbone capacity or decoder scale.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.01835

Learning Koopman operators for coupled systems via information on governing equations of subsystems

Tatsuya Naoi, Jun Ohkubo

原文摘要

Nonlinear coupled systems are ubiquitous in science and engineering. The analysis and modeling of such systems are challenging due to their high dimensionality and complex interactions among subsystems. In recent years, operator-theoretic methods based on the Koopman operator have attracted attention as a powerful tool for analyzing and modeling nonlinear dynamical systems. Extended dynamic mode decomposition (EDMD) is one of the most popular methods for approximating the Koopman operator. However, EDMD is a purely data-driven method, and it may be unstable and inaccurate for coupled systems under limited data availability. In this paper, we propose a method to construct a finite-dimensional Koopman matrix for coupled systems using the differential equations governing each subsystem. By regularizing the Koopman matrix toward a prior constructed from the subsystem equations, the proposed method improves prediction accuracy when only a limited number of snapshot pairs are available. We also demonstrate its effectiveness through numerical experiments on coupled oscillator systems.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2510.22105

Streaming Generation for Music Accompaniment

Yusong Wu, Mason Wang, Heidi Lei, Stephen Brade, Lancelot Blanchard, Shih-Lun Wu, Aaron Courville, Anna Huang

原文摘要

Music generation models can produce high-fidelity coherent accompaniment given complete audio input, but are limited to editing and loop-based workflows. We study real-time audio-to-audio accompaniment: as a model hears an input audio stream (e.g., a singer singing), it has to also simultaneously generate in real-time a coherent accompanying stream (e.g., a guitar accompaniment). In this work, we propose a model design considering inevitable system delays in practical deployment with two design variables: future visibility $t_f$, the offset between the output playback time and the latest input time used for conditioning, and output chunk duration $k$, the number of frames emitted per call. We train Transformer decoders across a grid of $(t_f,k)$ and show two consistent trade-offs: increasing effective $t_f$ improves coherence by reducing the recency gap, but requires faster inference to stay within the latency budget; increasing $k$ improves throughput but results in degraded accompaniment due to a reduced update rate. Finally, we observe that naive maximum-likelihood streaming training is insufficient for coherent accompaniment where future context is not available, motivating advanced anticipatory and agentic objectives for live jamming.

cs.SD

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.13506

$γ$-weakly $θ$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions

Mohammad Pedramfar, Vaneet Aggarwal

原文摘要

Many objectives in machine learning and combinatorial optimization are non-concave. We introduce $γ$-weak $θ$-up-concavity, a first-order condition for nonnegative monotone functions in which a scaling function $θ$ lets the curvature change with the size of the solution. The resulting class strictly contains monotone DR-submodular functions and One-Sided Smooth (OSS) functions. It also contains functions whose marginal gains first increase and then decrease, and functions that vanish faster than any power of the norm at the origin. We construct a surrogate gradient from gradients along the segment from the origin to the current point and prove an upper-linearization inequality with a point-dependent approximation coefficient. Restricting actions to the closed convex hull of the coordinate-wise maximal feasible points makes this coefficient uniformly positive, with a value determined by the curvature parameters and the geometry of the feasible set. Standard reductions to linear optimization then give offline approximation algorithms and online algorithms with regret guarantees. The coefficient matches the optimal one for DR-submodular maximization and improves the best known coefficients for OSS maximization over matroid constraints whenever the OSS parameter is positive.

cs.LG · cs.AI · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.11506

Principled Design of Diffusion-based Optimizers for Inverse Problems

Julio Oscanoa, Irmak Sivgin, Cagan Alkan, Daniel Ennis, John Pauly, Mert Pilanci, Shreyas Vasanawala

