I am a first-year Ph.D. student in Computer Science at Dartmouth College, advised by Prof. Nikhil Singh, where I pursue cutting-edge research in computer vision and machine learning. Previously, I earned my Master's degree in Data Science from The Chinese University of Hong Kong, Shenzhen, under the guidance of Prof. Xiaoguang Han. My academic journey began with a Bachelor's degree in Biomedical Engineering from Shanghai Jiao Tong University.
I worked as a research intern at Alibaba DAMO Academy for five months, mentored by Tian Zhou. I also served as a Visiting Student with Prof. Ming-Hsuan Yang at UC Merced and Prof. Chao Ma at the AI Institute of Shanghai Jiao Tong University. I have previously collaborated with Prof. Lu Qi and Dr. Xiangtai Li at TikTok, as well as with Prof. Junwei Liang and Dr. Peijie Dong at AI Thrust, The Hong Kong University of Science and Technology (Guangzhou).
My research background primarily focuses on video prediction and spatiotemporal forecasting.
My long-term research interests lie in:👁️ Visual Representation Learning
- Continuous vs. discrete visual representations
- Superior tokenization strategies for Vision Transformers
- Richer semantic structure capture
🧠 Multimodal Large Language Models
- Efficient vision-language projectors
- Manifold-to-Euclidean space mappings
- Token compression for efficient inference
🤖 AI Agents
- Multi-agent interaction mechanisms
- Efficient consensus protocols (voting, judgment, decision-making)
- Real-world problem solving frameworks
I'm open for academic collaborations. If you are interested, please feel free to email me at tangyujin0275@gmail.com.
If you are from SJTU/CUHKSZ or resource-constrained regions and are applying to US CS PhD programs, don't hesitate to email me. I will try my best to reply in time, as a way to give back to the mentors and community who have helped me.
Educations
Internships
News
- 2025.09: Yujin enrolled in Dartmouth College as a Ph.D. student in Computer Science.
- 2025.03: Yujin joined Alibaba DAMO Academy as a research intern.
- 2024.10: PredFormer is available! This is the first pure-transformer based model in spatial-temporal predictive learning, which is recurrent-free and convolution-free, outperforming previous models by large margins with superior efficiency. Paper Code
- 2024.04: 🎉🎉 VMRNN was accepted by CVPRW24!
- 2024.03: Yujin was invited to give a talk in CUHKSZ in Data Science College. Congratulations to the 10th anniversary of CUHKSZ! 🎉🎉 Slides
- 2024.03: 🎉🎉 PostRainBench was accepted by ICLRW24!
- 2024.01: Yujin created Awesome-Mamba-Papers repository and keep updating it. This is the first Awesome Mamba repository and promotes Mamba related research. Link
- 2023.07: 🎉🎉 Yujin won Excellence Award in Jinan, Shandong in 0-24 hours Precipitation Nowcasting Challenge! Slides
- 2023.01: Yujin served as TA for AIAA 5032 Foundations of Artificial Intelligence in HKUSTGZ, Spring 2023, Instructors: Junwei Liang.
Publication & PrePrint
Academic Service
- 2025: Reviewer for Transactions on Machine Learning Research (TMLR) and International Journal of Computer Vision (IJCV)
- 2024: Reviewer for IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
Notes
Computer Vision PhD Survival Guide Series(1) CV Paper Tracking and Writing Link
Computer Vision PhD Survival Guide Series(2) Code Release Process and Tools Link
Computer Vision PhD Survival Guide Series(3) SSH Configuration and Common Linux Command Link
Resources for CV Researchers
Ming-Hsuan Yang-UCM: How to Get Your CVPR Paper Rejected? Link
Chao Ma-SJTU: (Collection) Research and Writing Tips for Computer Vision Researchers Link
Sida Peng-ZJU: The Process of Finishing a Research Project Link
Bolei Zhou-UCLA: How to Make Posters for Top Conference Paper Link
Yana Hasson-Inria: Useful Computer Vision PhD Resources Link
Bill Freeman-MIT: How to Write Papers Link Advice for Graduate Student Link
Thanks a lot to these generous people for sharing their valuable research experience!
‘She is a first-generation college student born in a small city in western China. She constantly overcomes environmental resistance, builds a strong spiritual core, and pushes herself to grow and progress with self-drive and self-discipline. Thinking before practice, iterating quickly in action, she aims to make beneficial changes to the world with artificial intelligence and promote social equity.’