Handong Li
Scholar

Handong Li

Google Scholar ID: -LnWwgIAAAAJ
Institute of Automation, Chinese Academy of Sciences
cross-modality pretraining
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
279
 
H-index
3
 
i10-index
3
 
Publications
6
 
Co-authors
10
list available
Contact
GitHubOpen ↗
Publications
2 items
AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding
2026
Cited
0
Thinking in Streaming Video
2026
Cited
0
Resume (English only)
Academic Achievements
  • "Breaking the Encoder Barrier for Seamless Video-Language Understanding", CoRR 2025
  • "Scaling Omni-modal Pretraining with Multimodal Context", ICLR 2025 (Withdrawn)
  • "Explore the Limits of Omni-modal Pretraining at Scale", CoRR 2024
  • "COSA: Concatenated Sample Pretrained Vision-Language Foundation Model", ICLR 2024
  • "VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset", NeurIPS 2023
  • "Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner", ACM Multimedia 2023
Co-authors
10 total
Jing Liu 刘静
Jing Liu 刘静
Professor in Institute of Automation of the Chinese Academy Sciences (CASIA)
Co-author 2
Co-author 2
mingzhen sun
mingzhen sun
CAS
Co-author 4
Co-author 4
Zijia Zhao
Zijia Zhao
Institute of Automation, Chinese Academy Sciences (CASIA)
Xingjian He
Xingjian He
Institute of Automation of the Chinese Academy Sciences (CASIA)
Xiangyu Yue
Xiangyu Yue
The Chinese University of Hong Kong / UC Berkeley / Stanford University / NJU
Longteng Guo 郭龙腾
Longteng Guo 郭龙腾
Associate Professor, Institute of Automation of the Chinese Academy Sciences (CASIA)