Research

Our Research Interests

Our research is driven by advanced Computer Vision and Machine Learning & Robot Vision, equipping machines to truly understand complex real-world environments. Our research spans 3D Reconstruction for precise geometric scene understanding, Social Kinematics for modeling human-agent dynamics, and LLMs & Creative AI for generating physics-based content. Especially, our group's research achievements are listed in below:

Autonomous Driving

  • Trajectory Prediction & Reasoning
  • Motion & Behavior Generation

Related Works:
AAAI'21, CVPR'22, ECCV'22, AAAI'23ORAL, ICCV'23, CVPR'24(1), CVPR'24(2), CVPR'25, IEEE TPAMI'26, NeurIPS'26(Under-Review)

Physical AI

  • Vision-Language Action Models
  • Robotics & Physical Simulation

Related Works:
CVPR'24(1), NeurIPS'26(Under-Review)

Generative AI

  • Video & Image Content Creation
  • Sign Language Generation
  • TEM / Medical Image Analysis

Related Works:
CVPR'24(2), ECCV'24, NeurIPS'26(Under-Review)

3D Reconstruction

  • 2D, 3D, 4D Scene Reconstruction
  • Depth Estimation & Completion

Related Works:
ICML'23, ICLR'24, NeurIPS'24, ICCV'25HIGHLIGHT, ECCV'26

Large Language Models

  • Vision-Language Alignment
  • Reasoning via VLMs

Related Works:
CVPR'24(2), IEEE TPAMI'26, NeurIPS'26(Under-Review)

Machine Learning for CV

  • Machine Learning Theory
  • Mathematical Formulation

Related Works:
CVPR'22, ICML'23, ICCV'23