Scholar
Hangjie Yuan
Google Scholar ID: jQ3bFDMAAAAJ
Alibaba DAMO | ZJU | MMLab@NTU
Citations & Impact
Citations
2,294
H-index
16
i10-index
20
Publications
20
Co-authors
22
list available
Publications
Cited
0
Resume (English only)
Academic Achievements
- - Published Papers: UniLumos and VideoMAR accepted to NeurIPS 2025; SAMora, DreamRelation, and FreeScale accepted to ICCV 2025; Dual-Arch and ZeroFlow accepted to ICML 2025; FreeMask and AeroGTO accepted to AAAI 2025; EvolveDirector and C-Flat accepted to NeurIPS 2024; PAPM accepted to ICML 2024, ArchCraft accepted to IJCAI 2024; InstructVideo, DreamVideo, and TF-T2V accepted to CVPR 2024; LUM-ViT accepted to ICLR 2024; VideoComposer accepted to NeurIPS 2023; RLIPv2 accepted to ICCV 2023; RLIP: Relational Language-Image Pre-training accepted to NeurIPS 2022 as a Spotlight paper; Elastic Response Distillation accepted to CVPR 2022; Object-guided Cross-modal Calibration Network accepted to AAAI 2022
- - Awards: Special Grant for Postdoctoral Research (Top 10 in Zhejiang Province); Outstanding Research Intern Award (20 in 1000+ candidates) for contribution in video generation to Alibaba; AAAI-22 Scholarship
Research Experience
- - Alibaba DAMO Academy: Research Scientist, focusing on cutting-edge problems in foundation models
- - Zhejiang University: Research position, working with Prof. Yi Yang
- - Representative Projects: VGen (includes InstructVideo), VideoComposer, Lumos series (includes Lumos-1), RLIP series (v1 and v2), DreamVideo series (v1 and v2), and ModelScopeT2V
Education
- - Ph.D. Degree: Graduated from Zhejiang University in the summer of 2024, supervised by Prof. Dong Ni, Prof. Samuel Albanie (University of Cambridge/DeepMind), Deli Zhao (Alibaba DAMO), and Shiwei Zhang (Alibaba Tongyi Wan Team)
- - Visiting Ph.D. Program: Conducted visiting research at MMLab@NTU, supervised by Prof. Ziwei Liu and Dr. Chenyang Si
Background
- - Research Interests: Generative models, representation learning, AI for science and engineering
- - Professional Field: Foundation models, visual generation/editing, visual autoregressive models, visual generation alignment, vision-language models, video understanding, visual relation detection (HOI detection/scene graph generation)
- - Introduction: A research scientist at Alibaba DAMO Academy, joining via the Alibaba Star program, focusing on cutting-edge problems in foundation models; also holds a research position at Zhejiang University, working with Prof. Yi Yang.
Miscellany
- - Recruiting Interns: Recruiting full-time or remote interns to work on cutting-edge problems in foundation models
- - Academic Service: Serving as an Area Chair for ICLR 2026
