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)

23,281 to 23,340 of 27,447

VLANeXt: Recipes for Building Strong VLA Models
Xiao-Ming Wu, Bin Fan, Kang Liao +6
cs.CVcs.AIcs.ROarXiv:2602.18532v32026
DODO: Discrete OCR Diffusion Models
Sean Man, Gilad Deutch, Roy Ganz +4
cs.CVarXiv:2602.16872v22026
Layer by layer, module by module: Choose both for optimal OOD probing of ViT
Ambroise Odonnat, Vasilii Feofanov, Laetitia Chapel +2
cs.CVcs.LGstat.MLarXiv:2603.05280v12026
Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models
Christian Simon, Masato Ishii, Wei-Yao Wang +8
cs.CVcs.AIarXiv:2602.20981v32026
The Universal Normal Embedding
Chen Tasker, Roy Betser, Eyal Gofer +2
cs.CVeess.IVarXiv:2603.21786v12026
GRIT: Teaching MLLMs to Think with Images
Yue Fan, Xuehai He, Diji Yang +6
cs.CVcs.AIcs.CLarXiv:2505.15879v22025
Emerging Properties in Unified Multimodal Pretraining
Chaorui Deng, Deyao Zhu, Kunchang Li +9
cs.CVarXiv:2505.14683v32025
Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias
JuneHyoung Kwon, MiHyeon Kim, Eunju Lee +3
cs.LGcs.CVarXiv:2602.21773v12026
Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting
Shuangkang Fang, I-Chao Shen, Xuanyang Zhang +5
cs.CVarXiv:2602.20933v12026
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
Jiuhai Chen, Zhiyang Xu, Xichen Pan +10
cs.CVcs.AIarXiv:2505.09568v12025
Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities
Shanshan Zhao, Xinjie Zhang, Jintao Guo +9
cs.CVarXiv:2505.02567v62025
PEARL: Personalized Streaming Video Understanding Model
Yuanhong Zheng, Ruichuan An, Xiaopeng Lin +10
cs.CVcs.AIcs.IRarXiv:2603.20422v12026
WoW: Towards a World omniscient World model Through Embodied Interaction
Xiaowei Chi, Peidong Jia, Chun-Kai Fan +33
cs.ROcs.CVcs.MMarXiv:2509.22642v22025
RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
Yufeng Yang, Xianfang Zeng, Zhangqi Jiang +8
cs.CVarXiv:2603.25502v12026
Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets
Team Hunyuan3D, :, Bowen Zhang +17
cs.CVcs.AIarXiv:2509.21245v12025
Template-Based Feature Aggregation Network for Industrial Anomaly Detection
Wei Luo, Haiming Yao, Wenyong Yu
cs.CVarXiv:2603.22874v12026
OmniOCR: Generalist OCR for Ethnic Minority Languages
Bonan Liu, Zeyu Zhang, Bingbing Meng +5
cs.CVarXiv:2602.21042v12026
Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
Fangfu Liu, Diankun Wu, Jiawei Chi +7
cs.CVcs.LGarXiv:2603.12255v12026
PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image
Ziang Cao, Fangzhou Hong, Zhaoxi Chen +2
cs.CVcs.ROarXiv:2511.13648v12025
LIBERO-X: Robustness Litmus for Vision-Language-Action Models
Guodong Wang, Chenkai Zhang, Qingjie Liu +4
cs.CVcs.AIcs.ROarXiv:2602.06556v12026
UniMM-V2X: MoE-Enhanced Multi-Level Fusion for End-to-End Cooperative Autonomous Driving
Ziyi Song, Chen Xia, Chenbing Wang +3
cs.ROcs.CVarXiv:2511.09013v12025
MedSAM2: Segment Anything in 3D Medical Images and Videos
Jun Ma, Zongxin Yang, Sumin Kim +6
eess.IVcs.AIcs.CVarXiv:2504.03600v12025
LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs
Keda Tao, Yuhua Zheng, Jia Xu +13
cs.CVarXiv:2603.19217v12026
From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation
Yibin Liu, Yaxing Lyu, Daqi Gao +5
cs.ROcs.AIcs.CLarXiv:2603.15600v22026
NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)
Guanyi Qin, Jie Liang, Bingbing Zhang +50
cs.CVcs.AIarXiv:2604.12512v12026
SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
Hongchi Xia, Xuan Li, Zhaoshuo Li +9
cs.CVcs.ROarXiv:2602.10116v22026
MetaphorStar: Image Metaphor Understanding and Reasoning with End-to-End Visual Reinforcement Learning
Chenhao Zhang, Yazhe Niu, Hongsheng Li
cs.CVcs.AIcs.CYarXiv:2602.10575v12026
Do Thought Streams Matter? Evaluating Reasoning in Gemini Vision-Language Models for Video Scene Understanding
Shivam Sharma, Sankalp Nagaonkar, Ashish Choithani +1
cs.CVarXiv:2604.11177v12026
Emu3.5: Native Multimodal Models are World Learners
Yufeng Cui, Honghao Chen, Haoge Deng +20
cs.CVarXiv:2510.26583v12025
Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting
Hao Feng, Wei Shi, Ke Zhang +9
cs.CVarXiv:2602.05384v12026
Learning Image-based Tree Crown Segmentation from Enhanced Lidar-based Pseudo-labels
Julius Pesonen, Stefan Rua, Josef Taher +3
cs.CVarXiv:2602.13022v12026
FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On
Johanna Karras, Yuanhao Wang, Yingwei Li +1
cs.CVcs.GRarXiv:2604.08526v12026
DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation
Xu Guo, Fulong Ye, Qichao Sun +7
cs.CVarXiv:2602.12160v12026
Geometric Autoencoder for Diffusion Models
Hangyu Liu, Jianyong Wang, Yutao Sun
cs.CVarXiv:2603.10365v22026
Driving on Registers
Ellington Kirby, Alexandre Boulch, Yihong Xu +11
cs.CVcs.AIcs.ROarXiv:2601.05083v22026
VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification
Jiahao Meng, Tan Yue, Qi Xu +7
cs.CVcs.MMarXiv:2604.01569v12026
HY3D-Bench: Generation of 3D Assets
Team Hunyuan3D, :, Bowen Zhang +22
cs.CVcs.AIarXiv:2602.03907v12026
Adaptive Rectangular Convolution for Remote Sensing Pansharpening
Xueyang Wang, Zhixin Zheng, Jiandong Shao +2
cs.CVeess.IVarXiv:2503.00467v12025
FOTBCD: A Large-Scale Building Change Detection Benchmark from French Orthophotos and Topographic Data
Abdelrrahman Moubane
cs.CVarXiv:2601.22596v12026
Geometry-Aware Rotary Position Embedding for Consistent Video World Model
Chendong Xiang, Jiajun Liu, Jintao Zhang +7
cs.CVarXiv:2602.07854v32026
EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation
Shiyuan Yang, Ruihuang Li, Jiale Tao +3
cs.CVarXiv:2603.06014v12026
AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors
Matic Fučka, Vitjan Zavrtanik, Danijel Skočaj
cs.CVarXiv:2601.20524v22026
Locality-Attending Vision Transformer
Sina Hajimiri, Farzad Beizaee, Fereshteh Shakeri +3
cs.CVarXiv:2603.04892v12026
SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching
Yasaman Haghighi, Alexandre Alahi
cs.CVcs.LGarXiv:2602.24208v12026
BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation
Zihao Zhu, Ruotong Wang, Siwei Lyu +2
cs.CVcs.AIarXiv:2603.02816v22026
Visual Jigsaw Post-Training Improves MLLMs
Penghao Wu, Yushan Zhang, Haiwen Diao +3
cs.CVarXiv:2509.25190v12025
OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models
Yufeng Zhong, Lei Chen, Xuanle Zhao +7
cs.CVarXiv:2601.21639v22026
ACE-LoRA: Graph-Attentive Context Enhancement for Parameter-Efficient Adaptation of Medical Vision-Language Models
M. Arda Aydın, Melih B. Yilmaz, Aykut Koç +1
cs.CVarXiv:2603.17079v12026
DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference
Aditya Kumar Singh, Hitesh Kandala, Pratik Prabhanjan Brahma +2
cs.CVcs.AIarXiv:2602.18846v22026
Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control
Linxi Xie, Lisong C. Sun, Ashley Neall +3
cs.CVarXiv:2602.18422v12026
VIOLA: Towards Video In-Context Learning with Minimal Annotations
Ryo Fujii, Hideo Saito, Ryo Hachiuma
cs.CVcs.AIarXiv:2601.15549v12026
MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning
Shengyuan Liu, Liuxin Bao, Qi Yang +6
cs.CVcs.AIarXiv:2602.03320v12026
UM-Text: A Unified Multimodal Model for Image Understanding and Visual Text Editing
Lichen Ma, Xiaolong Fu, Gaojing Zhou +6
cs.CVarXiv:2601.08321v32026
Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning
Yifan Wang, Shiyu Li, Peiming Li +3
cs.CLcs.CVarXiv:2601.14750v42026
Uncertainty-Aware Vision-Language Segmentation for Medical Imaging
Aryan Das, Tanishq Rachamalla, Koushik Biswas +2
cs.CVcs.LGarXiv:2602.14498v22026
MMVU: Measuring Expert-Level Multi-Discipline Video Understanding
Yilun Zhao, Lujing Xie, Haowei Zhang +16
cs.CVcs.AIcs.CLarXiv:2501.12380v12025
Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization
Xingjian Diao, Zheyuan Liu, Chunhui Zhang +6
cs.CVcs.CLarXiv:2601.04442v22026
Kimi-VL Technical Report
Kimi Team, Angang Du, Bohong Yin +92
cs.CVarXiv:2504.07491v32025
On the Generalization Capacities of MLLMs for Spatial Intelligence
Gongjie Zhang, Wenhao Li, Quanhao Qian +4
cs.CVcs.LGarXiv:2603.06704v12026
CONQUER: Context-Aware Representation with Query Enhancement for Text-Based Person Search
Zequn Xie
cs.CVarXiv:2601.18625v12026

