Yuhang Zang
Scholar

Yuhang Zang

Google Scholar ID: hW23VKIAAAAJ
Shanghai AI Laboratory
Natural Language ProcessingVision Language Model
Citations & Impact
All-time
Citations
6,046
 
H-index
26
 
i10-index
42
 
Publications
20
 
Co-authors
76
list available
Resume (English only)
Academic Achievements
  • Multiple papers accepted by top international conferences and journals such as NeurIPS 2025, ICCV 2025, Findings of ACL 2025, ICML 2025, CVPR 2025, ICLR 2025, NeurIPS 2024, ACM MM 2024, ECCV 2024, CVPR 2024, IJCV. Notable works include UnifiedReward-Think, Hi-Flow, Visual-RFT, MM-IFEngine, X-Prompt, Bootstrap3D, Grounded CoT Highlight, Light-A-Video, MIR, SAM2Long, IXC-2.5-Reward, Light-ColPali, VideoRoPE, SongGen, ByTheWay, OVO-Bench, Dispider, PyramidDrop, WildAvatar, MIA-DPO, MotionClone, MMLongbench-Doc, ShareGPT4Video, MMDU, InternLM-XC2-4khd, VideoStreaming, MMStar, VLMEvalKit, Long-CLIP, MVSGaussian, Alpha-CLIP, CascadeMatch, OV-DETR.
Research Experience
  • Joined Apple (AI/ML) as a research intern in June 2023.
Education
  • Obtained Bachelor's degree from UESTC in 2019; obtained PhD from Nanyang Technological University in 2023, supervised by Prof. Chen Change Loy.
Background
  • Current research focuses on 1) post-training for multimodal LLMs (reinforcement fine-tuning, reward models), and 2) vision-language pre-training.
Miscellany
  • Hobbies and interests not mentioned