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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 06:40 — 2026-11-22 06:40(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.21690

EgoLink: Egocentric Language-Vision Interactive Network Knowledge Challenge Summary

Renhe Sun, Yueying Feng, Bohan Yu, Tong Niu, Yunqi Liu, Zitong Wang, Haolin He, Kexin Shi 等 15 位作者

原文摘要

The EgoLink Challenge at ACM Multimedia 2026 benchmarks egocentric multimodal intelligence linking first-person perception, social reasoning, and interactive action. Unlike benchmarks centered on visible objects and activities, EgoLink evaluates whether models can interpret emotional and social cues, resolve visually grounded references, and convert user requests into verified tool-mediated actions. Its two tracks cover social reasoning in egocentric video and interactive agents that complete service tasks through dialogue, tool use, and closed-loop execution. Together, they test whether perception, reasoning, and decision-making remain coupled under both offline question answering and state-changing interaction. We highlight a multi-stage Track 1 data pipeline for multiple-choice question (MCQ) generation, chain-of-thought generation, automatic quality grading, and video-contribution filtering. We summarize the task design, evaluation metrics, rules, leaderboards, and representative solutions. The benchmark combines objective answer scoring with process- and result-based evaluation, enabling analysis of both final correctness and execution quality. The best Track 1 system achieved 0.9263 accuracy, while the best Track 2 system achieved 0.844 joint success and 0.916 micro accuracy. Participant reports reveal a shared principle: strong systems make intermediate evidence explicit through candidate verification, option-robust reasoning, scenario-aware planning, tool canonicalization, and state-aware correction before answering or acting. These findings highlight the importance of process verification and evidence-grounded reasoning for reliable egocentric multimodal intelligence.

cs.CV · cs.AI

版本更新 · v2arXiv:2611.18312

On the Same Track: Privacy Leaks in Electric Rail Transport via Magnetic Fields

Stefan Czybik, Pia Hanfeld, Konrad Rieck

原文摘要

Inertial sensors of smartphones are a well-known privacy risk, as they allow inferring sensitive user movements and activity without explicit permissions. Among these sensors, the magnetometer has received little attention, as it is assumed to measure mainly the Earth's magnetic field. In this paper, we show that electric trains generate distinctive magnetic fields that can be captured by a smartphone magnetometer. Apps deployed on the device can access these signals without user permission, enabling two novel attacks on passenger privacy: First, we are able to determine whether the user is riding an electric train (transport mode detection). Second, we can infer whether other victims are aboard the same train due to shared patterns in the magnetic field (colocation prediction). In an empirical evaluation across 217 train rides, we demonstrate that both attacks are effective, confirming a real-world threat. We discuss countermeasures and argue that magnetometer access should require explicit user permission in mobile operating systems.

cs.CR

版本更新 · v4arXiv:2508.07216

Bridging Semantic Logic Gaps: A Cognition Inspired Multimodal Boundary Preserving Network for Image Manipulation Localization

Songlin Li, Zhiqing Guo, Yuanman Li, Zeyu Li, Yunfeng Diao, Gaobo Yang, Liejun Wang

原文摘要

The existing image manipulation localization (IML) models mainly relies on visual cues, but ignores the semantic logical relationships between content features. In fact, the content semantics conveyed by real images often conform to human cognitive laws. However, image manipulation technology usually destroys the internal relationship between content features, thus leaving semantic clues for IML. In this paper, we propose a cognition inspired multimodal boundary preserving network (CMB-Net). Specifically, CMB-Net utilizes large language models (LLMs) to analyze manipulated regions within images and generate prompt-based textual information to compensate for the lack of semantic relationships in the visual information. Considering that the erroneous texts induced by hallucination from LLMs will damage the accuracy of IML, we propose an image-text central ambiguity module (ITCAM). It assigns weights to the text features by quantifying the ambiguity between text and image features, thereby ensuring the beneficial impact of textual information. We also propose an image-text interaction module (ITIM) that aligns visual and text features using a correlation matrix for fine-grained interaction. Finally, inspired by invertible neural networks, we propose a restoration edge decoder (RED) that mutually generates input and output features to preserve boundary information in manipulated regions without loss. Extensive experiments show that CMB-Net outperforms most existing IML models. Our code is available on https://github.com/vpsg-research/CMB-Net.

cs.CV

版本更新 · v4arXiv:2605.20223

Why Latent Actions Fail, and How to Prevent It

Jung Min Lee, Taehyun Cho, Li Zhao, Jungwoo Lee

原文摘要

Latent action models (LAMs) aim to learn action-like representations from unlabeled videos by compressing frame-to-frame changes. The frames of in-the-wild videos, however, contain not only the agent's own state but exogenous state such as background clutter. Since the exogenous state introduces changes unrelated to actions, it hinders reliable latent action learning. This paper investigates this problem analytically by extending a linear LAM framework to explicitly model exogenous state. Our analysis reveals two insights: (1) minimizing the standard reconstruction objective produces latent actions that encode exogenous information from future observation; and (2) learning in a representation space that focuses on endogenous components is a key to mitigating the interference of noise. We further show that previously proposed auxiliary objectives, such as action-supervision, provably encourage latent actions to be consistent across exogenous states. These findings are validated through experiments on both linear and nonlinear LAMs, providing a unified theoretical analysis of how exogenous state hinders latent action learning and why common remedies work.

