Kai Liu
Scholar

Kai Liu

Google Scholar ID: 3B1rM1wAAAAJ
Zhejiang University
open-world learningvision-language learninglarge language models
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
284
 
H-index
6
 
i10-index
4
 
Publications
11
 
Co-authors
0
 
Contact
Emailkail@zju.edu.cnGitHubOpen ↗
Publications
2 items
JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation
2026
Cited
0
AUHead: Realistic Emotional Talking Head Generation via Action Units Control
2026
Cited
0
Resume
Academic Achievements
  • First-author papers accepted at top-tier conferences and journals
  • One paper accepted as Spotlight at NeurIPS’25 (2025)
  • One paper accepted at ACL’25 main conference (2025)
  • One paper accepted by IEEE TIP (Nov 2024)
  • Three papers accepted at NeurIPS’24 (Oct 2024)
  • Notable works include 'JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation' (NeurIPS 2025 Spotlight), 'Javisdit: Joint audio-video diffusion transformer with hierarchical spatio-temporal prior synchronization' (arXiv 2025), and 'Structure-aware Domain Knowledge Injection for Large Language Models' (ACL 2025)