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)

18,481 to 18,540 of 18,817

MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
Minghao Guo, Qingyue Jiao, Zeru Shi +14
cs.CVcs.CLcs.IRarXiv:2605.15128v12026
MBench: A Comprehensive Benchmark on Memory Capability for Video World Models
Shengjun Zhang, Zhang Zhang, Simin Huang +11
cs.CVarXiv:2606.00793v22026
No One Knows the State of the Art in Geospatial Foundation Models
Isaac Corley, Nils Lehmann, Caleb Robinson +6
cs.CVcs.CYarXiv:2605.12678v22026
Next Forcing: Causal World Modeling with Multi-Chunk Prediction
Gangwei Xu, Qihang Zhang, Jiaming Zhou +4
cs.CVarXiv:2606.11187v12026
SCAIL-2: Unifying Controlled Character Animation with End-to-End In-Context Conditioning
Wenhao Yan, Fengjia Guo, Zhuoyi Yang +1
cs.CVarXiv:2606.10804v32026
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Zhiheng Liu, Weiming Ren, Xiaoke Huang +12
cs.CVarXiv:2604.24763v22026
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
Xiang An, Yin Xie, Feilong Tang +27
cs.CVarXiv:2605.25979v12026
ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
Yining Hong, Jiageng Liu, Han Yin +5
cs.CVcs.AIcs.CLarXiv:2605.18746v22026
iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework
Jianjie Fang, Yingshan Lei, Qin Wan +8
cs.CVcs.AIarXiv:2605.03941v22026
AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing
Jisong Cai, Long Ling, Shiwei Chu +10
cs.ROcs.AIcs.CVarXiv:2606.09811v12026
NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
Peng Cai, Zhaofan Zou, Shifa Liu +6
cs.CVcs.AIarXiv:2608.12898v12026
WorldRover: A Scalable Synthetic Video Data Engine for World Exploration with Rich Annotations
Xiaojie Xu, Zhengyuan Lin, Runyi Li +3
cs.CVcs.GRarXiv:2608.15659v12026
A Plug-and-Play 2D Motion Interface for Real-World Motion Language Models
Kaname Yokoyama, Norimichi Ukita
cs.CVarXiv:2608.15984v12026
NARRATE: A Multimodal Real-World Australian Driving Dataset for Human-Centred Explanations in Automated Driving
Ashkan Yousefi Zadeh, Zishuo Zhu, Xiaomeng Li +5
cs.CVcs.AIcs.CLarXiv:2608.14767v12026
CG-GLORE: A Conjugate Gradient-Based Global-Local Regularization Network for Sparse-View CT Reconstruction
Tran Xuan Hieu Le, Doanh C. Bui, Vu Trung Duong Le +5
cs.CVcs.AIarXiv:2608.15246v12026
DualMiT-Net: Local-Global Transformer-Convolutional Fusion for Breast Mass Segmentation in Mammographic Regions of Interest
Alibek Kamiluly, Milana Muratova, Yash Patel +1
cs.CVcs.AIcs.LGarXiv:2608.15019v12026
MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems
Penghao Yin, Haomin Wang, Qihong Tang +3
cs.CVcs.AIcs.MMarXiv:2608.15006v12026
ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval
Peng Chunyi, Xu Zhipeng, Yan Yukun +9
cs.CVcs.IRarXiv:2608.15698v12026
A Unified Backbone--Expert Framework with Relation-Token and Residual--Classifier Interfaces for Automatic Modulation Recognition
Zhixiang Deng, Houbiao Li, Zongyong Cui
cs.CVcs.AIarXiv:2608.15160v12026
MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling
Manwen Liao, Xinyu Lian, Jian Mao +11
cs.CVcs.GRarXiv:2608.14783v12026
MOSS-VL Technical Report
Pengyu Wang, Chenkun Tan, Shaojun Zhou +29
cs.CVarXiv:2608.15045v12026
HarnessEval-W: Agentifying the Evaluation of Visual Worlds
Weiliang Chen, Haowen Sun, Jun Gao +40
cs.CVarXiv:2608.16859v12026
A Metric Learning Reality Check
Kevin Musgrave, Serge Belongie, Ser-Nam Lim
cs.CVarXiv:2003.08505v32020
Summaries:한국어
GaussianSelector: Lightweight Human-Guided Object Selection in 3D Gaussian Splatting with Graph Optimization
Baihan Yang, Tiexin Li, Yuheng Liu +4
cs.CVarXiv:2608.01492v12026
ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow
Jin Cao, Zian Meng, Kaipeng Zhang
cs.CVcs.AIcs.LGarXiv:2607.28362v12026
HumanCLAW: Can Vision-Language Models Act Through a Body?
Li Siyao, Jiawei Gu, Shuai Liu +15
cs.CVcs.ROarXiv:2607.27180v22026
Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos
Sreyan Ghosh, Arushi Goel, Kaousheik Jayakumar +19
eess.AScs.CVarXiv:2607.16107v12026
GraphVid: Interactive Graph-Controllable Video Generation
Vedant Shah, Onkar Susladkar, Tushar Prakash +5
