Keming Wu
Scholar

Keming Wu

Google Scholar ID: cOzwZBMAAAAJ
Ph.D. Student, Tsinghua University
Computer VisionVision Language ModelsGenerative AI
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
31
 
H-index
4
 
i10-index
1
 
Publications
11
 
Co-authors
3
list available
Contact
No contact links provided.
Publications
17 items
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
2026
Cited
0
TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
2026
Cited
0
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
2026
Cited
0
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
2026
Cited
0
PRISM: Pre-alignment via Black-box On-policy Distillation for Multimodal Reinforcement Learning
2026
Cited
0
ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks
2026
Cited
0
DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation
2026
Cited
3
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
2025
Cited
0
Resume (English only)
Co-authors
3 total
Yuhui Yuan
Yuhui Yuan
Canva CORE, ex-Microsoft Research Asia
Guoqi Li
Guoqi Li
Professor, Institue of Automation，Chinese Academy of Sciences，Previously Tsinghua University
Wenhu Chen
Wenhu Chen
Assistant Professor at University of Waterloo