cs.CV

新论文 · v1arXiv:2611.20671

MASTA: A Feedback-Scheduled Multi-Agent System for End-to-End Tamarin Modeling and Analysis

Yongkang Xiao, Qiyi Deng, Jing Chen, Min Shi, Ju Ma, Ruiying Du

原文摘要

Tamarin-based formal verification of security protocols requires expert-authored multiset rewriting rules and temporal-logic lemmas. Translating a natural-language protocol description into a complete formal model with an LLM is hard because syntactic, reachability, and property-level errors compound across the multi-step modeling process, and a single agent that both authors and self-evaluates cannot reliably localize them. We present MASTA, a multi-agent system that addresses these difficulties through three innovations. First, an operational--evaluative role decomposition assigns rule modeling to an Architect, property modeling to an Auditor, and pure dispatch to a dedicated Arbiter that holds no authoring duties. Second, the Arbiter implements a Tamarin-anchored scheduler that dispatches the next agent based on the latest verifier verdict and routes problem-tagged fixes through a modification list, with a six-class problem taxonomy and an LLM deduplication check preventing routing deadlock. Third, we construct a benchmark of 10 protocols paired with 139 mutation variants and five fine-grained metrics that jointly assess model correctness ($M_1$--$M_3$) and completeness ($M_4$--$M_5$). On this benchmark, MASTA on Qwen 3.5-plus improves over OpenCode on the same backbone by up to $+0.27$ on individual metrics and ranks first on both the correctness and completeness averages, surpassing Codex (GPT-5.5) and Claude Code (Opus 4.7) despite using a weaker LLM. Ablations on five protocols confirm that removing the Arbiter collapses property and verification scores to zero.

cs.CR · cs.AI

版本更新 · v3arXiv:2609.03270

Carbon-aware Resource Management for Latency-Sensitive Cloud Computing Environments: A Taxonomy and Future Directions

Tharindu B. Hewage, Shashikant Ilager, Maria Rodriguez Read, Patricia Arroba, Rajkumar Buyya

原文摘要

The proliferation of cloud-based latency-sensitive workloads, such as autonomous driving, real-time healthcare services, industrial automation, immersive interactive services, and intelligent AI-based applications requires infrastructures tuned to meet stringent latency constraints. Today, these workloads are reshaping the cloud from a general-purpose computing platform into a diverse ecosystem of workload-specific cloud environments. As demand for latency-sensitive workloads grows, cloud providers must scale their infrastructures accordingly, adversely increasing the carbon footprint and challenging net-zero goals. However, the strict performance requirements and rigid deployment patterns used to satisfy latency Service Level Objectives (SLOs) constrains conventional carbon optimization. Therefore, novel carbon-aware techniques are needed to exploit application-specific opportunities for reducing both operational and embodied carbon footprints while preserving latency guarantees. This survey examines carbon-aware resource management for latency-sensitive cloud computing environments. We introduce a holistic taxonomy that organizes existing techniques by carbon management objective, workload management mechanism, control architecture, system tier, latency requirements, and deployment stage. Then, we use this taxonomy to classify and critically analyze existing approaches, revealing the interactions and trade-offs between latency guarantees and operational and embodied carbon reduction. Finally, we identify limitations in the literature and present a structured research agenda for the design of sustainable latency-sensitive cloud systems.

cs.DC

新论文 · v1arXiv:2611.20666

Conditional Diffusion Models for Amortized Bayesian System Identification

Mike Hänseroth, Niklas Wahlström, Thomas B. Schön, Thomas Seel, Jan-Hendrik Ewering

原文摘要

Generative diffusion models rapidly solve Bayesian inverse problems, such as image restoration and inpainting, with a single trained model and without retraining for each new observation or task. Bayesian system identification, which typically involves inferring the hidden states and parameters of a dynamical system from measurements, poses a closely related inverse problem. Yet it is often addressed with computationally heavy Monte Carlo methods that must be rerun for every new measurement record. Moreover, these methods are restricted to a single inference task, and their cost grows with the state dimension and the record length. To alleviate these restrictions, we interpret Bayesian system identification in hiddem Markov models (HMMs) as a general Bayesian inverse problem, taking advantage of conditional diffusion models. Specifically, a transformer-based diffusion model is trained once on short segments of simulated trajectories to approximate the joint posterior of states and parameters. Through an attention mask induced by the Markov property and a relative time encoding, it can then be deployed on any new measurement record of custom length. At inference time, the same model can flexibly and rapidly be conditioned for joint state and parameter inference, state smoothing, parameter inference, or reconstructing missing measurements, without retraining. We demonstrate these capabilities on four benchmark systems and examine how the length of the training segments affects state and parameter inference. On records five times longer than the training segments, the model maintains its state accuracy, whereas comparison methods either show a more than tenfold error increase or require ten times as much sampling time.

cs.LG · eess.SY

新论文 · v1arXiv:2611.20665

SiGMA: Site-Grounded Multi-Modal ISAC Data Generation for Environment-Aware Communications

Yijie Bian, Wei Guo, Kai Zhang, Xiao Ye, Shurui Xu, Shenghui Song, Jun Zhang, Khaled B. Letaief

