MS
Mike Zheng Shou
cs.CVcs.AIcs.ROcs.CLcs.MMcs.LGcs.HCcs.CRcs.GRcs.MA
On Valency
published · living versionsW_yspzx7a9·v1 · currentpublished
Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement
with Liaoyuan Fan, Yuhao Zheng, Dongxing Mao, Hangyu Ran +16
1 version
Preprints & journals
205 papers in the corpus · 2020–2026Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use2610.30108v1 · Yanzhe Chen, Ziyi Yang, Jifeng Zhu et al.2026 · 0 citationsarXivon Valency
SolarRenderer: Few-Step Generative Reference Rendering2610.28630v1 · Guian Fang, Shengju Qian, Dongyue Lu et al.2026 · 0 citationsarXivon Valency
Player-1: Learning to Play from Synthetic Experience2610.20584v1 · Mingyu Ouyang, Yiran Wang, Siyuan Hu et al.2026 · 0 citationsarXiv
Orbia: Do Generated Videos Form a Consistent 3D World?2610.20693v2 · Dongyue Lu, Guian Fang, Hur Lim et al.2026 · 0 citationsarXiv
Language-4D Cross-Boosting for Generalized Zero-Shot 6DoF Tracking and 3D Reconstruction.42424203 · Sun, Jingtao, Wang, Yaonan, Zhao, Jiawen et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(10):13496-13514
PaperDoctor: Evidence-Grounded and Actionable Feedback for Scientific Papers in Progress2609.16995v1 · Kevin Qinghong Lin, Siyuan Hu, Pan Lu et al.2026 · 0 citationsarXiv
Show-Harness: Just a VLM Agent Can Play Robots2609.10522v1 · Yanzhe Chen, Zechen Bai, Zhijun Cao et al.2026 · 0 citationsarXiv
PAI-Actor: Cinematic Multi-Character Replacement in Dynamic Scenes2609.05918v1 · Bangxun Tang, Heyuan Gao, Yiren Song et al.2026 · 0 citationsarXiv
Where Success Breaks: Failure-Boundary Learning for Robust Vision-Language-Action Models2609.06114v3 · Yanzhe Chen, Zhijun Cao, Mike Zheng Shou2026 · 0 citationsarXiv
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models2609.02886v1 · Junchao Huang, Guian Fang, Shengju Qian et al.2026 · 0 citationsarXiv
Learning Long-Form Movie Prior via Large Language Models.42672025 · Xie, Jinheng, Feng, Jiajun, Shou, Mike Zheng2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;PP
A Collaborative Multi-Modality Interaction for VLA-based End-to-End Autonomous Driving2608.20890v1 · Jingtao Sun, Xiaohai He, Yike Zhang et al.2026 · 0 citationsarXiv
StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs2608.13416v4 · Joya Chen, Zeyun Zhong, Mike Zheng Shou2026 · 0 citationsarXiv
MANGO-Grasp: Mahalanobis Fields over Geometry-Oriented 3D Gaussians for Cross-Embodiment Dexterous Grasping2608.02014v2 · Heng Zhang, Kevin Yuchen Ma, Mike Zheng Shou et al.2026 · 0 citationsarXiv
Hermite Curves as Trajectory Priors for Vision-Language-Action Models2608.01265v2 · Qi Lv, Jianming Xing, Zhao Yang et al.2026 · 0 citationsarXiv
Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning2607.02963v1 · Wenzheng Zeng, Siyi Jiao, Chen Gao et al.2026 · 0 citationsarXiv
ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents2606.31392v1 · Binjie Zhang, Mike Zheng Shou2026 · 0 citationsarXiv
A Survey on Foundations and Frontiers of Multimodal Agentic Frameworks: Techniques and Applications2608.20379v1 · Neel Mokaria, Rishie Raj, Dheeraj Baiju et al.2026 · 0 citationsarXiv
Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos2606.24448v1 · Danze Chen, Yanzhe Chen, Qiming Huang et al.2026 · 0 citationsarXiv
ActionMap: Robot Policy Learning via Voxel Action Heatmap2606.06904v2 · Pei Yang, Hai Ci, Yanzhe Chen et al.2026 · 0 citationsarXiv
Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation?2606.04811v2 · Rui Zhao, Kaiming Yang, Jifeng Zhu et al.2026 · 0 citationsarXiv
Demo2Tutorial: From Human Experience to Multimodal Software Tutorials2606.03951v1 · Zechen Bai, Zhiheng Chen, Yiqi Lin et al.2026 · 0 citationsarXiv
PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion2606.01399v1 · Heyuan Gao, Bangxun Tang, Yiren Song et al.2026 · 0 citationsarXiv
SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution2605.19319v1 · Yiren Song, Yihan Wang, Xiyao Deng et al.2026 · 0 citationsarXiv
VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformers2605.17312v1 · Yiren Song, Wangzi Yao, Haofan Wang et al.2026 · 0 citationsarXiv
Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration2605.17423v1 · Yiren Song, Huilin Zhong, Kevin Qinghong Lin et al.2026 · 0 citationsarXiv
StreamingEffect: Real-Time Human-Centric Video Effect Generation2605.17019v1 · Yiren Song, Cheng Liu, Yuxin Jiang et al.2026 · 0 citationsarXiv
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation2605.13724v1 · Yuchao Gu, Guian Fang, Yuxin Jiang et al.2026 · 0 citationsarXiv
OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation2605.12038v1 · Yiren Song, Xiyao Deng, Pei Yang et al.2026 · 0 citationsarXiv
World Action Models: The Next Frontier in Embodied AI2605.12090v1 · Siyin Wang, Junhao Shi, Zhaoyang Fu et al.2026 · 0 citationsarXiv
Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation2605.07381v1 · Yanzhe Chen, Kevin Yuchen Ma, Qi Lv et al.2026 · 0 citationsarXiv
Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimation.41442298 · Sun, Jingtao, Wang, Yaonan, Feng, Mingtao et al.2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(5):5113-5130
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond2604.22748v3 · Meng Chu, Xuan Billy Zhang, Kevin Qinghong Lin et al.2026 · 0 citationsarXiv
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents2604.07429v1 · Mingyu Ouyang, Siyuan Hu, Kevin Qinghong Lin et al.2026 · 0 citationsarXiv
UENR-600K: A Large-Scale Physically Grounded Dataset for Nighttime Video Deraining2604.04402v1 · Pei Yang, Hai Ci, Beibei Lin et al.2026 · 0 citationsarXiv
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models2604.04707v2 · DataFlow Team, Bohan Zeng, Daili Hua et al.2026 · 0 citationsarXiv
SAM-I2V++: Efficiently Upgrading SAM for Promptable Video Segmentation.41452691 · Mei, Haiyang, Zhang, Pengyu, Shou, Mike Zheng2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(4):4878-4895
P-Flow: Prompting Visual Effects Generation2603.22091v1 · Rui Zhao, Mike Zheng Shou2026 · 0 citationsarXiv
Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance2603.02175v4 · Yiqi Lin, Guoqiang Liang, Ziyun Zeng et al.2026 · 0 citationsarXiv
Semantic-Contact Fields for Category-Level Generalizable Tactile Tool Manipulation2602.13833v2 · Kevin Yuchen Ma, Heng Zhang, Weisi Lin et al.2026 · 0 citationsarXiv
Olaf-World: Orienting Latent Actions for Video World Modeling2602.10104v2 · Yuxin Jiang, Yuchao Gu, Ivor W. Tsang et al.2026 · 0 citationsarXiv
World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy2602.06508v2 · Xiaokang Liu, Zechen Bai, Hai Ci et al.2026 · 0 citationsarXiv
ShowUI-Aloha: Human-Taught GUI Agent2601.07181v1 · Yichun Zhang, Xiangwu Guo, Yauhong Goh et al.2026 · 0 citationsarXiv
FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection2601.03928v1 · Mingyu Ouyang, Kevin Qinghong Lin, Mike Zheng Shou et al.2026 · 0 citationsarXiv
ShowUI-: Flow-based Generative Models as GUI Dexterous Hands2512.24965v1 · Siyuan Hu, Kevin Qinghong Lin, Mike Zheng Shou2025 · 0 citationsarXiv
Factorized Learning for Temporally Grounded Video-Language Models2512.24097v1 · Wenzheng Zeng, Difei Gao, Mike Zheng Shou et al.2025 · 2 citationsarXiv
Mitty: Diffusion-based Human-to-Robot Video Generation2512.17253v1 · Yiren Song, Cheng Liu, Weijia Mao et al.2025 · 0 citationsarXiv
EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models2512.14666v1 · Zechen Bai, Chen Gao, Mike Zheng Shou2025 · 0 citationsarXiv
OmniPSD: Layered PSD Generation with Diffusion Transformer2512.09247v1 · Cheng Liu, Yiren Song, Haofan Wang et al.2025 · 0 citationsarXiv
H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos2512.09406v1 · Hai Ci, Xiaokang Liu, Pei Yang et al.2025 · 0 citationsarXiv
Career total: 247 works. 205 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.