原文摘要

Score-based diffusion models achieve state-of-the-art performance for inverse problems, but their practical deployment is hindered by long inference times and cumbersome hyperparameter tuning. While pretrained diffusion models can be reused across tasks without retraining, inference-time hyperparameters such as the noise schedule and posterior sampling weights typically require ad-hoc adjustment for each problem setup. We propose principled reparameterizations that induce invariances, allowing the same hyperparameters to be reused across multiple problems without re-tuning. In addition, building on the RED-diff framework, which reformulates posterior sampling as an optimization problem, we further develop the OptDiff pipeline. OptDiff provides a simplified tuning framework that facilitates the integration of convex optimization tools to accelerate inference. Experiments on image reconstruction, deblurring, and super-resolution show substantial speedups and improved image quality.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2505.01584

Silent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adaptive Video Streaming

Zhiqiang He, Zhi Liu

原文摘要

Adaptive video streaming optimizes Quality of Experience (QoE) metrics by selecting appropriate bitrates according to varying network bandwidth and user demands. In practice, however, real-world network bandwidth often exhibits heterogeneity relative to training environments. Current methods predominantly tackle this problem through learning-based approaches designed to improve generalization performance. Our systematic investigation reveals a critical limitation: neural networks suffer from plasticity loss, significantly impeding their ability to adapt to heterogeneous network conditions. Through theoretical analysis of neural propagation mechanisms, we demonstrate that existing dormant neuron metrics inadequately characterize neural plasticity loss. To address this limitation, we have developed the Silent Neuron theory, which provides a more comprehensive framework for understanding plasticity degradation. Based on these theoretical insights, we propose the Reset Silent Neuron (ReSiN), which preserves neural plasticity through strategic neuron resets guided by both forward and backward propagation states. Moreover, we establish a tighter performance bound for ReSiN under non-stationary network conditions. In our implementation of an adaptive video streaming system, ReSiN shows substantial gains under non-stationary conditions in which the available bandwidth alternates between high and low regimes, improving the QoE by 178%, and it remains beneficial under stationary real-world traces, where it improves the QoE by 1.6%. Code will be available: https://tinyzqh.github.io/ReSiN/

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.13635

Min-CSPs on Complete Instances III: Nearly Optimal Characterizations of Approximation for Symmetric CSPs

Yihwan Chae, Chenglin Fan, Donghyeon Lee, Euiwoong Lee

原文摘要

This paper studies complete Min-$k$-CSPs: an instance on $n$ variables has one nontrivial constraint for every $k$-set of variables (so $\binom{n}{k}$ constraints in total), and the goal is to find an assignment that minimizes the number of unsatisfied constraints. They are motivated by the connections to machine learning and data science, as well as the possibility of being testbeds for new algorithmic techniques. Previous recent results presented polynomial-time algorithms for the decision version of every complete Boolean $k$-CSP, which is a necessary condition for any multiplicative approximations for the minimization version, but nontrivial approximation results have been limited to fragile CSPs, 2-SAT, and NAE-3-SAT, leaving the approximability of most complete Boolean Min-CSPs open, including complete Min-$k$-SAT. In this paper, we resolve this question, up to nearly matching factors, for the natural class of symmetric Boolean predicates. Given $A \subseteq \{0, \dots, k\}$, Min-CSP($A$) is a Min-$k$-CSP where each constraint is specified by $k$ literals and is satisfied if the number of true literals belongs to $A$. Let $w(A)$ be the maximum number of consecutive integers in $A$. Our main results for complete Min-CSP($A$) are (1) a QPTAS for $w(A) \leq 2$ and (2) an $\widetilde{O}(n^{w(A)-3})$-approximation for $w(A) \geq 3$, as well as almost matching hardness results for the latter. Our QPTAS for $w(A)=2$ significantly improves the previous $O(1)$-approximation for Min-2-SAT and the $\operatorname{polylog}(n)$-approximation for Min-NAE-3-SAT, as well as extends the PTAS for fragile CSPs (i.e., $w(A) = 1$).