cs.CVcs.AIarXiv:2607.21580v12026
FilmBench: A Film-Grade Benchmark for Cinematic Video Generation
Shengyi Wang, Niantong Li, Guangzheng Hu +27
cs.CVcs.AIarXiv:2607.24241v22026
GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience
Sitong Gong, Caixin Kang, Tianyu Yan +7
cs.CVcs.AIarXiv:2608.02392v22026
PhiZero: A World Model Built Around Physical Language
Shuyao Shang, Yuqi Wang, Ruopeng Gao +4
cs.CVarXiv:2607.28624v12026
Latent-Identity Tuning in Text-to-Image Personalization Models
Daniel Garibi, Ronen Kamenetsky, Hadar Averbuch-Elor +2
cs.CVcs.GRarXiv:2607.11885v12026
Hierarchical Denoising For Multi-Step Visual Reasoning
Zezhong Qian, Xiaowei Chi, Chak-Wing Mak +9
cs.CVarXiv:2607.15278v12026
A Theory of Contrastive Learning with Natural Images
Antonio Torralba, Yair Weiss
cs.CVarXiv:2607.07470v12026
SiamJEPA: On the Role of Siamese Student Encoders in JEPA
Makoto Yamada
cs.CVstat.MLarXiv:2607.04044v22026
Representation Fréchet Loss for Visual Generation
Jiawei Yang, Zhengyang Geng, Xuan Ju +2
cs.CVarXiv:2604.28190v12026
Summaries:한국어
EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots
Heqing Yang, Yang Yi, Liyao Wang +8
cs.ROcs.CVarXiv:2607.02646v12026
MirrorPPR: Exemplar-Based Portrait Photo Retouching
Zhihong Liu, Zheng Li, Jiachun Jin +4
cs.CVarXiv:2606.29308v12026
SAM2Matting: Generalized Image and Video Matting
Ruiqi Shen, Guangquan Jie, Chang Liu +1
cs.CVarXiv:2606.27339v12026
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
Quanhao Li, Junqiu Yu, Kaixun Jiang +7
cs.LGcs.CVarXiv:2605.15055v12026
World Action Models: The Next Frontier in Embodied AI
Siyin Wang, Junhao Shi, Zhaoyang Fu +11
cs.ROcs.CLcs.CVarXiv:2605.12090v12026
WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation
Kaining Ying, Hengrui Hu, Siyu Ren +6
cs.CVarXiv:2605.25874v12026
D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
Dengyang Jiang, Xin Jin, Dongyang Liu +9
cs.CVarXiv:2605.05204v32026
UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors
Zhiwen Yang, Yang Zhou, Haowei Chen +4
cs.CVarXiv:2606.11131v12026
minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
Min Zhao, Hongzhou Zhu, Bokai Yan +9
cs.CVarXiv:2605.30263v12026
Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising
Jun Guo, Qiwei Li, Peiyan Li +7
cs.ROcs.AIcs.CVarXiv:2604.26694v22026
World Model for Robot Learning: A Comprehensive Survey
Bohan Hou, Gen Li, Jindou Jia +15
cs.ROcs.CVarXiv:2605.00080v12026
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Zelun Zhang, Hongen Liu, Suyin Liang +12
cs.CVarXiv:2606.03264v12026
DreamX-World 1.0: A General-Purpose Interactive World Model
DreamX Team, Yancheng Bai, Rui Chen +20
cs.CVarXiv:2606.16993v12026
SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
Rui Xu, Wenyue Chen, Jiepeng Wang +7
cs.CVcs.GRcs.MMarXiv:2411.18966v22024
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
Yuchao Gu, Guian Fang, Yuxin Jiang +4
cs.CVcs.AIarXiv:2605.13724v12026
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
GLM-V Team, :, Wenyi Hong +95
cs.CVarXiv:2604.26752v32026
Summaries:简体中文
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Haiwen Diao, Penghao Wu, Hanming Deng +55
cs.CVarXiv:2605.12500v12026
ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?
Yuyang Zhang, Wenyao Zhang, Zekun Qi +7
cs.CVcs.ROarXiv:2606.19531v12026
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
Yukang Chen, Luozhou Wang, Wei Huang +13
cs.CVcs.DCarXiv:2605.18739v22026
Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
Min Zhao, Hongzhou Zhu, Kaiwen Zheng +6
cs.CVarXiv:2605.15141v32026
Cosmos 3: Omnimodal World Models for Physical AI
NVIDIA, :, Aditi +293
cs.CVcs.AIcs.LGarXiv:2606.02800v42026
Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models
Glenn Jocher, Jing Qiu, Mengyu Liu +3
cs.CVcs.AIarXiv:2606.03748v12026
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
SingGuard Team
cs.CVcs.CLarXiv:2606.22873v32026
Mind the Heads: Topological Representation Alignment for Multimodal LLMs
Davide Caffagni, Alberto Compagnoni, Federico Melis +5
cs.CVcs.AIcs.CLarXiv:2606.23885v12026
Summaries:한국어

