Hao Chen
Scholar

Hao Chen

Google Scholar ID: QMuIRLYAAAAJ
ByteDance
video processingrepresentation learningcomputer vision
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,245
 
H-index
12
 
i10-index
12
 
Publications
18
 
Co-authors
0
 
Contact
Emailhaochen.umd@gmail.comCVOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
4 items
ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations
2026
Cited
0
Continuous Adversarial Flow Models
2026
Cited
0
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
2026
Cited
1
UniWeTok: An Unified Binary Tokenizer with Codebook Size $\mathit{2^{128}}$ for Unified Multimodal Large Language Model
2026
Cited
0
Resume
Academic Achievements
  • - Published multiple papers, such as 'NeRV: Neural Representations for Videos' (NeurIPS 2021), 'HNeRV: A Hybrid Neural Representation for Videos' (CVPR 2023), etc.
  • - Involved in various projects, such as 'Growing Visual Generative Capacity for Pre-Trained MLLMs', 'Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model', etc.
Research Experience
  • - Research Scientist at ByteDance
  • - Postdoctoral Researcher at Meta
Education
  • - Ph.D., Computer Science, University of Maryland, College Park, Advisor: Prof. Abhinav Shrivastava
  • - Master's, Pattern Recognition & Intelligent Systems, Huazhong University of Science & Technology (HUST), Advisor: Prof. Guoyou Wang
  • - Bachelor's, School of Optical and Electronic Information, HUST
Background
  • Currently a Research Scientist at ByteDance. Previously, worked as a Postdoctoral Researcher at Meta. Research interests include generative models and neural representations.