原文摘要

Learning-based multi-modal integrated sensing and communication (ISAC) requires data that associate environmental observations with the wireless response generated by the same site and dynamic scene state. Acquiring such data at new sites requires sensor calibration, coordinated measurements, and cross-modal association. We present site-grounded multi-modal ISAC data generation (SiGMA), which combines OpenStreetMap (OSM), Overture Maps, and procedural three-dimensional (3D) reconstruction to create georeferenced urban scenes. A shared scene geometry and time-indexed actor state link synchronized red-green-blue (RGB) images, light detection and ranging (LiDAR) point clouds, positioning records, frequency-modulated continuous-wave (FMCW) Radar in-phase and quadrature (IQ) samples, and ray-traced wireless channels. For configurable reflected propagation under direct-link blockage, SiGMA generates optional reconfigurable intelligent surface (RIS) component channels for phase-configuration evaluation across shared scene states. The evaluation results demonstrate that the framework improves zero-shot beam prediction performance on real DeepSense 6G measurements compared with an OSM-derived synthetic-data baseline. A camera-assisted RIS case study further demonstrates the generation of sensing-associated supervision for configurable reflected propagation. The dataset generation pipeline is available at https://github.com/Trans-cending/SiGMA-main.

eess.SP · cs.DB

新论文 · v1arXiv:2611.20663

ParGLU: Partial Gating Improves Language Modeling in MoE Transformers

Yuting Ge

原文摘要

Multiplicative gating improves Transformer feed-forward networks (FFNs), but it reduces intermediate representation width under a fixed parameter budget. This trade-off is particularly relevant to Mixture-of-Experts (MoE) models, where individual experts have limited capacity. We introduce ParGLU, a partially gated FFN that combines SwiGLU and ReLU$^2$ in two parallel branches. ParGLU matches the parameter count and principal matrix computation budget of conventional SwiGLU. We evaluate ParGLU in 30M, 75M, and 152M MoE language models using three random seeds per scale. ParGLU outperforms SwiGLU across all three seeds at 75M and 152M, reducing mean validation NLL by 0.0200 and 0.0249, respectively. Results at 30M are mixed. Controlled ablations show that increasing backbone width or expert width strengthens ParGLU's relative performance. Ablation studies further show that combining SwiGLU and ReLU$^2$ improves performance over either architecture alone. Token-frequency analysis reveals larger improvements on low-frequency tokens. These findings show that fully gated FFNs are not always the most effective use of an MoE expert's parameter budget. Partial gating can improve language modeling in MoE Transformers.

cs.LG

新论文 · v1arXiv:2611.20660

Enhancing Mixed Oil Length Prediction through Graph Representation Learning

Xinyi Hong, Hai Shu, Zhaoyang Zhang, Lei Chen, Yanfeng Yang, Ziqi Chen

原文摘要

During the pipeline transportation of refined oil products, the inevitable formation of mixed oil segments poses considerable economic challenges to pipeline networks. Therefore, it is important to accurately predict the length of these mixed oil segments. Although previous methods have achieved relatively accurate predictions by integrating machine and deep learning algorithms, they ignore the statistical dependencies that remain among real-world mixed oil samples, which degrades model accuracy. To address this issue, we propose a novel Sample Dependencies Incorporated Graph Representation Learning (SDI-GRL) model. By representing samples and pipeline features as nodes of a graph, SDI-GRL connects dependent samples through their shared features, allowing message passing to propagate information across related samples. This graph-based framework allows our model to capture the statistical dependencies among samples absent in prior works. A case study on a mixed oil dataset demonstrates that our SDI-GRL model surpasses the strongest existing approach, reducing both the RMSE and the MAE by more than 10%.

cs.LG · stat.ML

版本更新 · v2arXiv:2510.10468

Galilean Symmetry in Robotics

Robert Mahony, Jonathan Kelly, Stephan Weiss

原文摘要

In this paper, we present a robotics-tailored exposition of Galilean symmetry that leverages the community's familiarity with and understanding of rigid-body transformations and pose representations. Our approach contrasts with common treatments in the physics literature that introduce Galilean symmetry as a stepping stone to Einstein's relativity. We show that the classical homogeneous matrix algebra known well to roboticist translates directly into the Galilean modeling framework and provides a powerful tool for tackling robotics problems involving inertial measurements and spatio-temporal variables. We demonstrate the potential of the approach by developing a powerful model for studying motion of vehicles in an Earth fixed rotating reference frame, and developing a fusion algorithm for measurements with uncertain time-stamps.

cs.RO · eess.SY

版本更新 · v2arXiv:2607.02891

Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions

Zihao Hu, Yuan Yao, Jiheng Zhang, Zhengyuan Zhou

原文摘要

Many online decision-making problems involve both round-specific feasible actions and drifting reward models: eligible ad impressions, feasible prices, and available treatments can change over time, while user preferences, demand curves, and patient responses may evolve. Motivated by these applications, we study non-stationary linear bandits with round-specific feasible decision sets. Our key contribution is a blockwise reduction that connects parameter drift in non-stationary linear bandits to model misspecification in contextual linear bandits while preserving the round-specific decision benchmark. This connection allows us to leverage misspecification-adaptive learning to obtain dynamic-regret guarantees for general time-varying decision sets. For a known path-length budget $P_T$, we establish these guarantees for general compact, adaptive non-anticipating decision sets under an oblivious parameter path, and for $K$-armed contextual linear bandits under an oblivious environment. For general time-varying decision sets, our bounds improve the dependence on $T$ and $P_T$ from the $\widetilde O(T^{3/4}P_T^{1/4})$ guarantees available for existing LinUCB-based approaches to $\widetilde O(T^{2/3}P_T^{1/3})$, matching the non-stationary lower-bound dependence up to logarithmic factors.

cs.LG · stat.ML

版本更新 · v5arXiv:2605.03940

Reentrant value fields as delayed coupled reaction-diffusion systems on finite graphs

Karsten Bohlen

原文摘要

We describe a dynamical system in which a symbolic field is coupled to a geometric field via a bipartite Hilbert-Schmidt kernel. The system is fully described by a retarded functional differential equation (RFDE) on the history space, subject to Lipschitz and small gain conditions. We show that the RFDE is well-posed under constant input and that it admits a compact global attractor. The principal subsystem $(H_L, X_R, P)$, which is comprised of the two primary fields as well as an executive field, is shown to be globally stable independent of delay, provided that the interfield coupling satisfies $C_{\mathcal{K}}^2<μ_Lμ_R$. In addition, we describe design specifications that fulfill the hypotheses of the main Theorem.

math.DS · cs.AI

版本更新 · v3arXiv:2609.39583

MADGRAV: a multilevel anomaly-detection pipeline for gravitational-wave searches applied to LIGO data

Gianluca Inguglia, Huw Haigh, Ulyana Dupletsa, Alessandro Longo

原文摘要

We present the results of \textbf{MADGRAV}, a deep-learning-based search for high-mass compact binary coalescences, applied to the data collected by the LIGO interferometers during the third observing run and during the first and second part of the fourth observing run. The \textbf{MADGRAV} pipeline consists of a series of sequential convolutional neural networks that perform anomaly detection, glitch classification, coherence testing, and signal ranking. Data from the Hanford and Livingston LIGO detectors are studied (both individually and in coherence) by way of 1 second Q-transform windows. Of the candidates that survive every stage of the pipeline, 48 reach the significance threshold, and we report 47 gravitational wave detections characterised by a false alarm rate below $1\,{\rm yr}^{-1}$ with a probability of astrophysical origin $p_{\rm astro}>0.9$. Of the 47 detections, 44 are shared with the minimally modelled coherent WaveBurst search. The observed total source-frame masses, extracted from official gravitational wave transient catalogues, are in the $14-236 M_{\odot}$ range with a median of $69 M_{\odot}$, and a median SNR of 16. We note that the recovered fraction of confident detections rises with mass: for LIGO detectors network SNR $>10$ the pipeline recovers $8.1\%$ of confident catalog events below $30 M_{\odot}$, $39.8\%$ between $30$ and $100 M_{\odot}$, and $53.3\%$ above $100 M_{\odot}$, corresponding to $33.3\%$, $45.5\%$ and $53.3\%$ of the events detected by coherent WaveBurst in the same bins. These results suggest that anomaly detection pipelines can serve as an independent detection channel complementary to matched filtering in the high-mass high-SNR regime.

gr-qc · astro-ph.IM · cs.LG

新论文 · v1arXiv:2611.20655

MetaAct: Self-Evolving Executable Action Constraints for Embodied Language Agents

Jiaxing Zhao, Hanwen Wang, Di Liu, Shaoteng Liu, Jing-Ran Su, Yanheng Li, Qian Zha, Jiaxi Li 等 12 位作者

原文摘要

Self-evolving language agents have emerged as a promising paradigm for continuously improving agent behavior through experience. However, most existing approaches evolve textual artifacts, which can influence action preferences but cannot reliably enforce action admissibility in embodied environments with discrete and often irreversible actions. We propose MetaAct, which shifts self-evolution from textual guidance to executable action constraints by synthesizing GEAR (Grounded Executable Action Rules) from execution feedback. Each rule is represented as a typed specification, compiled into a deterministic guard, and validated offline through trajectory replay without additional model calls or environment interactions. Across four benchmarks, MetaAct improves task performance; on ScienceWorld and WebShop, violations drop from 70% to 0% and 40% to 1%, with score gains of +10.1 and +8.0. Our code is available at https://github.com/BaiCubed/MetaAct.

cs.CL

新论文 · v1arXiv:2611.20653

RAMP: Rethinking Multimodal Evaluation through Answer Readout Protocols

Jianye Zeng, Qiao Yikang, Duan Huang, Ziying Song

原文摘要

Multimodal large language models (MLLMs) are often evaluated by converting model outputs into discrete answers. The conversion protocol determines which scores become predictions and can strongly influence the reported results. We introduce RAMP (Readout Aware Multimodal Protocol), a systematic framework that compares direct yes/no token logits, surface-form scores, and typed or reversed A/B interfaces under fixed model checkpoints and paired visual questions. On 500 POPE adversarial questions, typed versus bare readout changes accuracy by $-20.2$ percentage points for SmolVLM-256M, $-16.4$ for TinyLLaVA-1.1B, and $+1.8$ for Qwen2.5-VL-3B. Paired transitions reveal extensive prediction changes even when the net accuracy difference is small: 79 of 104 binary ChartQA items change correctness for SmolVLM-500M, despite a $+1.0$-point net difference. We further analyze prompt wording, candidate forms, option position, cross-task effects, and calibration. An independent offline replay reproduces 16,140 first-token decisions from saved raw scores with exact agreement. Our findings establish answer readout as a measurable component of multimodal evaluation and provide a reproducible protocol for analyzing model comparisons.

