Computer Vision and Pattern Recognition

Papers filed under cs.CV on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

23,161 to 23,220 of 27,462

Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization
Yeongtak Oh, Dongwook Lee, Sangkwon Park +2
cs.CVarXiv:2605.09996v22026
EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations
Tanapat Ratchatorn, Masayuki Tanaka
cs.LGcs.CVarXiv:2608.15105v12026
PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking
Dengxian Gong, Yuanzheng Wu, Haobo Yuan +11
cs.CVarXiv:2607.00115v12026
Local Gains and Fixed-Assignment Set Losses in Shared Set Decoders
Ze Zhang, Yang Zhang
cs.CVcs.LGarXiv:2608.14717v12026
Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction
Yao Zhang, Zhuchenyang Liu, Yanlan He +2
cs.CVcs.IRarXiv:2603.09930v22026
See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic Manipulation
Tingjun Dai, Mingfei Han, Tingwen Du +6
cs.ROcs.CVarXiv:2603.09292v22026
Enhancing In-context Panoramic Generation via Geometric-aware Pretraining
Haoran Feng, Ruiyang Zhang, Longyi Zhang +2
cs.CVarXiv:2607.08765v22026
Semantic Slots for Video Object-Centric Learning
Khalil Sabri, Guillaume-Alexandre Bilodeau, Nicolas Saunier +1
cs.CVarXiv:2608.21636v12026
What to Preserve, Where to Adapt: A Depth-Wise Analysis of Forgetting in Continual Gynecological Image Segmentation
Amal Saqib, Tausifa Jan Saleem, Numan Saeed +1
cs.CVcs.LGarXiv:2608.13660v12026
SkillNet: Create, Evaluate, and Connect AI Skills
Yuan Liang, Ruobin Zhong, Haoming Xu +47
cs.AIcs.CLcs.CVarXiv:2603.04448v22026
MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation
Xiaohan Zhang, Yuqing Wen, Junlin Chen +9
cs.CVcs.SDarXiv:2607.14189v12026
LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents
Yogeswar Reddy Thota
cs.OScs.AIcs.CVarXiv:2606.30697v12026
Voxel-based 3D Facies Segmentation from Seismic Data: A Comparative Study
Duc-Thanh Pham, Minh-Tan Pham, Anh Nguyen +1
cs.CVcs.AIarXiv:2608.14058v12026
A Modular Agent for Reliable and Auditable Spatial Relation Verification in CT Scans
Simon Vincent Abel, Heiko Hillenhagen, Michael Götz +3
cs.CVcs.AIarXiv:2608.21140v12026
Panoptic Pairwise Distortion Graph
Muhammad Kamran Janjua, Abdul Wahab, Bahador Rashidi
cs.CVcs.AIcs.LGarXiv:2604.11004v12026
Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations
Zhixue Fang, Zhimin Zhang, Bi'an Du +6
cs.CVarXiv:2608.01628v22026
A Critical Synthesis of Uncertainty Quantification and Foundation Models for Semantic Segmentation
Steven Landgraf, Joceline Hinz, Markus Ulrich
cs.CVcs.AIcs.LGarXiv:2608.18709v12026
CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
Gene Chou, Charles Herrmann, Kyle Genova +6
cs.CVarXiv:2604.19741v22026
SeGPruner: Semantic-Geometric Visual Token Pruner for 3D Question Answering
Wenli Li, Kai Zhao, Haoran Jiang +3
cs.CVarXiv:2603.29437v12026
U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training
Zhiwen Yang, Jiayin Li, Hao Lu +3
cs.CVarXiv:2606.11032v22026
Watch, Remember, Reason: Human-View Video Understanding with MLLMs
Jiahao Meng, Yue Tan, Qi Xu +12
cs.CVcs.AIcs.MMarXiv:2606.07433v12026
SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis
Yecong Wan, Fan Li, Mingwen Shao +1
cs.CVarXiv:2605.07287v22026
PaintBench: Deterministic Evaluation of Precise Visual Editing
Kai Xu, Ellis Brown, Shrikar Madhu +3
cs.GRcs.CVcs.LGarXiv:2606.00188v12026
Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback
Edoardo Bianchi, Antonio Liotta
cs.CVarXiv:2605.03848v12026
Towards Interpretable Foundation Models for Retinal Fundus Images
Samuel Ofosu Mensah, Camila Roa, Kerol Djoumessi +1
cs.CVcs.LGstat.COarXiv:2603.18846v42026
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
GLM-V Team, :, Wenyi Hong +95
cs.CVarXiv:2604.26752v32026
Picking the Right Image to Classify: Reliable-Input Selection in Teledermatology
Fabian Gröger, Marco Weishaupt, Philippe Gottfrois +6
cs.CVcs.AIarXiv:2608.16198v12026
Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Data
Mohammadmehdi Ataei, Farzaneh Askari, Kamal Rahimi Malekshan +1
cs.CVarXiv:2604.24479v12026
DriveVA: Video Action Models are Zero-Shot Drivers
Mengmeng Liu, Diankun Zhang, Jiuming Liu +7
cs.CVcs.ROarXiv:2604.04198v22026
