Scholar
Ziyuan Huang
Google Scholar ID: A9D-disAAAAJ
Ant Group
Multimodal LLM
Visual Generation
Unified Model
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
2,578
H-index
20
i10-index
29
Publications
20
Co-authors
15
list available
Contact
Email
ziyuan.huang@u.nus.edu
Twitter
Open ↗
GitHub
Open ↗
Publications
2 items
TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders
2026
Cited
0
StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision
2026
Cited
0
Resume (English only)
Academic Achievements
2024, 'Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight', Tech report.
2024, 'Towards Better Vision-Inspired Vision-Language Models', CVPR.
2024, 'Res-tuning: A flexible and efficient tuning paradigm via unbinding tuner from backbone', NeurIPS.
2023, 'Towards Real-World Visual Tracking with Temporal Contexts', TPAMI.
2023, 'Temporally-Adaptive Models for Efficient Video Understanding', Tech report.
Co-authors
15 total
Shiwei Zhang
Alibaba Group
Changhong Fu (C. Fu)
Associate Professor - Tongji University, Shanghai, China
Zhiwu Qing
Huazhong University of Science and Technology
Yiming Li
Research Scientist, NVIDIA
Marcelo Ang
National University of Singapore
Ziwei Liu
Associate Professor, Nanyang Technological University
Liang Pan
Shanghai AI Lab
Ming Yang
Facebook AI Research - NEC Laboratories America
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up