跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

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

统计口径与数据新鲜度

统计 2026-11-15 23:09 — 2026-11-16 23:09(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

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

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

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

浏览论文库

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

找到 17,708 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)
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

新论文 · v1arXiv:2611.15155

PRELUDE: Separating Common Components from Target-Specific Dependencies for Multivariate Time Series Forecasting

Dongqing Song, Jianyu Xu, Haobin Ding, Xinyi Guo, Jiahao Du, Ruiqi He, Ruiqi Liu, Yuntong Xie 等 9 位作者

原文摘要

Multivariate time series forecasting often improves the prediction of a target by modeling the interactions among variables, and cross-variable modules such as cross-sectional pooling, inter-variable attention, and graph structures are used to construct such interactions. However, by intervening on the cross-variable reading of existing models at inference time, we find that although these models substantially reduce forecasting error through cross-variable interaction, their reading is nearly identical for all targets: the gain appears to come from dependencies among variables but mainly comes from the common component. We term this phenomenon spurious dependency and attribute it to common-component confounding: present in every variable, the common component affects how reading distinguishes sources, so that reading tends to be shared across targets and concentrates on a few similar averages; dependencies thus make up a small share of the read-in content, and a common component composed of several drivers is only partly captured. Theoretical analysis further shows that the common component and dependencies place different requirements on reading and should therefore be handled in different ways. Accordingly, we propose PRELUDE, a separated-reading framework that estimates the common component holistically through cross-sectional pooling and multiple common factors, and reads dependencies for each target via lead-lag relations in the innovation space obtained by prewhitening. Extensive experiments on 16 real-world datasets from four domains show that PRELUDE effectively mitigates spurious dependency and achieves the best overall performance: it attains the best MSE on 23 of the 24 short-horizon and air-quality settings and reduces the average MSE by 6.1% relative to the strongest baseline.

cs.LG

新论文 · v1arXiv:2611.15153

MatrixSplat: Matrix-Parallel and Feature-Scalable 3D Gaussian Splatting Rendering on GPUs

Yangming Zhang, Siyi Wu, Jian Wang, Bingzhe Li, Wei Niu, Sheng Di, Ming Li, Miao Yin

原文摘要

3D Gaussian Splatting (3DGS) has emerged as a mainstream representation for real-time novel view synthesis and 3D reconstruction. However, existing 3DGS rendering pipelines are poorly aligned with modern GPU architectures: depth-sorted alpha compositing introduces strong per-pixel sequential dependencies, limiting parallelism and resulting in scalar FMA-dominated execution that underutilizes high-throughput matrix units such as Tensor Cores. This mismatch becomes more severe for multimodal and semantically enriched 3DGS, where high-dimensional features must be accumulated from millions of Gaussians, leading to rapidly increasing computation and memory costs. We propose MatrixSplat, a matrix-parallel rendering framework for feature-scalable 3DGS on modern GPUs. We first identify the sequential dependency of alpha compositing as a key obstacle to efficient high-dimensional feature rendering, and adopt an order-independent weighted accumulation formulation that transforms feature rendering into matrix-oriented computation. Our framework features three key designs: (i) a tile-based splatting pipeline that maps feature accumulation to warp-level matrix-multiply-accumulate execution on Tensor Cores; (ii) a warp-granularity Gaussian packing strategy that mitigates visibility irregularity and improves feature reuse; and (iii) a lazy channel-batched feature-fetching pipeline that reduces shared-memory pressure, maintains high warp occupancy, and overlaps memory access with matrix execution for high-dimensional features. On Mip-NeRF 360, LERF, and 3D-OVS, MatrixSplat achieves up to 3.8$\times$ speedup over 3DGS and 2$\times$ over TC-GS while maintaining rendering quality and semantic accuracy, and further reduces render-kernel time by up to 36.7$\times$ for high-dimensional features. Integrated into existing fast renderers, it provides an additional 1.69-2.84$\times$ speedup.