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2505.20107

Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning

Ziyi Zhang, Li Shen, Deheng Ye, Yong Luo, Huangxuan Zhao, Meng Liu, Wei Yu, Lefei Zhang

原文摘要

Text-to-multiview (T2MV) diffusion models have shown great promise in generating multiple views of a scene from a single text prompt. While few-step backbones enable real-time T2MV generation, they often compromise key aspects of generation quality, such as per-view fidelity and cross-view consistency. Reinforcement learning (RL) finetuning offers a potential solution, yet existing approaches designed for single-image diffusion do not readily extend to the few-step T2MV setting, as they neglect cross-view coordination and suffer from weak learning signals in few-step regimes. To address this, we propose MVC-ZigAL, a tailored RL finetuning framework for few-step T2MV diffusion models. Specifically, its core insights are: (1) a new MDP formulation that jointly models all generated views and assesses their collective quality via a joint-view reward; (2) a novel advantage learning strategy that exploits the performance gains of a self-refinement sampling scheme over standard sampling, yielding stronger learning signals for effective RL finetuning; and (3) a unified RL framework that extends advantage learning with a Lagrangian dual formulation for multiview-constrained optimization, balancing single-view and joint-view objectives through adaptive primal-dual updates under a self-paced threshold curriculum that harmonizes exploration and constraint enforcement. Collectively, these designs enable robust and balanced RL finetuning for few-step T2MV diffusion models, yielding substantial gains in both per-view fidelity and cross-view consistency. Code is available at https://github.com/ZiyiZhang27/MVC-ZigAL.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2505.23458

Diffusion Guidance Is a Controllable Policy Improvement Operator

Kevin Frans, Seohong Park, Pieter Abbeel, Sergey Levine

原文摘要

At the core of reinforcement learning is the idea of learning beyond the performance in the data. However, scaling such systems has proven notoriously tricky. In contrast, techniques from generative modeling have proven remarkably scalable and are simple to train. In this work, we combine these strengths, by deriving a direct relation between policy improvement and guidance of diffusion models. The resulting framework, CFGRL, is trained with the simplicity of supervised learning, yet can further improve on the policies in the data. On offline RL tasks, we observe a reliable trend -- increased guidance weighting leads to increased performance. Of particular importance, CFGRL can operate without explicitly learning a value function, allowing us to generalize simple supervised methods (e.g., goal-conditioned behavioral cloning) to further prioritize optimality, gaining performance for "free" across the board.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.18504

UMER: Unifying Embedding and Ranking via Pair-Aware Discriminative Reasoning for Universal Multimodal Retrieval

Libiao Chen, Xiyang Liu, Yanheng Wei, Zhenyu Tang

原文摘要

Modern Web information access increasingly involves heterogeneous multimodal content, including images, videos and visually rich documents. Users may seek not only globally similar content but also candidates that satisfy fine-grained attributes, relations or answer evidence under complex instructions. Supporting such access requires both efficient corpus-scale retrieval and fine-grained relevance reasoning. Multimodal large language model (MLLM)-based embedding methods derive representations from MLLM hidden states, and recent work further uses Chain-of-Thought (CoT) reasoning to improve embedding capability by injecting intermediate semantic evidence into the representation. However, existing CoT methods typically use item-wise reasoning over queries and candidates in isolation, providing no explicit evidence to distinguish a positive from a semantically confusable hard negative. Moreover, contrastive embeddings capture global similarity but struggle with meta-tasks requiring answer verification, category judgment or fine-grained reasoning. In this paper, we propose UMER, a Unified Multimodal Embedding and Ranking framework for universal multimodal retrieval. UMER replaces item-wise reflection with PairAware Discriminative Reasoning, which compares query-candidate pairs to identify instruction-relevant matching and discrepancy evidence. UMER jointly learns contrastive embeddings for efficient global matching and discriminative ranking for explicit pairwise relevance judgment within a single MLLM. A complementary mutual distillation strategy further transfers reliable pairwise preferences between the embedding and ranking functions. On MMEB-V2, UMER-R scores 65.5/70.6 with Qwen2-VL-2B/7B, outperforming the strongest included matched-backbone baselines by 1.4/2.0 points. UMER also supports budget-adjustable inference from efficient embedding retrieval to optional pair-aware reranking.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.31022

