Paper 'ETA: Energy-based Test-time Adaptation for Depth Completion' accepted to ICCV 2025
Paper 'ProtoDepth: Unsupervised Continual Depth Completion with Prototypes' accepted to CVPR 2025
Paper 'HOMER: Homography-Based Efficient Multi-view 3D Object Removal' published as arXiv technical report in 2025
Paper 'PriorDiffusion: Leverage Language Prior in Diffusion Models for Monocular Depth Estimation' published as arXiv technical report in 2024
Paper 'RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions' published in 2024
Served as reviewer for CVPR (2022, 2025 [Outstanding Reviewer]), ICCV (2023, 2025), ECCV (2024), ICML (2025), ICLR (2025, 2026), NeurIPS (2024, 2025), ACM MM (2023, 2025), AISTATS (2024, 2025), ICASSP (2024, 2025), TCSVT
Background
Third-year Ph.D. student in Computer Science at Yale University (2023–expected 2027), advised by Prof. Alex Wong
Research interests include Computer Vision, Machine Learning, and Robotics
Focuses on Multimodal Embodied AI inspired by human learning
Current research centers on Vision-Language Models for 3D Vision
Research vision: empower embodied AI with multimodal sensing and leverage pre-trained multimodal representations to interact with the physical world like humans