cs.CV · cs.CL

版本更新 · v2arXiv:2611.03103

VLALagBench: Understanding When and Why VLA Inference Latency Matters

Qi Wen, Borui Xu, Hussein Amro, Hongshi Tan, Hanmin Lin, Chaoyi Ruan, Shanghao Liu, Gang Yang 等 14 位作者

原文摘要

Vision-language-action (VLA) models offer a promising path toward general-purpose robot manipulation. While inference latency can affect task success in a constantly evolving physical world, the relationship between latency and task success rate remains poorly understood. In this paper, we introduce VLALagBench, a comprehensive benchmark for studying VLA inference latency sensitivity across task types, object speeds, execution modes (synchronous and asynchronous), and VLA policies. Using VLALagBench, we find that even a modest inference latency of 100 ms can nearly halve task success on moving targets, with sensitivity varying substantially across tasks and policies. These differences reflect task-specific requirements for precision and continuous motion. By overlapping inference with action execution, asynchronous execution can recover some of the lost success at the cost of more frequent inference requests. Building on these findings, we develop an empirical model that predicts task success from limited calibration data, achieving root-mean-square prediction errors of only 5.7-7.8% across various VLA policies. Given an inference system's latency and per-robot throughput, these predictions guide the selection of system-specific VLA algorithm configurations to maximize task success. We believe VLALagBench and these findings provide a solid foundation for future robotics algorithm-system co-design.

cs.RO

新论文 · v1arXiv:2611.20648

Competent Autonomous Driving Through Fine Tuning Vision Language Action Models with Symbolic Traffic Rules

Barkin Dagda, Vinal Asodia, Iman Sharifi, Peng Wei, Saber Fallah

原文摘要

Vision-language-action (VLA) models offer a unified approach to perception, reasoning, and control for autonomous driving, but accurate action prediction alone does not establish compliance with traffic regulations. This paper presents a rule-guided VLA framework that incorporates symbolic traffic-rule feedback into policy optimisation. The framework combines supervised fine-tuning on expert demonstrations with reinforcement learning (RL) refinement using a reward that encourages encoded-rule compliance while penalising deviations from expert actions. Selected provisions of the United Kingdom Highway Code are formalised as executable first-order logic rules using PyReason, covering speed adaptation, following distance, and road-user priority. A frozen vision-language model extracts scene predicates, which are combined with vehicle-state information to assess the projected consequences of candidate control actions. Offline evaluation on held-out data collected in the CARLA simulator compares three group-based RL methods. The results show improvements in both action prediction accuracy and encoded-rule compliance over the supervised baseline. The best-performing variant increases the overall rule pass rate from 92.9% to 97.6%, with zero observed violations of the encoded road-user-priority check in the evaluated samples. These findings support symbolic rule feedback as a means of improving VLA policy alignment with explicit traffic-rule criteria.

cs.CV

新论文 · v1arXiv:2611.20645

Defect-Aware Masked Autoencoders for Unsupervised Clustering of Steel Surface Defects

Shrey Patel

原文摘要

Reliable recognition of steel surface defects is essential for automated quality inspection, but supervised methods require manually annotated images that are costly to produce. This creates a need for methods that can learn useful defect representations directly from unlabelled surface images. This work presents Defect aware MAE, a label free masked autoencoder for clustering steel surface defects. Each image is divided into 196 patches, with 147 masked and 49 processed by a Vision Transformer encoder. Texture energy based masking preferentially hides structurally informative patches, while a shallow decoder reconstructs HOG descriptors that capture local texture and edge orientation. Strong augmentation and an intermediate layer readout are used to form the final image features. Pretraining uses no class labels, bounding boxes, detection branch, or contrastive loss. On the held out NEU DET split, UMAP followed by Ward clustering achieves 98.6% Hungarian matched accuracy, 0.968 NMI, 0.967 ARI, and 0.838 silhouette score. Under an identical encoder and training schedule, it exceeds a SimCLR contrastive baseline in accuracy, NMI, ARI and silhouette scores across 5 seeds.

cs.CV

版本更新 · v2arXiv:2607.24402

CogRec: Structure-Cognitive Fast-and-Slow Reasoning for Generative Recommendation

Xiang Liu, Jingsong Su, Shuqi Zhao, Pengbo Mo, Yiming Qiu, Huimu Wang, Mingming Li, Jiao Dai 等 10 位作者

原文摘要

Generative recommendation reformulates next-item prediction as identifier sequence generation, yet existing methods mainly treat the generated identifiers as target sequences to be memorized, leaving their hierarchical and relational structure underused for explicit reasoning. We propose CogRec, a structure-cognitive fast-and-slow reasoning framework that grounds intermediate reasoning in the same SID topology used for target generation. CogRec augments the vertical SID hierarchy with intra-layer semantic graphs and introduces SID Routing to represent recommendation reasoning through layer-wise Match, LateralJump, and Explore operations. These operations provide a structural interpretation of fast localization and slow navigation. A supervised multi-stage pipeline aligns newly introduced SID tokens, establishes direct generation, and trains natural-language and SID Routing branches from a shared checkpoint. Experiments on three Amazon Reviews 2014 categories show dataset-dependent effects of SID Routing. Routing improves Hit@10 and NDCG@10 over its direct-generation counterpart on Beauty and Sports, while reducing both metrics on Toys. These results characterize the benefits and dataset-dependent behavior of SID-grounded intermediate reasoning for generative recommendation. Code is available at https://github.com/caskcsg/CogRec.

cs.IR

新论文 · v1arXiv:2611.20643

Safety-Preserving Medical LLM Fine-Tuning via Bilevel Data Selection

Ruoxuan Shi, Sheng Yang, Zhengxing Su, Xiaoyang Hou, Yating Liu

原文摘要

As general large language models (LLMs) are increasingly adapted for patient-facing medical applications, improving medical capability while controlling patient-facing risks remains a critical challenge. Large-scale medical instruction data are essential for acquiring domain knowledge through supervised fine-tuning (SFT), but unsafe responses can undermine existing safety alignment. To address this problem, we propose Scalable Bilevel Data Selection (S-BDS) for safety-preserving medical SFT. By controlling selection-weight concentration, S-BDS enables reliable sample ranking over large candidate pools and identifies training examples that improve medical capability while controlling patient-facing risks. We combine clinician-validated safe data and selected data with unscreened medical instruction data for SFT, and jointly evaluate medical capability and patient-facing safety on HealthBench and PatientSafetyBench, respectively. Experiments across Llama and Qwen models show that S-BDS achieves the highest safe rates among all compared methods, outperforming the strongest baselines by 4.64 and 3.00 percentage points, respectively, while maintaining competitive medical capability. Further experiments show that varying the safety-oriented weight during SFT controls the trade-off between medical capability and patient-facing safety.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2611.03390

Progressive Multi-Scale Super-Resolution via Cascaded Bicubic Anchors and Inter-Scale Mutual Refinement

Chun-An Lin, Yu-Chia Chang, Chi-Mao Fan, Yen-Chieh Ouyang, Tsung-Jung Liu

原文摘要

Super-resolution networks are trained for one magnification factor, so several output resolutions require several models. We propose PMS-SR, a progressive single-input multiple-output network that produces x2, x4, and x8 results in one forward pass, with a Transformer backbone on the low-resolution grid. In Stage 1, each scale is predicted as a residual over the detached bicubic upsampling of the previous scale's prediction. With Dirac and zero initialization, training starts exactly from the bicubic cascade, and each head adds only the band the previous scale lacks. In Stage 2, inter-scale mutual refinement couples the scales in both directions through space-to-depth feedback, deformable alignment, and per-pixel fusion, so x8 features refine the x2 output. Trained on DF2K, the 7.95M-parameter model achieves a higher PSNR than every compared multi-scale method at x4 and x8 on all five standard benchmarks. At x8, it outperforms the x8-specific DRN-L on all of them, leads all compared methods on Urban100, and is within 0.13 dB of the best result elsewhere. Against three single-scale SwinIR-M models, PMS-SR uses 22% of the parameters, runs 2.9x faster on BSD100 inputs, and its outputs agree 6.7-12.4 dB more closely. Code and pretrained models will be released at https://github.com/julian135707/PMS-SR upon acceptance.

cs.CV · cs.LG · eess.IV

新论文 · v1arXiv:2611.20641

When is Uniform Sampling Optimal? Coresets for Distributional Clustering

Junqiu Hu, Lingxiao Huang, Baoduo Xu

原文摘要

Recent work [1] settled the optimal worst-case strong $\varepsilon$-coreset size for Euclidean $k$-means in unrestricted dimension at $\tildeΘ(\min\{k^{3/2}\varepsilon^{-2}, k\varepsilon^{-4}\})$, showing that the natural target $\tilde{O}(k\varepsilon^{-2})$ is unattainable in general. For mixtures of $k$ isotropic Gaussian components with balanced weights and bounded scale imbalance in dimension $d\ge\log k$, we show that uniform sampling yields strong $\varepsilon$-coresets of size $\tilde{O}(k\varepsilon^{-2})$, without cluster separation. This saves a factor of $\min\{\sqrt{k},\varepsilon^{-2}\}$ over the worst-case bound, up to logarithms. For population approximation by independent, equally weighted samples, the near-linear rate is optimal up to logarithmic factors over this class. More generally, for datasets generated from an isotropic Gaussian mixture $μ$ satisfying a mild cost-comparison assumption, uniform sampling yields strong $\varepsilon$-coresets of size $\tilde{O}((kζ_μ+π_{\min}^{-1})\varepsilon^{-2})$, where $π_{\min}$ is the minimum component weight and $ζ_μ$ measures scale imbalance. Our proof uses a base-shift cost decomposition: one query center per component describes the base costs, and graph spanners control the sparse corrections from points switching centers. For general mixtures under cost and tail assumptions, we obtain $\tilde{O}((kζ_μ+π_{\min}^{-1})\varepsilon^{-2}\min\{\sqrt{k},\varepsilon^{-2}\})$ samples. We also prove a matching $\tildeΩ(\min\{k^{3/2}\varepsilon^{-2},k\varepsilon^{-4}\})$ lower bound for population approximation by uniform sampling from anisotropic Gaussian mixtures, even with equal weights and a shared covariance matrix. [1] Junqiu Hu, Lingxiao Huang, Jian Li, and Baoduo Xu. Tight coreset bounds for $(k, z)$-clustering in Euclidean and doubling metrics, 2026. arXiv:2610.34373.

cs.DS · cs.CG

版本更新 · v3arXiv:2603.22916

GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle

Hai Zhu, Yantao Yu, Lei Shen, Bing Wang, Xiaoyi Zeng

原文摘要

In recommender systems, collaborative signals work well for popular items but are nearly absent for cold-start ones. Semantic content helps new items, yet over-reliance on it blurs the behavioral distinctions of popular items. Existing Semantic ID (SID) based methods handle this trade-off only partially, because their fusion of the two signals is rigid and item-agnostic. We present GateSID, a ranking framework that takes SID from an upstream tokenizer and adapts how each SID is used to the item's maturity through a single shared gate. The gate drives three mechanisms. Gating-Fused Shared Attention (GFSA) fuses the attention distributions of the two modalities rather than their representations. Gate-Regulated Contrastive Alignment (GRCA) strengthens semantic-behavioral alignment for items with weak collaborative evidence and relaxes it when collaborative structure is reliable. Gate-Regulated Semantic Resolution (GRSR) uses coarse shared SID prefixes for items with weak behavioral evidence and opens deeper SID levels when the gate indicates more reliable collaborative evidence. On a large-scale industrial dataset, GateSID leads the strongest SID-enhanced baseline by +0.27% CTR AUC and +0.36% CTCVR GAUC, with gains balanced across item groups rather than trading cold-start for popular-item performance; on the public Taobao-MM benchmark, it also leads overall and gives the strongest new-item results under both DIN and RankMixer backbones. In a one-month online A/B test, GMV improves by 2.6%, CTR by 1.1%, and Order by 1.6%, at a cost of less than 5 ms of additional latency. We also provide a systematic analysis of SID design choices, covering embedding type, codebook configuration, and fusion strategy.

cs.IR

新论文 · v1arXiv:2611.20635

Contrastive Activation-Guided Zeroth-Order Preference Optimisation for Memory-Efficient LLM Alignment

Weiyun Huang, Alessio Galatolo

原文摘要

Direct Preference Optimisation (DPO) simplifies reinforcement learning from human feedback, but still relies on traditional backpropagation and its associated activation-memory cost. Zeroth-order (ZO) optimisation avoids backpropagation, yet isotropic perturbations can produce noisy updates for preference objectives defined by differences between chosen and rejected responses. We introduce Contrastive Activation-guided Zeroth-Order Direct Preference Optimisation (CA-ZODPO), which constructs a low-rank search subspace from the activation discrepancy between the chosen and rejected responses in each preference pair. Perturbations are restricted to this subspace, while momentum is maintained in low-rank coordinates to preserve the memory advantages of ZO training. On Qwen2.5-1.5B with Anthropic HH-RLHF, CA-ZODPO outperforms common ZO baselines and remains competitive with first-order DPO in pairwise preference evaluation. It also reduces peak GPU memory by about 59\% at a sequence length of 2048 while retaining the sequence-length scaling behaviour of zeroth-order training.

cs.LG

版本更新 · v3arXiv:2605.15511

OmicsGBench: A Framework for Evaluating Graph Neural Networks on Omics Data

Louisa Cornelis, Johan Mathe, Louis Van Langendonck, Guillermo Bernárdez, Nina Miolane

原文摘要

Graph Neural Networks (GNNs) have become the dominant framework for inductive graph-level learning. Yet most benchmarks focus on the regime $n \gg p$, where the number of graphs $n$ greatly exceeds the number of nodes per graph $p$. This overlooks biological domains such as omics, which operate in the opposite $n \ll p$ regime, characterized by large graphs of genes, transcripts, or proteins across few patient samples. This raises the question: how do GNNs perform in this low-sample, high-node omics setting? We introduce OmicsGBench (Omics-Graph Bench), the first benchmarking platform for graph-level prediction on omics expression data, a domain whose defining characteristic is the $n \ll p$ regime. We provide a standardized, end-to-end modular infrastructure from raw omics data to families of featured graphs with varied structural properties. We benchmark classical GNNs, as well as GNNs designed for large graphs and omics applications, alongside MLPs and machine learning baselines to establish reference performances. Our results show that widely used GNNs often do not outperform simple MLPs and classical baselines. Ablation studies show that performance relies primarily on feature selection and whether the readout preserves node identity. Furthermore, graphs built from known biological interactions offer no consistent advantage over co-expression graphs. These findings challenge the prevailing assumption that graph structure inherently adds value in this domain, fostering a critical reassessment of current learning paradigms. Ultimately, by exposing these limitations, OmicsGBench provides the open-source ecosystem necessary for the community to develop and validate novel architectures explicitly tailored for biological graphs. The code is available at https://github.com/geometric-intelligence/OmicsGBench.