Computer Vision and Pattern Recognition

MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory

MBench: A Comprehensive Benchmark on Memory Capability for Video World Models

No One Knows the State of the Art in Geospatial Foundation Models

Next Forcing: Causal World Modeling with Multi-Chunk Prediction

SCAIL-2: Unifying Controlled Character Animation with End-to-End In-Context Conditioning

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop

iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework

AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing

NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents

WorldRover: A Scalable Synthetic Video Data Engine for World Exploration with Rich Annotations

A Plug-and-Play 2D Motion Interface for Real-World Motion Language Models

NARRATE: A Multimodal Real-World Australian Driving Dataset for Human-Centred Explanations in Automated Driving

CG-GLORE: A Conjugate Gradient-Based Global-Local Regularization Network for Sparse-View CT Reconstruction

DualMiT-Net: Local-Global Transformer-Convolutional Fusion for Breast Mass Segmentation in Mammographic Regions of Interest

MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems

ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval

A Unified Backbone--Expert Framework with Relation-Token and Residual--Classifier Interfaces for Automatic Modulation Recognition

MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling

MOSS-VL Technical Report

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

A Metric Learning Reality Check

GaussianSelector: Lightweight Human-Guided Object Selection in 3D Gaussian Splatting with Graph Optimization

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow

HumanCLAW: Can Vision-Language Models Act Through a Body?

Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos

GraphVid: Interactive Graph-Controllable Video Generation

FilmBench: A Film-Grade Benchmark for Cinematic Video Generation

GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience

PhiZero: A World Model Built Around Physical Language

Latent-Identity Tuning in Text-to-Image Personalization Models

Hierarchical Denoising For Multi-Step Visual Reasoning

A Theory of Contrastive Learning with Natural Images

SiamJEPA: On the Role of Siamese Student Encoders in JEPA

Representation Fréchet Loss for Visual Generation

EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots

MirrorPPR: Exemplar-Based Portrait Photo Retouching

SAM2Matting: Generalized Image and Video Matting

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models

World Action Models: The Next Frontier in Embodied AI

WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models

Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising

World Model for Robot Learning: A Comprehensive Survey

PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training

DreamX-World 1.0: A General-Purpose Interactive World Model

SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

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

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation

Cosmos 3: Omnimodal World Models for Physical AI

Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models

SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

Mind the Heads: Topological Representation Alignment for Multimodal LLMs