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)

18,421 to 18,480 of 18,817

MIRROR: Multimodal Intelligent Radiology Reasoning and Observation Reporter
Vignesh Nagarajan, Sriram Venkatapathy
cs.CVcs.AIcs.LGarXiv:2608.16709v12026
A cross-modal generative model for incomplete and degraded prostate MRI with multicentre clinical validation
Siyuan Ma, Liang He, Mengying Zhu +14
eess.IVcs.AIcs.CVarXiv:2608.16233v12026
Picking the Right Image to Classify: Reliable-Input Selection in Teledermatology
Fabian Gröger, Marco Weishaupt, Philippe Gottfrois +6
cs.CVcs.AIarXiv:2608.16198v12026
DriveCache: Action-Aware Caching for Driving World Model Inference
Jianchun Yang, Jian Liang, Xianda Guo +5
cs.AIcs.CVarXiv:2608.16354v12026
X$^2$Localizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localization
Zichao Zeng, Weijia Fan, Yufan Chen +7
cs.CVcs.AIcs.ROarXiv:2608.16658v12026
Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning
Xiaoyu Zhu, Xinke Deng, Suresh Taddewadikar +4
cs.CVcs.AIcs.CLarXiv:2608.15869v12026
Turning spectra into images improves plant trait retrieval with 2D-CNNs
Javier Lopatin, Teja Kattenborn, Eya Cherif +1
cs.CVcs.LGarXiv:2608.16661v12026
OceanDepths: A Global Dataset of Paired Subsurface and Surface Ocean Observations
Simon Donike, Ruben Cartuyvels, Antonino Ian Ferola +3
cs.LGcs.AIcs.CVarXiv:2608.16373v22026
FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion
Yu Lu, Junjie Yang, Piotr Koniusz +2
cs.CVarXiv:2606.10671v22026
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang +47
cs.AIcs.CLcs.CRarXiv:2605.29801v12026
JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence
Dingyu Yao, Junhao Zhou, Chenxu Yang +12
cs.CVcs.AIarXiv:2606.14777v12026
MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism
Cong Chen, Guo Gan, Kaixiang Ji +7
cs.CVcs.AIcs.CLarXiv:2606.07512v22026
CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
Yihao Meng, Zichen Liu, Hao Ouyang +11
cs.CVarXiv:2605.12496v12026
PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World
Changpeng Wang, Xin Lin, Junhan Liu +5
cs.CVcs.AIarXiv:2605.13169v22026
IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation
Shijie Lian, Bin Yu, Xiaopeng Lin +8
cs.ROcs.AIcs.CLarXiv:2605.14712v22026
VTInstructor: Visual Trajectory Prompting for Navigation Instruction Generation in Continuous Environments
Haolin Yang, Yuxing Long, Zihan Yang +1
cs.ROcs.AIcs.CLarXiv:2608.15284v12026
PaSTel: Anchoring Histology in Spatial Transcriptomics via Multi-Scale Hierarchical Bio-Prior Contrastive Pretraining
Azim Dehghani Amirabad, Junchao Zhu, Pushpak Pati +3
cs.CVcs.AIarXiv:2608.14924v12026
FZ-VLM: A Two Stage Florence-Zephyr Vision Language Model Framework for Pulmonary Nodule Characterization and Clinical Decision Making
Pramit Dutta, Jenita Manokaran, Richa Mittal +2
cs.CVcs.AIarXiv:2608.15004v12026
PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis
Jinrang Jia, Zhenjia Li, Yijiang Hu +1
cs.CVarXiv:2605.17916v22026
ActWorld: From Explorable to Interactive World Model via Action-Aware Memory
Zhexiao Xiong, Yizhi Song, Hao Kang +11
cs.CVarXiv:2606.17730v12026
You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences
Ninad Daithankar, Alexi Gladstone, Yann LeCun +1
cs.CVcs.AIcs.LGarXiv:2606.15956v12026
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
AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents
Pan Wang, Yihao Hu, Xiujin Liu +3
cs.CVarXiv:2605.17933v12026
SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models
Zizhao Tong, Yeying Jin, Hongfeng Lai +11
cs.CVarXiv:2605.23345v22026
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
Rui Yang, Qianhui Wu, Yuxi Chen +7
cs.LGcs.AIcs.CLarXiv:2606.02031v22026
EarlyTom: Early Token Compression Completes Fast Video Understanding
Hesong Wang, Xin Jin, Lu Lu +4
cs.CVarXiv:2605.30010v12026
ActiveMimic: Egocentric Video Pretraining with Active Perception
Xingyao Lin, Guojin Zhong, Tianyi Lu +4
cs.ROcs.CVarXiv:2606.06194v12026
RepWAM: World Action Modeling with Representation Visual-Action Tokenizers
Junke Wang, Qihang Zhang, Shuai Yang +5
cs.CVarXiv:2606.13674v22026
Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream Environments
Xiaoyu Yang, En Yu, Wei Duan +1
cs.CVcs.AIcs.LGarXiv:2510.04142v32025
SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation
Tianfei Ren, Zhipeng Yan, Yiming Zhao +13
cs.CVcs.AIarXiv:2605.08043v12026
Current World Models Lack a Persistent State Core
Jinpeng Lu, Dexu Zhu, Haoyuan Shi +8
cs.CVarXiv:2606.20545v12026
Aurora: Unified Video Editing with a Tool-Using Agent
Yongsheng Yu, Ziyun Zeng, Zhiyuan Xiao +4
cs.CVarXiv:2605.18748v12026
Leveraging Verifier-Based Reinforcement Learning in Image Editing
Hanzhong Guo, Jie Wu, Jie Liu +6
cs.CVarXiv:2604.27505v22026
SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection
Tiancheng Zhang, Mengmeng Wang, Yan Gao +3
cs.CVcs.AIarXiv:2608.16338v12026
Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining
Wenyao Zhang, Bozhou Zhang, Zekun Qi +3
cs.ROcs.CVarXiv:2604.16391v12026
FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow Matching
Danilo Danese, Angela Lombardi, Matteo Attimonelli +2
cs.CVarXiv:2601.05212v22026
MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation
Kaixing Yang, Jiashu Zhu, Xulong Tang +7
cs.CVarXiv:2512.18181v32025
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
Fangfu Liu, Kai He, Tianchang Shen +7
cs.CVarXiv:2605.28816v12026
Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
Yifan Wang, Tong He
cs.CVarXiv:2605.15182v12026
MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents
Ziyun Zeng, Hang Hua, Bocheng Zou +3
cs.CVarXiv:2605.18652v12026
One-Forcing: Towards Stable One-Step Autoregressive Video Generation
Jiaqi Feng, Justin Cui, Yuanhao Ban +1
cs.CVcs.AIarXiv:2605.23458v12026
GenClaw: Code-Driven Agentic Image Generation
Junyan Ye, Jun He, Zilong Huang +4
cs.CVarXiv:2605.30248v22026
Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation
Jie Zhang, Xiaoyue Chen, Anzhe Chen +36
cs.CVarXiv:2606.17030v32026
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data
Jiwen Liu, Shujuan Li, Zhixue Fang +8
cs.CVcs.AIarXiv:2606.13432v12026
From Generalist to Specialist: A Context-Fusion Framework for Endoscopic Polyp Reporting with a Frozen VLM
Ruijie Yang, Yan Zhu, Peiyao Fu +7
cs.AIcs.CVarXiv:2608.15580v12026
Audio-Visual Segmentation via Depth-Guided Collaborative Modeling
Zhaojin Fu, Yuyang Hong, Qi Yang +4
cs.CVcs.AIarXiv:2608.16285v12026
RigidBench: Evaluating Rigid-Body Physics in Video Generation Models
Swarnim Jain, Shangzhe Wu
cs.CVcs.LGarXiv:2608.15555v12026
Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts
Ziang Wu, Peng Jin, Qishen Yin +4
cs.CVcs.AIarXiv:2608.00574v12026
Representation Forcing for Bottleneck-Free Unified Multimodal Models
Yuqing Wang, Zhijie Lin, Ceyuan Yang +10
cs.CVarXiv:2605.31604v42026
Light-WAM: Efficient World Action Models with State-Fusion Action Decoding
Ziang Li, Dongzhou Cheng, Yibin Wang +5
cs.CVarXiv:2606.08242v12026
AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting
Yuyuan Liu, Yuanhong Chen, Chong Wang +6
cs.CVarXiv:2506.01015v22025
PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
Yunhan Yang, Chunshi Wang, Junliang Ye +7
cs.CVarXiv:2605.05163v12026
Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
NVIDIA, :, Amala Sanjay Deshmukh +216
cs.LGcs.AIcs.CVarXiv:2604.24954v22026
HumanNet: Scaling Human-centric Video Learning to One Million Hours
Yufan Deng, Daquan Zhou
cs.CVcs.ROarXiv:2605.06747v12026
L2P: Unlocking Latent Potential for Pixel Generation
Zhennan Chen, Junwei Zhu, Xu Chen +7
cs.CVcs.AIarXiv:2605.12013v12026
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
Weijie Wang, Xiaoxuan He, Youping Gu +9
cs.CVarXiv:2604.24764v42026
WALL-WM: Carving World Action Modeling at the Event Joints
Shalfun Li, Victor Yao, Charles Yang +28
cs.ROcs.CVarXiv:2606.01955v12026
ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning
Yiming Zhang, Jiacheng Chen, Jiaqi Tan +3
cs.CVarXiv:2604.24300v22026
Qwen-Image-2.0 Technical Report
Bing Zhao, Chenfei Wu, Deqing Li +72
cs.CVarXiv:2605.10730v12026
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction
Jianing Zhang, Chenhao Zheng, Yajun Yang +10
cs.CVarXiv:2606.18558v12026