cs.LG

新论文 · v1arXiv:2611.20628

PixelBench: Evaluating Language Models for Pixel-Art Creation

Mutian Hong, Jianxuan Yao, Mingkun Yue, Changkai Li, Hower Yang, Haibin Ling

原文摘要

Pixel art is widely used in games and digital content creation, requiring readable forms, coherent spatial relationships, and harmonious colors under limited resolution and palette constraints. Language models show growing promise in visual creation, yet their pixel art creation capabilities lack systematic evaluation. We introduce PixelBench, formalizing text-to-image generation and instruction-guided editing for pixel art and providing a benchmark for these tasks. We further present a creation environment in which language model agents invoke drawing tools through code to generate and edit pixel art. We assess the quality of generated artwork through human evaluation and employ a multimodal large language model as a judge, validating the agreement between its automated assessments and human preferences. We compare language models and configurations across diverse subjects and canvas sizes. In our experiments, GPT-6 Astra achieves both the highest average judge score and the best average human rank, highlighting the potential of general-purpose language models for pixel art creation. We release the tasks, all artworks, the human rankings, and the judge protocol.

cs.CV

版本更新 · v3arXiv:2605.21061

Grounding Driving VLA via Inverse Kinematics

Junsung Park, Hyunjung Shim

原文摘要

Counterfactual obstacle insertion exposes blind planning in representative Driving VLAs: their trajectories remain largely unchanged despite a vehicle appearing directly ahead. An empirically calibrated bias-variance analysis identifies how ego-predictable training examples admit a shortcut through ego status and commands. We address this failure with an inverse-kinematics-inspired architecture that anchors trajectory decoding on current and predicted future visual states. First, a next visual state prediction objective that requires the LLM to predict the future visual scene provides dense visual supervision and suppresses shortcut paths. Second, a separate Inverse Kinematics Network (a cross-attention-based conditional diffusion model) that takes only the current and future visual states as input is designed to suppress reliance on ego status and textual shortcuts during trajectory decoding. Our 0.5B model achieves state-of-the-art trajectory planning performance on NAVSIM-v1, NAVSIM-v2, and nuScenes using cameras alone, without LiDAR or a BEV encoder. Against the matched OpenDriveVLA* baseline, it improves NAVSIM PDMS and EPDMS by 19.0 and 20.4 points, respectively. Controlled ablations and intervention analyses support improved use of visual features, with future-state prediction sharpening hazard-specific responses.

cs.CV · cs.AI · cs.RO

版本更新 · v2arXiv:2606.18692

Text-Based Visualizations for Learning Analytics: Perspectives from STEM Education Researchers

Huyen N. Nguyen, Kathleen Bowe, Minh-Huyen Nguyen, Kit Thompson, Caleb M. Trujillo

原文摘要

Visualizing student reflections collected throughout a course can help instructors track changes in student language and inform teaching decisions. Interpreting these changes, however, requires tools that connect overall patterns with individual responses, and how to design such visualizations for learning analytics remains an open question. To address this gap, we conducted a mixed-methods study with 10 STEM education researchers who offered dual perspectives as both instructors and qualitative researchers. We used two visualization platforms as probes to elicit expert perspectives: the Journal Data Dashboard, for analyzing formative assessments, and WordStream Maker, for authoring custom visualizations. Participants evaluated both platforms by analyzing weekly student journal responses from a data visualization course. Findings revealed shared prioritization of context and control, discipline-rooted differences in perceived usefulness, and, notably, epistemological disagreement about frequency as viable evidence in qualitative work. Some participants regarded frequency-based visualization as a productive entry point to qualitative analysis, while others argued that it conflicts with the values of qualitative data analysis and may obscure rare but critical responses. These findings support the argument that perceived ease of use and usefulness, context of use or role, and epistemic frames are relevant to users of qualitative data visualization and learning analytics tools. We discuss design implications for future tools to better integrate quantitative techniques with qualitative interpretation. Transcripts, tutorials, and all supplementary materials are available at https://osf.io/z2f8d.

cs.CY · cs.HC

版本更新 · v2arXiv:2611.16424

PhysCapBench: A Cross-Domain Benchmark for Physically Grounded Video Captioning

Haofeng Wang, Xuanyi Liu, Pengcheng Wen, Ruiqi Li, Yuhao Zhang, Tiange Zhang, Boren Zheng, Siyu Tao 等 15 位作者

原文摘要

Physical AI aims to learn transferable physical knowledge from real-world experience to understand, predict, and act in the physical world. Internet videos and embodied demonstrations provide complementary observations of motion, interaction, and state evolution. A foundational data challenge is to measure and preserve this physical information as training supervision. In video-language pretraining, captions express observed processes in language, yet a semantically correct description can omit the interactions and transitions that define those processes. Rich physical experience in video does not automatically translate into sufficient language supervision. This gap calls for a yardstick to assess annotation quality, compare captioning strategies, and guide training-data refinement. Motivated by our data construction for world-model pretraining, we introduce PhysCapBench, to our knowledge the first unified physical-caption benchmark spanning all three domains: third-person scenes, egocentric manipulation, and handheld-gripper demonstrations. It provides human-verified annotations for 1,500 video sequences and evaluates accuracy and coverage through seven physical dimensions. We examine downstream utility through video reconstruction and manipulation-policy fine-tuning. Physical captions reduce reconstruction LPIPS by 8.6-9.5% on third-person videos and 26.9-30.9% on egocentric videos relative to metadata captions. Training-instruction enrichment improves both PhysCapBench scores and policy success, including a 7.5-percentage-point gain for pi0.5 on a RoboTwin 2.0 subtask. PhysCapBench makes the physical content of language supervision inspectable and comparable, providing a cross-domain basis for its evaluation and improvement.

cs.CV · cs.AI