cs.CV

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

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

新论文 · v1arXiv:2611.15150

Knowledge Transfer for Conditional Flow Matching: Frozen Estimation and Adaptation

Yian Huang, Jian Huang

原文摘要

Conditional generative modeling with limited target data can benefit from representations learned in a related source population. We develop a transfer learning framework for conditional flow matching that accommodates distinct source and target response distributions and dimensions. Two procedures exploit a representation learned from source data: TFM-Freeze estimates a target velocity head with the representation fixed, whereas TFM-Adapt jointly learns the head and a representation adaptation under a functional anchoring penalty. For explicit neural network classes, we establish bounds on conditional squared Wasserstein risk that account for source estimation, target fitting, representation mismatch, and numerical integration. When the source representation admits a smooth correction, adaptation replaces the frozen mismatch contribution by the cost of learning the correction and a controllable regularization bias. An information lower bound identifies regimes in which adaptation attains a strictly faster conditional squared Wasserstein risk rate than any generator restricted to the frozen context information. We also develop independent validation procedure for selecting among fitted conditional generators. We show that the selection procedure satisfies an oracle inequality, and the switching rule guarantees, with high probability, no increase in conditional energy risk relative to a target-only generator. Simulations and real data applications illustrate the gains from our proposed methods and the effectiveness of target validation in guarding against negative transfer.

cs.LG · stat.ME

新论文 · v1arXiv:2611.15149

From Concepts to Interactions: Dynamic Graph Semantic Recomposition for Safe Visual Generation

Qinghui Gong, Jinshan Lai, Xunlei Chen, Hua Meng, Zhengchun Zhou

原文摘要

Recent advances in flow-matching Transformers have greatly improved Text-to-Image (T2I) and Text-to-Video (T2V) generation, but unconstrained generation risks producing illegal or unethical content. Safety alignment must therefore suppress unsafe content while preserving legitimate generation. A concept's safety depends on context: a knife used for cooking is safe, whereas its use in violence is harmful. Yet most concept erasure methods indiscriminately suppress static, isolated representations, overlooking evolving semantic interactions. Consequently, safe scenes containing potentially sensitive terms may be unintentionally suppressed, compromising generation quality. To address this, we propose Dynamic Graph Semantic Recomposition (DGSR), which dynamically constructs and updates a semantic interaction graph from evolving text visual states during sampling. Context aware graph reasoning captures semantic dependencies, while paired safe/unsafe supervision distinguishes harmful from legitimate interactions, enabling precise identification of and selective intervention on high risk semantic relationships while preserving benign semantics. DGSR freezes the pretrained backbone and supports both image and video generation. Experiments show that DGSR achieves the lowest Attack Success Rate (ASR) in 10 of 12 T2I evaluations and reduces the average T2V unsafe frame rate by 41.2\% relative to the strongest baseline, while maintaining high generation fidelity and temporal consistency.

cs.CV

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

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

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

新论文 · v1arXiv:2611.15146

Reframing Video Inverse Tone Mapping as Blind Posterior Inference via Latent Luminance Supervision

Hanwool Sul, Chang-Hoon Jeong, Kisung Shin, Bomseok Park, Donghoon Cha, Hansl von Kwon, DoHyung Ku, Byoung-Tak Zhang