Augmented Lagrangian Predictive Coding

Jeffrey Seely, Julian Gould

原文摘要

Predictive coding (PC) is a local-learning alternative to backpropagation (BP), training deep networks via local energy-minimization dynamics rather than a global backward pass. We introduce Augmented Lagrangian Predictive Coding (PC-ALM), which maintains PC's inference budget but aligns each weight update toward BP by accumulating per-layer constraint errors into a layer-local Lagrange multiplier. In linear PC networks, PC-ALM converges to an equilibrium with exact BP gradients distributed across the network via only layer-local updates. We analyze PC-ALM in nonlinear PC networks up to depth 128 and show that it matches BP performance across all width-depth regimes, notably in deep narrow networks where PC underperforms. PC-ALM introduces recurrent dynamics in each layer's activations. Compared to PC's heat flow on a scalar energy, PC-ALM dynamics are driven by dual ascent on the augmented Lagrangian. We observe "ballistic" credit propagation across very deep networks, with credit signals evenly distributed across layers, compared to PC's slow, diffusive credit propagation. Beyond the algorithm itself, the augmented Lagrangian framework offers a generalization of PC, and may yield insights into how distributed systems could compute and propagate BP-like credit signals through purely local dynamics.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.13626

FlashMotion: Ultra-Fast Long-Term 3D Motion Generation

Kaixing Yang, Xulong Tang, Ronghui Li, Xiangyue Zhang, Ziqiao Peng, Mingshuang Luo, Chenxi Zhao, Haoyu Wu 等 13 位作者

原文摘要

3D human motion generation plays a crucial role in game development, extended reality (XR), digital humans, and embodied simulation. Beyond motion generation, practical pipelines include rigging, retargeting, and rendering, making ultra-fast long-term 3D motion generation without compromising quality valuable for real-time interactive applications. Despite promising progress, high-quality long-horizon motion generation under tight inference budgets remains challenging, owing to 2 coupled bottlenecks: (1) generative strategies that require many sampling steps for high-quality 3D motion generation and (2) model architectures with substantial per-step computational and memory costs for long sequences. We present FlashMotion, a co-designed framework for high-quality long-horizon 3D motion generation under a strict inference budget, covering text-to-motion, music-to-dance, and speech-to-gesture tasks. To enhance trajectory-level efficiency, we introduce a 3D motion-space MeanFlow formulation with kinematic and dynamic consistency constraints for few-step generation, together with an Adaptive Soft masking mechanism for temporally coherent motion editing. To improve per-step efficiency, we design a lightweight non-autoregressive BiMamba architecture with condition-guided state selection and AdaIN-based condition fusion mechanism, enhancing cross-modal alignment and generalization to longer motion sequences. Extensive experiments demonstrate that FlashMotion achieves overall state-of-the-art performance in both quality and efficiency across text-to-motion, speech-to-gesture, and music-to-dance generation. The project page is available at https://sun-happy-ykx.github.io/FlashMotion-Project/

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2107.12636

Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers

Wen Wang, Yang Cao, Jing Zhang, Fengxiang He, Zheng-Jun Zha, Yonggang Wen, Dacheng Tao

