Scholar
Shuaiyi Huang
Google Scholar ID: j-P28bQAAAAJ
META FAIR
Citations & Impact
Citations
616
H-index
9
i10-index
9
Publications
17
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- - Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition. ICCV 2025
- - TREND: Tri-teaching for Robust Preference-based Reinforcement Learning with Demonstrations. ICRA 2025
- - TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies. ICLR 2025
- - AUTOHALLUSION: Automatic Generation of Hallucination Benchmarks for Vision-Language Models. EMNLP 2024
- - ARDuP: Active Region Video Diffusion for Universal Policies. IROS 2024 (Oral Presentation)
- - What is Point Supervision Worth in Video Instance Segmentation? (Incomplete information)
Research Experience
- - Research Engineer at META FAIR Robotics, World Model Team, July 2025 - present. Worked on vision-language-latent-action models for general robot manipulation.
- - Research Intern at NVIDIA, May - Aug 2023. Worked on video diffusion for robot manipulation. Mentors: De-An Huang, Linxi 'Jim' Fan, Yuke Zhu.
- - Research Intern at NVIDIA, May - Nov 2022. Worked on video instance segmentation with point supervision. Mentors: Zhiding Yu, De-An Huang, Shiyi Lan.
Education
- - Ph.D. in Computer Science from the University of Maryland, College Park, advised by Prof. Abhinav Shrivastava.
- - M.S. in Computer Science from ShanghaiTech University, advised by Prof. Xuming He.
- - B.Eng. in Software Engineering from Tongji University.
Background
- - Research Interests: Intersection of Computer Vision and Autonomous Agents, focusing on video understanding, object recognition, policy learning, and generative world modeling.
- - Goal: To build foundation models that seamlessly integrate visual, linguistic, and action understanding for real-world applications.
Miscellany
- Looking for full-time jobs in industry. Please feel free to contact.
Co-authors