📚 文献库
Literature Library

From Pixels to Actions - Towards Native Vision-Language-Action Policies

作者
Authors: Weichen Fan | Haiwen Diao | Penghao Wu | Siyuan Hu... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 136 📚 30

DreamX: Video Diffusion 模型 (Model) is a Universal Latent Action Learner

DreamX: Video Diffusion Model is a Universal Latent Action Learner

作者
Authors: Jisoo Kim | Chaehyun Kim | Junsu Kim | Jiho Park |... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 58 📚 9

Pixel: A Co-Designed Full-Stack Robot System for 学习 (Learning) General-Purpose Mobile Manipulation

Pixel: A Co-Designed Full-Stack Robot System for Learning General-Purpose Mobile Manipulation

作者
Authors: Tony Tao | Jason Jingzhou Liu | Ruslan Salakhutdin... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 82 📚 9

GazeRIB: Systematic Evaluation of Multi-Reader Gaze-Guided Chest X-ray 学习 (Learning)

GazeRIB: Systematic Evaluation of Multi-Reader Gaze-Guided Chest X-ray Learning

作者
Authors: Nattakorn Kittisut | Roy M. Gabriel | Marly van As... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 43 📚 20

Micro-Edits: Computational Support for Fine-Scale Edits in Film

作者
Authors: Nhan Tran | Hijung Valentina Shin | Abe Davis | Ma... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 117 📚 10

Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals?

作者
Authors: Jialv Zou | Xiaotong Li | Zhengrong Yue | Xu Huang... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 50 📚 24

ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning

作者
Authors: Chaehyun Kim | Chi-Pin Huang | Jisoo Kim | Min-Hun... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 200 📚 2

VibeVideoBench:Evaluating Multimodal Agents on Code-Driven Video Generation

作者
Authors: Muxi Diao | Wenbin Xu | Lele Yang | Xuyang Ma | Yu... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 113 📚 9

SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied 学习...

SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Le...

作者
Authors: Yuhan Liu | Lianhui Qin | Shenji Wan 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 155 📚 29

Reading, Writing, Sharing, and Interacting with the World through Video

作者
Authors: Shengqiong Wu | Meng Luo | Bobo Li | Ziwei Liu | S... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 20 📚 7

A Unified Framework for Image-to-3D Part Generation via Variable Granularity

作者
Authors: Qiwen Gu | Xin Zhou | Xiwu Chen | Zhongyang Zhu | ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 129 📚 8

Rethinking Video Autoencoders for Interactive World 模型 (Model)s

Rethinking Video Autoencoders for Interactive World Models

作者
Authors: Adrien Ramanana Rahary | Yutong Bai | Nicolas Dufo... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 116 📚 3

AEON: Unifying Video and 3D World 模型 (Model)s

AEON: Unifying Video and 3D World Models

作者
Authors: Weiqi Zhang | Wenyuan Zhang | Yu-Shen Liu | Junshe... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 102 📚 4

Can It Actually Work? Synthesizing Functional CAD Mechanisms

作者
Authors: Wenqian Zhang | Yangyi Huang | Zigeng Xu | Weiyang... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 196 📚 26

学习 (Learning) to Correct Geometry in Generated Videos

Learning to Correct Geometry in Generated Videos

作者
Authors: Weijie Lyu | Tiancheng Shen | Jason Li | Yujing Wa... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 27 📚 2

SoftCache: Adaptive Step Size Caching for Diffusion Transformers

作者
Authors: Shimon Malnick | Nadav Orenstein | Ohad Fried | Sh... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 165 📚 20

Which Tokens to Merge? Diffusion Dynamics for Efficient Image Generation

作者
Authors: SeungJu Cha | Ye-Chan Kim | HyunGee Kim | Sungho K... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 128 📚 5

Gen4P: Video Generators are 4D Perceivers

作者
Authors: Yitong Xia | Zeren Jiang | Chuanxia Zheng 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 161 📚 7

Can 学习 (Learning) to Answer Spatial Questions Improve Novel-View Generation?

Can Learning to Answer Spatial Questions Improve Novel-View Generation?

作者
Authors: Jahyeok Koo | Hyeonseo Yu | Seungho Jang | Jaewoo ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 106 📚 15

LoopWAM: Closed-Loop Generalist Policy Improvement from Deployment Rollouts

作者
Authors: Wenxuan Guo | Yingping Liang | Zhaoguo Wang | Ziyu... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 71 📚 15