I am a PhD student at Nanyang Technological University, at MMLab@NTU, advised by Prof. Chen Change Loy. I also work as an AI researcher at HeyGen, working closely with Mr. Yi Ren and Dr. Zhenhui Ye. Before my PhD study, I was fortunate to work with Dr. Wei Li. My research interests include computer vision and generative models.
I received my Master degree in Artificial Intelligence at Nanyang Technological University in 2023 and B.Eng in Automation at XJTU in 2020.
🔥 News
- 2026.07: 🎉🎉 TAVR is accepted by SIGGRAPH Asia 2026. See you in Kuala Lumpur!
- 2026.08: 🎉🎉 Two papers are accepted by ECCV 2026.
- 2025.09: 🎉🎉 PoseFuse3D-KI is accepted by NeurIPS 2025.
📝 Publications
Avatar V: Scaling Video-Reference Avatar Video Generation
HeyGen Research (alphabetical: Benjamin Liang, Ce Chen, Desmond Lin, Ivan Somov, Jiajun Zhao, Jiewei Yuan, Jingfeng Zhang, Junhao Huang, Nik Nolte, Pedram Haqiqi, Penghan Wang, Rong Yan, Rui Zhang, Sam Prokopchuk, Sivan Wang, Viktor Goriachko, Yi Ren, Yuanming Li, Yutao Chen, Zhenhui Ye, Zhibin Hong, Zilong Nie, Zujin Guo)
TAVR: Generate Your Talking Avatar from Video Reference
Zujin Guo, Zhenhui Ye, Yi Ren, Yuanming Li, Ce Chen, Zhibin Hong, Chen Change Loy
Paper / Code / Model / Benchmark / Project page
TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitions
Ce Chen, Yi Ren, Yuanming Li, Viktor Goriachko, Zhenhui Ye, Zujin Guo, Zhibin Hong, Mingming Gong
Paper / Code / Project page / Blog
HippoCamp: Benchmarking Contextual Agents on Personal Computers
Zhe Yang, Shulin Tian, Kairui Hu, Shuai Liu, Hoang-Nhat Nguyen, Yichi Zhang, Zujin Guo, Mengying Yu, Zinan Zhang, Jingkang Yang, Chen Change Loy, Ziwei Liu
Paper / Code / Data / Project page
Controllable Human-centric Keyframe Interpolation with Generative Prior
Zujin Guo, Size Wu, Zhongang Cai, Wei Li, Chen Change Loy
Paper / Code / Project page
Generalizable Implicit Motion Modeling for Video Frame Interpolation
Zujin Guo, Wei Li, Chen Change Loy
Paper / Code / Project page
Pair then Relation: Pair-Net for Panoptic Scene Graph Generation
Jinghao Wang, Zhengyu Wen, Xiangtai Li, Zujin Guo, Jingkang Yang, Ziwei Liu
Panoptic Video Scene Graph Generation
Jingkang Yang, Wenxuan Peng, Xiangtai Li, Zujin Guo, Liangyu Chen, Bo Li, Zheng Ma, Wayne Zhang, Kaiyang Zhou, Chen Change Loy, Ziwei Liu
Panoptic Scene Graph Generation
Jingkang Yang, Yi Zhe Ang, Zujin Guo, Kaiyang Zhou, Wayne Zhang, Ziwei Liu
Paper / Code / Project page / Demo
🎬 Demo
💻 Code & Dataset
- TAVR: Code, model and benchmark for Generate Your Talking Avatar from Video Reference, SIGGRAPH Asia’26
- PoseFuse3D-KI: Code, model checkpoints and dataset (with SMPL-X linear interpolator), NeurIPS’25
- GIMM-VFI: Code for Generalizable Implicit Motion Modeling for Video Frame Interpolation (GIMM-VFI), NeurIPS’24
- PSG: Dataset and Benchmark for Panoptic Scene Graph Generation (PSG), ECCV’22
- RAM: Code for Relate Anything
📖 Educations
- 2026 - now, PhD student, MMLab@NTU, Nanyang Technological University, Singapore.
- 2021 - 2023, M.Sc. in Artificial Intelligence, Nanyang Technological University, Singapore.
- 2016 - 2020, B.Eng. in Automation, Xi’an Jiaotong University, China.
🎓 Academic Service
- Conference/Journal Reviewer: CVPR, ICCV, ECCV, NeurIPS, AAAI, ICLR, AISTATS, ICML, IJCV.