Computer Vision and Pattern Recognition

VLANeXt: Recipes for Building Strong VLA Models

DODO: Discrete OCR Diffusion Models

Layer by layer, module by module: Choose both for optimal OOD probing of ViT

Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models

The Universal Normal Embedding

GRIT: Teaching MLLMs to Think with Images

Emerging Properties in Unified Multimodal Pretraining

Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias

Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting

BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities

PEARL: Personalized Streaming Video Understanding Model

WoW: Towards a World omniscient World model Through Embodied Interaction

RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models

Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

Template-Based Feature Aggregation Network for Industrial Anomaly Detection

OmniOCR: Generalist OCR for Ethnic Minority Languages

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image

LIBERO-X: Robustness Litmus for Vision-Language-Action Models

UniMM-V2X: MoE-Enhanced Multi-Level Fusion for End-to-End Cooperative Autonomous Driving

MedSAM2: Segment Anything in 3D Medical Images and Videos

LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs

From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)

SAGE: Scalable Agentic 3D Scene Generation for Embodied AI

MetaphorStar: Image Metaphor Understanding and Reasoning with End-to-End Visual Reinforcement Learning

Do Thought Streams Matter? Evaluating Reasoning in Gemini Vision-Language Models for Video Scene Understanding

Emu3.5: Native Multimodal Models are World Learners

Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting

Learning Image-based Tree Crown Segmentation from Enhanced Lidar-based Pseudo-labels

FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On

DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation

Geometric Autoencoder for Diffusion Models

Driving on Registers

VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification

HY3D-Bench: Generation of 3D Assets

Adaptive Rectangular Convolution for Remote Sensing Pansharpening

FOTBCD: A Large-Scale Building Change Detection Benchmark from French Orthophotos and Topographic Data

Geometry-Aware Rotary Position Embedding for Consistent Video World Model

EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation

AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors

Locality-Attending Vision Transformer

SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation

Visual Jigsaw Post-Training Improves MLLMs

OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models

ACE-LoRA: Graph-Attentive Context Enhancement for Parameter-Efficient Adaptation of Medical Vision-Language Models

DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference

Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control

VIOLA: Towards Video In-Context Learning with Minimal Annotations

MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning

UM-Text: A Unified Multimodal Model for Image Understanding and Visual Text Editing

Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning

Uncertainty-Aware Vision-Language Segmentation for Medical Imaging

MMVU: Measuring Expert-Level Multi-Discipline Video Understanding

Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization

Kimi-VL Technical Report

On the Generalization Capacities of MLLMs for Spatial Intelligence

CONQUER: Context-Aware Representation with Query Enhancement for Text-Based Person Search