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models
Lexiang Xiong, Qi Li, Jingwen Ye +1
cs.CVarXiv:2603.15557v12026
LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV
Tengfei Liu, Yang Shi, Xuanyu Zhu +17
cs.CVcs.MMcs.SDarXiv:2605.26244v12026
Can Multimodal Large Language Models Understand OCT?
Baochen Fu, Wenzhi Deng, Baihao Jin +5
cs.CVcs.CLarXiv:2607.16609v12026
FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation
Zimu Lu, Houxing Ren, Yunqiao Yang +4
cs.SEcs.CLcs.CVarXiv:2602.03798v12026
Pixel-Level Pavement Distress Assessment Using Instance Segmentation
Logan Dewick, Bibesh Pyakurel, Kong Pheng Yang +2
cs.CVarXiv:2605.26095v22026
Toward Parking Spot Occupancy Recognition: A Self-Supervised Approach
Luan Marko Kujavski, Rayson Laroca, Paulo Lisboa de Almeida
cs.CVarXiv:2606.20886v12026
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding
Hejun Dong, Junbo Niu, Bin Wang +3
cs.CVarXiv:2603.22458v12026
VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction
Kaixin Zhu, Yiwen Tang, Yifan Yang +9
cs.CVcs.AIarXiv:2605.15186v22026
Style or Signature? Artist-Disjoint Evaluation of Style Classification in Frozen Vision Embeddings
Rory Ashton
cs.CVcs.LGarXiv:2608.14435v12026
Phi-4-reasoning-vision-15B Technical Report
Jyoti Aneja, Michael Harrison, Neel Joshi +3
cs.AIcs.CVarXiv:2603.03975v12026
Semantic Generative Tuning for Unified Multimodal Models
Songsong Yu, Yuxin Chen, Ying Shan +1
cs.CVcs.AIarXiv:2605.18714v22026
PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis
Jinrang Jia, Zhenjia Li, Yijiang Hu +1
cs.CVarXiv:2605.17916v22026
Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping
Tianxiang Du, Hulingxiao He, Yuxin Peng
cs.CVarXiv:2602.23980v12026
OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains
Xinyue Cai, Chaoyou Fu, Yi-Fan Zhang +2
cs.CVarXiv:2606.14702v22026
AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning
Mingyang Song, Haoyu Sun, Jiawei Gu +4
cs.AIcs.CLcs.CVarXiv:2601.18631v22026
How Accurate are Video Quality Models for Diffusion-Based Video Super-Resolution?
Benjamin Herb, Steve Göring, Alexander Raake +1
eess.IVcs.CVarXiv:2605.25940v12026
MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation
Youjun Zhao, Alex Warren, Gary K. L. Tam +1
cs.CVcs.LGarXiv:2608.07463v12026
DocAtlas: Multilingual Document Understanding Across 80+ Languages
Ahmed Heakl, Youssef Mohamed, Abdullah Sohail +6
cs.CLcs.CVcs.LGarXiv:2605.12623v22026
Hepato-LLaVA: An Expert MLLM with Sparse Topo-Pack Attention for Hepatocellular Pathology Analysis on Whole Slide Images
Yuxuan Yang, Zhonghao Yan, Yi Zhang +6
cs.CVarXiv:2602.19424v32026
A Hybrid Approach for Closing the Sim2real Appearance Gap in Game Engine Synthetic Datasets
Stefanos Pasios
cs.CVarXiv:2605.02291v12026
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
Guotao Liang, Zhangcheng Wang, Chuang Wang +6
cs.CVarXiv:2605.01517v12026
GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning
Haoyu Wang, Guoqing Ma, Zeyu Zhang +3
cs.CVcs.ROarXiv:2606.17480v12026
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
Fanqing Meng, Lingxiao Du, Zijian Wu +46
cs.CVcs.SEarXiv:2604.23781v22026
Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs
Yunhong Lu, Qichao Wang, Hengyuan Cao +2
cs.CVarXiv:2605.09433v12026
Watch Before You Answer: Learning from Visually Grounded Post-Training
Yuxuan Zhang, EunJeong Hwang, Huaisong Zhang +8
cs.CVcs.AIcs.CLarXiv:2604.05117v12026
Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study
Hao Dong, Hongzhao Li, Shupan Li +3
cs.CVcs.AIcs.LGarXiv:2605.06643v12026
O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning
Mei Yuan, Qi Long, Qifeng Wu +5
cs.CVcs.AIcs.CLarXiv:2607.18142v12026
Adapting Vision-Language Models for E-commerce Understanding at Scale
Matteo Nulli, Vladimir Orshulevich, Tala Bazazo +9
cs.CVcs.AIarXiv:2602.11733v12026
World Action Models: The Next Frontier in Embodied AI
Siyin Wang, Junhao Shi, Zhaoyang Fu +11
cs.ROcs.CLcs.CVarXiv:2605.12090v12026
Olaf-World: Orienting Latent Actions for Video World Modeling
Yuxin Jiang, Yuchao Gu, Ivor W. Tsang +1
cs.CVcs.AIcs.LGarXiv:2602.10104v22026
VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale
Sven Elflein, Ruilong Li, Sérgio Agostinho +4
cs.CVarXiv:2602.23361v12026