原文摘要

Detection transformers have recently shown promising object detection results and attracted increasing attention. However, how to develop effective domain adaptation techniques to improve its cross-domain performance remains unexplored and unclear. In this paper, we delve into this topic and empirically find that direct feature distribution alignment on the CNN backbone only brings limited improvements, as it does not guarantee domain-invariant sequence features in the transformer for prediction. To address this issue, we propose a novel Sequence Feature Alignment (SFA) method that is specially designed for the adaptation of detection transformers. Technically, SFA consists of a domain query-based feature alignment (DQFA) module and a token-wise feature alignment (TFA) module. In DQFA, a novel domain query is used to aggregate and align global context from the token sequence of both domains. DQFA reduces the domain discrepancy in global feature representations and object relations when deploying in the transformer encoder and decoder, respectively. Meanwhile, TFA aligns token features in the sequence from both domains, which reduces the domain gaps in local and instance-level feature representations in the transformer encoder and decoder, respectively. Besides, a novel bipartite matching consistency loss is proposed to enhance the feature discriminability for robust object detection. Experiments on three challenging benchmarks show that SFA outperforms state-of-the-art domain adaptive object detection methods. Code has been made available at: https://github.com/encounter1997/SFA.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.13788

LLM Validation Makes Minimal-Pair Benchmarks Easier for Language Models

Guofang Tang, Zheng Qu

原文摘要

Minimal-pair benchmarks are only as good as their labels, and LLMs are an obvious substitute for costly human validation. We test it on BLiMP (English) and QFrBLiMP (Quebec French), the two public minimal-pair datasets releasing every forced-choice human judgment. Three LLMs validate by forced choice, by rating, and as a panel, scored against human panels of one, three and five judges in two pre-registered phases. On BLiMP, forced-choice validators agree with held-out human majorities more often than five-judge panels, yet catch far fewer pairs whose label humans reject than one judge does. By point estimate, no validator is worth more than one judge. The errors are not random. On both datasets, across 10 open LMs, human-supported pairs that the pre-registered LLM filter flags are 18.9 points harder than those it accepts, in all 70 LM-validator combinations, and harder than pairs a single human judge flags. Filtering thus removes items on which LMs fail but humans do not, raising accuracy more than random removal. A protocol frozen before any output replicates the gap and the lift on Dutch BLiMP-NL. LLM validation makes minimal-pair benchmarks easier for the models they are meant to test; we release code, validator outputs and item-level scores.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.14019

Program-Aided Patchable Skill Evolution

Jiahao Wang, Yuqi Xiong, Qing Yang, Zhipeng Xu, Zhenghao Liu, Zulong Chen, Yubin Bao

原文摘要

Agent skills have emerged as an effective means of enabling LLM agents to solve complex, interactive tasks by encoding reusable knowledge without modifying model parameters. Recent approaches further improve skill adaptation by distilling reusable experience from agent execution trajectories and evolving skills based on downstream task feedback. However, existing methods primarily represent skills as natural language documents, intertwining procedural logic with descriptive knowledge and making skills difficult to maintain and evolve. To address this limitation, we propose PASE (Program-Aided Patchable Skill Evolution), a program-aided framework that iteratively evolves skills by associating them with executable programs. Unlike prior approaches that encode trajectory-derived experience primarily in natural language, PASE separates reusable procedural logic into editable programs, enabling targeted updates to executable components while reducing the need to repeatedly revise natural language skills. Extensive experiments across diverse models and benchmarks demonstrate that PASE consistently outperforms all baselines, by achieving over 2.8% improvements. Further analyses show that PASE exhibits greater evolutionary stability and generalisation capability, highlighting the critical role of programmatic knowledge in skill evolution. We will release all data and code via GitHub.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.04411

TxBench: Verifying Public Incident Data to Benchmark Smart-Contract Attack Detectors

Tamer Abdelaziz, karim Ali

原文摘要

Malicious transactions on smart contracts cause billions of dollars in losses. To evaluate their detectors, most datasets copy the attack transactions that public incident databases cite and pair them with random transactions. However, these databases never check their citations against execution, and random transactions rarely resemble attacks. We present TXBENCH, a benchmark that verifies both attacks and legitimate transactions against their execution. TXBENCH labels a cited transaction as an attack only when its execution takes value from others and independent evidence ties it to its incident. Its legitimate transactions perform the same operations as attacks and carry positive evidence of legitimacy. Applying these checks to two public databases, we find that they share only 10.6% of their 1,850 cited transactions and that only 1,012 are verifiable attacks, worth $868.2 million. A blind manual review confirms 98/100 sampled attacks and 100/100 legitimate transactions.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.27741

Three-Photon Bayesian Imaging of Ortho-Positronium

L. Raczynski, W. Krzemien, A. Coussat, M. Bala, B. C. Hiesmayr, K. Klimaszewski, M. Obara, R. Y. Shopa

原文摘要

PET provides functional images relying on two-photon coincidences from positron-electron annihilation. In human tissue, about 40\% of annihilations are preceded by Ps formation, of which o-Ps component partially decays into three photons, with the remainder annihilating via pick-off or spin-exchange into two photons. This three-photon channel carries additional information about the surrounding micro-environment, including the three-to-two-photon yield ratio as a potential diagnostic marker. We propose the TRIO algorithm, a novel three-photon event-by-event image reconstruction algorithm formulated as a Bayesian maximum a posteriori inference problem. TRIO unifies time-based trilateration, energy-based reconstruction and, for the first time, a physics-informed prior derived from the QED description of Ps decay within a single probabilistic framework. In contrast to positronium lifetime imaging, which requires a prompt photon and is therefore restricted to specific radionuclides, TRIO relies solely on the three photons and is fully compatible with standard radionuclides such as 18F. Monte Carlo simulation modelled after the Siemens Biograph Quadra scanner demonstrates a mean position error of 1.65~cm, improving by a factor of about 2.8 over the time-based trilateration (4.59 cm) and a factor of about 5.3 over energy-based reconstruction alone (8.7 cm). More importantly, the proposed Bayesian approach is compatible with existing TOF-PET scanners that can register three-photon annihilation coincidences.

physics.med-ph · cs.CV · physics.comp-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.07629

Online Learning with Ordered Experts (via Two-point Feedback)

Shiliang Zuo

原文摘要

We study adversarial online learning with expert recommendations in a totally ordered action space, where the experts' recommendations may change and be reordered arbitrarily. Our focus is two-point feedback: on each round the learner plays two current recommendations, observes both, and pays their average. We study two problems. In the separated monotone problem, the loss is the sum of a hidden nondecreasing component and a hidden nonincreasing component, and a query reveals the two components separately. In the BV problem, the losses are bounded and have bounded variation (BV) along the order, and a query reveals only the loss. In the separated monotone problem, two paid observations achieve \[ O\bigl(\log(|\cF|T)\sqrt{T\log|\cF|}\bigr) \] regret against the best of $|\cF|$ experts, within a logarithmic factor of the classical full-information bound. For the BV problem, we obtain $\wtO(\sqrt T+|\cF|)$ regret. We give an application in dynamic pricing with expert advice, showing that two-option menus matches the full information rate up to $\log$ factors. The main technical ingredient is a marginal-preserving endpoint flow estimator. Two observations reveal a loss increment along the order; random paths supply telescoping identities that turn this local information into unbiased loss estimates for all current recommendations. A reversible pair sampler preserves the learner's intended marginal at both played actions. The estimator's second-moment and stability bounds support online updates for both feedback models.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v8arXiv:2602.07618

Neural Networks With Dense Computational Graphs Are Not Universal Approximators

Levi Rauchwerger, Stefanie Jegelka, Ron Levie

原文摘要

We investigate the approximation capabilities of dense neural networks. While universal approximation theorems establish that sufficiently large architectures can approximate arbitrary continuous functions when there are no restrictions on the weights, we show that dense neural networks do not possess this universality. Our argument is based on a model compression approach, combining the weak regularity lemma with an interpretation of feedforward networks as message passing graph neural networks. We consider ReLU neural networks subject to natural constraints on weights and input and output dimensions, which model a notion of dense connectivity. Within this setting, we demonstrate the existence of Lipschitz continuous functions that cannot be approximated by such networks. This highlights intrinsic limitations of neural networks with dense layers and motivates the use of sparse connectivity as a necessary ingredient for achieving true universality.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