原文摘要

High-dynamic-range (HDR) displays are now common, but most video content, such as archival footage, broadcast material, and the output of generative video models, exists only in standard dynamic range (SDR). The need is sharpest for generated video, which has no HDR master at all and is graded alongside live-action and visual-effects material finished in HDR. Converting SDR to HDR means undoing a tone-mapping operation that was never recorded, and clipping destroys the radiance wherever it acts, so HDR recovery is a blind inverse problem. Methods built on generative video priors fill clipped regions with plausible structure, but their reconstructions are systematically biased: in every public method we test, saturated content leans too bright or too dark, and the direction of the lean moves with the tone operator behind the input. We call this failure the luminance error, measure both its magnitude and its sign, and make it the focus of this work. Reframing ITM as posterior inference under an unknown operator locates the failure in two places and yields two corrections. A fixed affine functional of the video-diffusion latent reads log-luminance without decoding; on that coordinate an asymmetric loss selects an expectile of the posterior, applied only where clipping leaves luminance unconstrained. We also synthesize training SDR through an explicit family of tone operators, so the model marginalizes over what the observation cannot show. Trained this way, our luminance error stays flatter across operators and smaller on average than any public method, and the full system achieves the best perceptual quality on all three benchmarks.

cs.CV · cs.AI

新论文 · v1arXiv:2611.15142

When Does Learned Constraint Selection Pay in Security-Constrained Optimisation? A Boundary Map from SCOPF to Unit Commitment

Milad Kazemi, Behzad Kazemtabrizi

原文摘要

Learning-to-optimise methods for security-constrained optimal power flow (SCOPF) predict the security constraints that bind on each instance and solve only the reduced problem, with reported speed-ups of two to four orders of magnitude over the full problem. We ask whether learned selection beats the strongest learning-free alternative: a fixed umbrella set enforcing every constraint observed to bind in training. Our criterion, the price of a spare, answers this in advance: an enforced but inactive constraint is free, so the umbrella is exactly optimal wherever feasible, and learning can pay only where a spare decision carries a price. We test it systematically, including every PGLib-OPF network up to 10,000 buses. For SCOPF on a fixed network the umbrella is never beaten: its median size is five constraints across 43 networks, with no size trend, and our selector, while reproducing speed-ups of published magnitude (about x80,000 at case500), gains at most 0.25 ms over the umbrella and violates constraints on 4-5% of instances. Configuration diversity can break the umbrella's coverage on a small, densely meshed network but not at 2,000 buses, and we certify coverage with conformal risk control. In unit commitment, where a spare has a price, a static commitment loses 4-12% out of sample, and a predict-repair-reduce pipeline recovers it (cost gap 0.2-2.9%, fully feasible, 16-161x faster than the MILP). In our experiments, whether learning pays depends not on problem size but on whether a spare carries a price.

eess.SY · cs.AI

新论文 · v1arXiv:2611.15137

Serving-Aligned Entire-Space Conversion Modeling via Click-Through Rate Knowledge Distillation

Pavel Dolin, Xun Zou, Jiatian Wu, Deguang Kong

原文摘要

Recommendation systems may use predicted click-through conversion rate (pCTCVR), the product of predicted click-through rate (pCTR) and post-click conversion rate (pCVR), to guide ranking decisions. Many pCVR models build on the Entire Space Multi-Task Model (ESMM), which jointly trains pCVR and auxiliary pCTR towers using pCTR and pCTCVR losses, but deploys only the pCVR tower. At serving time, this tower may be paired with a separately trained pCTR model, creating a training-serving mismatch in pCTCVR when its predictions differ from those of the auxiliary pCTR tower. In this paper, we use knowledge distillation (KD) from logged serving pCTR scores to supervise ESMM's auxiliary pCTR tower and improve training-serving pCTCVR alignment. We denote variants by KD-$α$, where $α$ controls the hard-label loss weight. On the Ali-CCP dataset, KD-0.3, the best variant on serving pCTCVR, increases ROC-AUC not only for serving pCTCVR but also for pCVR by 2.1% and 1.6%, respectively, and PR-AUC by 9.9% and 8.8%, respectively, relative to the ESMM baseline. We also test negative downsampling with 5% nonclick retention. Downsampled KD-0.3 increases mean AUC for serving pCTCVR and pCVR by 1.2% and 0.9%, respectively, -and PR-AUC by 8.5% and 4.5%, respectively, relative to downsampled ESMM.

