Kunchang Li
Scholar

Kunchang Li

Google Scholar ID: D4tLSbsAAAAJ
ByteDance Seed
Video UnderstandingMultimodal Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
7,997
 
H-index
25
 
i10-index
30
 
Publications
20
 
Co-authors
22
list available
Contact
CVOpen ↗TwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
12 items
UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
2026
Cited
0
VQ-VA World: Towards High-Quality Visual Question-Visual Answering
2025
Cited
0
LightBagel: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation
2025
Cited
0
Super Encoding Network: Recursive Association of Multi-Modal Encoders for Video Understanding
2025
Cited
0
Emerging Properties in Unified Multimodal Pretraining
2025
Cited
0
Make Your Training Flexible: Towards Deployment-Efficient Video Models
2025
Cited
0
V-Stylist: Video Stylization via Collaboration and Reflection of MLLM Agents
2025
Cited
0
TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision
2025
Cited
0
Resume (English only)
Co-authors
22 total
Yu Qiao
Yu Qiao
Professor of Shanghai AI Laboratory; Shenzhen Institutes of Advanced Technology, CAS
Yali Wang
Yali Wang
Professor, Shenzhen Institutes of Advanced Technology，Chinese Academy of Sciences
Limin Wang
Limin Wang
Nanjing University
Yi Wang
Yi Wang
Shanghai AI Laboratory
Yinan He
Yinan He
Shanghai Al Laboratory
Yizhuo Li
Yizhuo Li
The University of Hong Kong
Guo Chen
Guo Chen
Nanjing University
Xinhao Li
Xinhao Li
Nanjing University