Scholar
Zhengyuan Yang
Google Scholar ID: rP02ve8AAAAJ
Principal Researcher, Microsoft
Computer Vision
Multimedia
Multimodal
Post-Training
Agentic RL
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
9,960
H-index
38
i10-index
63
Publications
20
Co-authors
16
list available
Publications
49 items
VideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents
2026
Cited
0
Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation
2026
Cited
0
Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors
2026
Cited
0
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
2026
Cited
0
3D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis
2026
Cited
0
Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering
2026
Cited
0
Planning with the Views via Scene Self-Exploration
2026
Cited
0
SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects
2026
Cited
0
Load more
Co-authors
12 total
Lijuan Wang
Microsoft GenAI
Linjie Li
Microsoft
Zicheng Liu
Microsoft
Kevin Lin
Microsoft
Zhe Gan
Research Scientist, Apple
Ce Liu
AI Research Scientist Director, Meta GenAI; IEEE Fellow
Jianwei Yang
Research Scientist, Meta SuperIntelligence Lab
Weihao Yu
ByteDance Seed, United States; National University of Singapore (NUS)