cs.LG

新论文 · v1arXiv:2611.15135

ARTS: An Open-Source, Reproducible Three-Arm Platform for Autonomy Research in Minimally Invasive Surgery

Jiawei Ge, Chunwoo Kim, Antony Goldenberg, Douglas McDonough, Justin Liao, Bo Ning, Sylvia Ladstaetter, Katya Van Anderlecht 等 21 位作者

原文摘要

Research on surgical autonomy needs open platforms that any laboratory can build, yet the most widely shared platform depends on donated clinical hardware, and open alternatives on industrial arms each lack part of the surgical chain. We present the Autonomous Robotic Translational System (ARTS), an open-source three-arm platform for autonomy research in minimally invasive surgery, built entirely from purchasable parts for about USD 137,000. Two UR5e arms hold wristed da Vinci X/Xi instruments, a UR5 arm holds a stereo endoscope with two FLIR cameras, the surgeon console provides haptic handles, footswitches and a stereo viewer, and a hardware stop independent of the software lets a supervisor freeze all three arms in place. The ROS 2 software pins every dependency, installs from the same scripts on bare metal or in containers, and records stereo images with hardware-measured timing. On the real arms, ARTS commands each arm at its controller's full rate (e.g., 500 Hz on the UR5e), the two cameras expose within 12 microseconds of each other, hand motion reaches the arm in 58 ms, and the endoscope image reaches the monitor in 68 ms. The ISO 9283 pose repeatability is 0.14-0.25 mm, comparable to a da Vinci Research Kit (dVRK) Classic arm on the same protocol, and an optical tracker measured a mean remote-center-of-motion error of 0.34-0.37 mm. Three expert and three novice operators performed the Fundamentals of Laparoscopic Surgery (FLS) peg transfer through a laparoscopic trainer box, and one of the experts sutured on a suture pad. The hardware designs, firmware and software are available at https://github.com/MRE-Lab-UMD/arts.

cs.RO

新论文 · v1arXiv:2611.15131

Duo: A Reciprocal World Model for Full-Duplex Interaction

Hengyuan Cao, Biao Gong, Guoshan Lu, Qiyuan Zhang, Lin Liu, Yiding Tian, Yilei Jiang, Yuxin Ma 等 20 位作者

原文摘要

In this report, we introduce the Reciprocal World Model (RWM) and present Duo v1, a full-duplex world model that continuously perceives audiovisual inputs while responding to users in real time. The RWM treats intelligence and physical reality as equally fundamental to what constitutes a world. Existing world models largely focus on simulating the latter, leaving reasoning and decision-making as external controls rather than intrinsic parts of the world itself. In RWM, we identify two equally fundamental capabilities: Intent, which provides the cognition underlying world interactions, and Realization, which generates coherent audio-visual behavior. To realize this formulation, Duo v1 introduces three key technical designs: (1) Leveraging autoregressive modeling for continuous interaction reasoning and participation decisions, rather than restricting it to instruction understanding for diffusion models. (2) Constructing chunk-specific conditions and synchronize tokens across Intent and Realization on a unified timeline. Module-specific attention masks enforce causal dependencies both within and across chunks, preventing access to future inputs. (3) Mitigating distribution shift in both modules through dual rollout distillation, training on autoregressively generated Intent tokens and synthesized audiovisual histories from Realization. Both modules continuously perceive real-time audio, video, and text, enabling full-duplex interaction with spontaneous conversations and interruptions. Beyond conversation, users can share real objects, reshape virtual scenes, guide assistants, or play audiovisual games without mouse or keyboard controls. The release of Duo v1 makes our first step, with the next version coming soon. We look forward to broader exploration of this emerging field.

