Education
Rutgers, The State University of New Jersey - New Brunswick. Piscataway, NJ
- Supervised by Prof. Dimitris N. Metaxas
- Ph.D. Thesis: "Towards Efficient and Reliable Skeleton-Based Human Pose Modeling"
- GPA: 4.0/4.0
Tongji University. Shanghai, China
- Supervised by Prof. Jinyuan Jia and Prof. Shuang Liang
- Master Thesis: "Sketch-Based 3D Model Retrieval"
Tongji University. Shanghai, China
- GPA: 4.56/5.0, which is equivalent to 90.6 on 100 basis
Experience
Applied Research, Google DeepMind. Los Angeles, CA, USA
- Video Understanding (e.g., Multimodal Models, World Models)
- Video Generation (e.g., Diffusion Models, Visual Autoregressive Models)
- Human-Centric Perception (e.g., Recognition, Detection)
Perception Team, Google Research. Los Angeles, CA, USA
Brain Team, Google Research. Mountain View, CA, USA
- Boosting Transformers for High-Resolution Image Generation [NeurIPS'21]
- Improving Efficiency and Interpretability for Vision Transformers [AAAI'22 (Oral)]
Mobile Vision Team, Google Research. Los Angeles, CA, USA
- View-Disentangled Human Pose Representation Learning [CVPR'21 (Oral)]
- View-Invariant, Occlusion-Robust Probabilistic Pose Embedding [IJCV'21]
Computer Science Department, Rutgers University. Piscataway, NJ, USA
- 3D Human/Hand Pose Estimation from RGB Images [CVPR'19] [CVPR'20]
- Face/Pose/Video Generation with Generative Adversarial Networks [IJCAI'18] [ECCV'18] [IJCV'20]
- Domain Generalization via Adversarial Training & Meta-Learning [CVPR'20] [NeurIPS'20]
- Representation Learning on Graphs with Graph Convolutional Networks [NeurIPS'19]