Scholar
Chuofan Ma
Google Scholar ID: hgKtgWAAAAAJ
PhD student of Electrical and Electronic Engineering, The University of Hong Kong
Citations & Impact
Citations
255
H-index
7
i10-index
6
Publications
9
Co-authors
5
list available
Publications
Cited
6
Resume (English only)
Academic Achievements
- UniTok: A Unified Tokenizer for Visual Generation and Understanding, NeurIPS (Spotlight), 2025
- Liquid: Language Models are Scalable and Unified Multi-modal Generators, arxiv preprint, 2024
- Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation, NeurIPS, 2025
- Learning from Neighbors: Category Extrapolation for Long-Tail Learning, CVPR, 2025
- Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models, ECCV, 2024
- CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection, NeurIPS, 2023
- Recognize Any Regions, NeurIPS, 2024
- EGC: Image Generation and Classification via a Diffusion Energy-Based Model, ICCV, 2023
- Rethinking Resolution in the Context of Efficient Video Recognition, NeurIPS, 2022
Research Experience
- Involved in multiple research projects including UniTok, Liquid, etc.
Education
- Bachelor's degree in Computer Science from The University of Hong Kong (HKU); currently a Ph.D. student at CVMI Lab, HKU, supervised by Prof. Xiaojuan Qi.
Background
- Primary research interest lies in open-world visual intelligence and multi-modal foundation models. Open to collaboration opportunities.
Miscellany
- Website template from Jon Barron.