cs.CV · cs.SD

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

新论文 · v1arXiv:2611.15130

Read Once, Answer Many: Parallel Prompting for Shared-Context LLM Inference

Zekun Zhao, Jeffrey Flanigan

原文摘要

LLM workloads sometimes ask many independent questions about the same long document, as in document QA, data labeling and LLM-based evaluation. Prefix caching removes the redundant prefill shared by these queries, but each decode step still reads the document's key-value (KV) cache once per question, so decoding is bound by memory bandwidth and scales with the number of questions. We present Parallel Prompting, which decodes P questions as P independent streams of a single request all at once, fixing this issue. In our method, every step reads the shared document once for all P streams, and a stream-id attention mask, evaluated inside the attention kernel, keeps each answer conditioned only on the document and its own question. We implement Parallel Prompting in SGLang by adding about 80 lines to three existing files and a small engine package; the mask needs no dense tensor, and every decode step has a fixed shape that is captured as a CUDA graph. With CodeLlama-7B, 8k-16k-token documents and 64-256 questions per document, Parallel Prompting is 3.7x faster than stock SGLang with its FlashInfer backend on an A100 and 5.9-6.0x faster on an RTX A6000, on two SGLang releases, including the most recent release. Timed on identical inputs, it is faster than stock SGLang in all 144 runs (2 GPUs x 2 releases x 6 workloads x 6 input sets). Code: https://github.com/jlab-nlp/parallel-prompting

cs.CL · cs.AI · cs.DC · cs.LG

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

新论文 · v1arXiv:2611.15126

Recompute or Restore? Host-Tier KV for Multi-Model Agent Workflows on a Static-Graph NPU Serving Stack

Sungwon Woo, Seyeon Kim

原文摘要

Agent workflows issue dependent model calls that share long context prefixes, so serving them efficiently depends on reusing the key-value (KV) cache of those prefixes. On accelerators that compile model graphs ahead of time, however, the device KV budget is fixed, and prefixes evicted under load must be recomputed. Restoring them from host memory avoids this recomputation, but the transfer occupies the same engine thread as prefill and decode, so its benefit is not guaranteed. In this paper, we study when restoring beats recomputing on a commercial static-graph neural processing unit (NPU) stack (Rebellions ATOM+, vllm-rbln 0.10.2) that serves a Qwen3-8B planner on two cards and a Qwen3-0.6B executor on one. We first show that repeated prefill dominates planner work when default serving collapses: 89.5% of the executed planner prompt tokens had been materialized before. We then build a synchronous host-DRAM tier on the runtime's public KV copy calls, together with a scheduler-aware event model whose predictions are frozen before each test cohort. Experimental results show that the host tier raises workflow service-level objective (SLO) attainment from 22.8% to 100% and from 9.4% to 99.8% in the two tested overload conditions, and endpoint confirmation on two new seeds supports conservative load gains of 11.8% (chain) and 18.2% (fork), while mixed and bursty workloads remain seed-sensitive. The frozen model predicts median and 99th-percentile (P99) latency within its 15% tolerance in all 24 common-load conditions, including the 16-18% P99 increase that the tier causes for fork workflows, but it misorders three policy contrasts and overestimates the benefit of a cheaper store path (11% predicted against 3.1% measured). The trade-off therefore depends on runtime scheduling and transfer cost as well as cache capacity.