Computer Vision and Pattern Recognition

MIRROR: Multimodal Intelligent Radiology Reasoning and Observation Reporter

A cross-modal generative model for incomplete and degraded prostate MRI with multicentre clinical validation

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

DriveCache: Action-Aware Caching for Driving World Model Inference

X$^2$Localizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localization

Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning

Turning spectra into images improves plant trait retrieval with 2D-CNNs

OceanDepths: A Global Dataset of Paired Subsurface and Surface Ocean Observations

FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence

MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism

CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives

PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World

IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation

VTInstructor: Visual Trajectory Prompting for Navigation Instruction Generation in Continuous Environments

PaSTel: Anchoring Histology in Spatial Transcriptomics via Multi-Scale Hierarchical Bio-Prior Contrastive Pretraining

FZ-VLM: A Two Stage Florence-Zephyr Vision Language Model Framework for Pulmonary Nodule Characterization and Clinical Decision Making

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

ActWorld: From Explorable to Interactive World Model via Action-Aware Memory

You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences

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

AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents

SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

EarlyTom: Early Token Compression Completes Fast Video Understanding

ActiveMimic: Egocentric Video Pretraining with Active Perception

RepWAM: World Action Modeling with Representation Visual-Action Tokenizers

Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream Environments

SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation

Current World Models Lack a Persistent State Core

Aurora: Unified Video Editing with a Tool-Using Agent

Leveraging Verifier-Based Reinforcement Learning in Image Editing

SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection

Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining

FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow Matching

MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video

MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents

One-Forcing: Towards Stable One-Step Autoregressive Video Generation

GenClaw: Code-Driven Agentic Image Generation

Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation

OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data

From Generalist to Specialist: A Context-Fusion Framework for Endoscopic Polyp Reporting with a Frozen VLM

Audio-Visual Segmentation via Depth-Guided Collaborative Modeling

RigidBench: Evaluating Rigid-Body Physics in Video Generation Models

Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts

Representation Forcing for Bottleneck-Free Unified Multimodal Models

Light-WAM: Efficient World Action Models with State-Fusion Action Decoding

AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting

PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World

Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence

HumanNet: Scaling Human-centric Video Learning to One Million Hours

L2P: Unlocking Latent Potential for Pixel Generation

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

WALL-WM: Carving World Action Modeling at the Event Joints

ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning

Qwen-Image-2.0 Technical Report

MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction