📚 文献库
Literature Library

Reconstructing Humans and Objects in Interaction using Large Reconstruction 模型 (Model)s

Reconstructing Humans and Objects in Interaction using Large Reconstruction Models

作者
Authors: Agniv Chatterjee | Georgios Pavlakos 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 47 📚 12

Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information

作者
Authors: Chanho Park | Daehyeon Choi | Jihyun Lee | Minhyuk... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 71 📚 12

UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City

作者
Authors: Tianjie Ju | Zheng Wu | Yueqing Sun | Yuhan Cui | ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 110 📚 15

Zero-WAM: In-Context World-Action 模型 (Model)ing from Human Videos for Open-Ended Task Generalization

Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization

作者
Authors: Jiaming Zhou | Qihang Zhang | Gangwei Xu | Cunxin ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 153 📚 7

Do Robotic World 模型 (Model)s Really Follow Actions? Diagnosing and Aligning Action-Conditioned Gener...

Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation...

作者
Authors: Sixiang Chen | Jiaming Liu | Jixian Wu | Yichen Gu... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 40 📚 29

EG-ARSA: An Expert-Grounded Open 模型 (Model) for Visual Road Safety Auditing in Low-Resource Settings

EG-ARSA: An Expert-Grounded Open Model for Visual Road Safety Auditing in Low-Resource Settings

作者
Authors: Md Thamed Bin Zaman Chowdhury | Moazzem Hossain 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 134 📚 30

OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs

作者
Authors: Xianyun Sun | Chaoyou Fu | Zhengye Zhang | Feiyang... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 33 📚 25

Swift-Image: Exploring the Performance Frontier of Compact Unified Image Generation 模型 (Model)s

Swift-Image: Exploring the Performance Frontier of Compact Unified Image Generation Models

作者
Authors: Taihang Hu | Zhao Wang | Zuan Gao | Tao Liu | Hao ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 171 📚 29

WithEveryone: Unified Planning and Identity Grounding for Group Image Generation

作者
Authors: Hengyuan Xu | Qixun Wang | Yiji Cheng | Miles Yang... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 131 📚 26

4DAnyone: Create Anyone in 4D from a Casual Monocular Video

作者
Authors: Yudong Jin | Tao Xie | Qihang Zhang | Zehong Shen ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 52 📚 9

Image-Guided Pavement Defect Recognition in GPR 数据 (Data) with novel 3D Deep 学习 (Learning) Architect...

Image-Guided Pavement Defect Recognition in GPR Data with novel 3D Deep Learning Architecture

作者
Authors: Yuandong Pan | Linjun Lu | Mudan Wang | Florian No... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 63 📚 26

From Corpora to Co-Evolving Capabilities: Capability-Centric 数据 (Data) Design for Generalist Image G...

From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Genera...

作者
Authors: Xingjian Wang | Zhao Wang | Taihang Hu | Jun Zheng... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 150 📚 25

Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition...

作者
Authors: Bingxin Xu | Yuzhang Shang | Emilio Ferrara 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 56 📚 14

CPI-Bench: A Comprehensive,Practical and Intelligent Benchmark for Real-World Image Editing

作者
Authors: Qinye Zhou | Jun Zheng | Yongchao Du | Yuan Wang |... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 66 📚 4

HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark

作者
Authors: Dairu Liu | Zekun Qi | Jiayu Zeng | Ruixi Yu | Yu ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 134 📚 7

V-RAE: Rethinking Video Latent Spaces for Generation

作者
Authors: Minghui Guo | Shengqiong Wu | Hao Fei 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 47 📚 5

StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization

作者
Authors: Yuyang Yin | Zixiang Li | Longxuan Deng | Hongkai ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 196 📚 2

AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss

作者
Authors: Mingju Gao | Jingkai Zhou | Kun Gai | Changqian Yu... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 31 📚 9

Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots

作者
Authors: Shravan Venkatraman | Omkar Thawakar | Ritesh Thaw... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 152 📚 3

SimWAM: A Simple World Action 模型 (Model) for End-to-End Autonomous Driving

SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

作者
Authors: Zongchuang Zhao | Xin Zhou | Tianyang Xu | Zhengya... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 72 📚 0