cs.DC · cs.LG · cs.PF

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

新论文 · v1arXiv:2611.15125

Toward Cross-Rubric Surgical Skill Assessment via Joint Embedding Prediction

Jiajun Cheng, Haidar M. Abdul-Muhsin, Juha Choi, Shan Lin

原文摘要

Expert review of surgical videos is essential for surgical training but labor-intensive, motivating AI-assisted skill assessment to provide feedback at scale. Although surgical assessment rubrics may use different language to describe similar skills, existing automated methods commonly predict predefined skill levels or numerical scores tied to fixed rubrics, limiting their ability to transfer across semantically equivalent assessment criteria. We propose Predictive Rubric Alignment (PRA), a joint embedding prediction approach that scores surgical videos using natural-language descriptions of skill levels. Rather than matching level probabilities, PRA predicts a rater-weighted combination of skill-level description embeddings. Adjacent description features define a score-parameterized path, and the predicted embedding is projected onto this path to read the score. We introduce two variants: \textit{PRA-item}, which uses learned queries for predefined assessment items, and \textit{PRA-cond}, which generates queries from textual item names to enable assessment of unseen items without retraining. On AIxSuture, a dataset of expert-rated suturing videos, PRA outperforms published baselines in skill classification. We further evaluate zero-shot transfer to the smaller surgical skill assessment benchmark JIGSAWS. Trained on only two AIxSuture rubric items, PRA-cond assesses unseen JIGSAWS items without further training, yielding positive score correlations and greater Grad-CAM overlap with instruments and suture than a description-matching baseline. These results support predictive rubric alignment as a promising direction for flexible and explainable automated surgical skill assessment.

cs.CV

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

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

新论文 · v1arXiv:2611.15121

"I don't know what I don't know": Exploring the Benefits and Challenges of AI in Interdisciplinary Research

Indu Panigrahi, Tal August

原文摘要

Interdisciplinary research is widely lauded as beneficial for society but presents unique challenges to the researchers who bridge disciplinary boundaries. Despite the rapid increase in the availability and usage of AI systems for research tasks, there is little work studying how AI systems have impacted workflows that span unfamiliar disciplines. Through a survey ($N=62$) and follow-up interviews ($N=23$) with interdisciplinary researchers, we describe the unique challenges and opportunities for AI in interdisciplinary research workflows. Participants viewed AI both as a solution and exacerbation of the general challenge of "unknown unknowns": AI systems could facilitate a broad awareness of a new research area, yet also provide an illusion of understanding. Crucially, participants lacked the expertise and intuition to catch these illusions. Our findings motivate a focus on designing AI systems to support rather than automate collaboration across disciplines, scaffold learning opportunities, and include avenues for triangulation between resources.

cs.HC · cs.AI

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

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

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

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

新论文 · v1arXiv:2611.15117

PolyMorphWBC: Whole-Body Control from End-Effector Trajectories for Quadrupedal Mobile Manipulation across Arm Morphologies with Extended Reach

Heng Li, Yang Li, Yifan Duan, Ren Fang, Matao Duan, Wenhao Yu, Lu Zhang, Jianmin Ji 等 9 位作者

原文摘要

Quadrupedal mobile manipulators can extend their manipulation workspace by coordinating the mounted arm with the mobile base. At the task level, short-horizon end-effector (EE) trajectories provide an interface for specifying the desired manipulation motion without prescribing how it should be realized by the arm and base. However, executing such trajectories remains challenging because the controller must determine when and how the base should move, and this decision depends on the mounted-arm morphology. We therefore present PolyMorphWBC, a hierarchical controller that takes an EE trajectory as the sole task-level motion command and generates coordinated arm--base motions across four families of 6-DoF mounted arms, with extended-reach trajectories beyond the initial fixed-base reach. Within PolyMorphWBC, a trajectory-conditioned coordinator determines the base motion from previewed EE targets, while arm-specific Inverse Kinematics (IK) tracks the current target, and a frozen locomotion backend executes the resulting motion. Cross-arm reuse is enabled by a Unified Robot Description Format (URDF)-derived morphology conditioning, together with online residual-wrench feedback. We train PolyMorphWBC on procedurally generated arms and structured trajectories within and beyond fixed-base reach. In IsaacLab, it achieves 93.95% completion with 2.30cm position error and 4.81° orientation error on held-out trajectories and arm morphologies. In MuJoCo evaluation against UMI-on-Legs, PolyMorphWBC reduces EE position error by 69--72% and orientation error by 91--97% across four within- and extended-reach trajectories. On a physical Go2--ARX5 system, we demonstrate language-conditioned extended-reach pick-and-place using EE trajectories from pi_0 without vision-language-action (VLA)-generated base commands.

cs.RO

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