Computer Vision and Pattern Recognition

Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization

EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations

PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking

Local Gains and Fixed-Assignment Set Losses in Shared Set Decoders

Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction

See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic Manipulation

Enhancing In-context Panoramic Generation via Geometric-aware Pretraining

Semantic Slots for Video Object-Centric Learning

What to Preserve, Where to Adapt: A Depth-Wise Analysis of Forgetting in Continual Gynecological Image Segmentation

SkillNet: Create, Evaluate, and Connect AI Skills

MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation

LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents

Voxel-based 3D Facies Segmentation from Seismic Data: A Comparative Study

A Modular Agent for Reliable and Auditable Spatial Relation Verification in CT Scans

Panoptic Pairwise Distortion Graph

Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations

A Critical Synthesis of Uncertainty Quantification and Foundation Models for Semantic Segmentation

CityRAG: Stepping Into a City via Spatially-Grounded Video Generation

SeGPruner: Semantic-Geometric Visual Token Pruner for 3D Question Answering

U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training

Watch, Remember, Reason: Human-View Video Understanding with MLLMs

SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis

PaintBench: Deterministic Evaluation of Precise Visual Editing

Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback

Towards Interpretable Foundation Models for Retinal Fundus Images

GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

Picking the Right Image to Classify: Reliable-Input Selection in Teledermatology

Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Data

DriveVA: Video Action Models are Zero-Shot Drivers

Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models

LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV

Can Multimodal Large Language Models Understand OCT?

FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation

Pixel-Level Pavement Distress Assessment Using Instance Segmentation

Toward Parking Spot Occupancy Recognition: A Self-Supervised Approach

MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction

Style or Signature? Artist-Disjoint Evaluation of Style Classification in Frozen Vision Embeddings

Phi-4-reasoning-vision-15B Technical Report

Semantic Generative Tuning for Unified Multimodal Models

PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis

Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping

OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains

AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning

How Accurate are Video Quality Models for Diffusion-Based Video Super-Resolution?

MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation

DocAtlas: Multilingual Document Understanding Across 80+ Languages

Hepato-LLaVA: An Expert MLLM with Sparse Topo-Pack Attention for Hepatocellular Pathology Analysis on Whole Slide Images

A Hybrid Approach for Closing the Sim2real Appearance Gap in Game Engine Synthetic Datasets

VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation

GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning

ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents

Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs

Watch Before You Answer: Learning from Visually Grounded Post-Training

Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study

O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning

Adapting Vision-Language Models for E-commerce Understanding at Scale

World Action Models: The Next Frontier in Embodied AI

Olaf-World: Orienting Latent Actions for Video World Modeling

VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale