Received the Outstanding Early Career Researcher Award from IEIE AISP Society in 2025.
Multiple papers accepted to top-tier conferences including ICCV 2025, CVPR 2025, MICCAI 2025, IJCAI 2025, ICLR 2025, AAAI 2025, and ECCV 2024.
Team secured 3rd place in the Multimodal Arial View Imagery Classification Challenge at CVPR 2025.
Achieved 3rd place among 77 teams in the Multimodal Semantic Segmentation Challenge 2024 at IEEE WHISPERS.
Awarded one Bronze Best Paper Award and two Best Poster Awards at IPIU 2025.
Background
Aims to go beyond human perception, modeling and understanding the world we see and sense with greater precision.
Believes generative models are the most powerful—and indeed the only—solution for building systems that understand the world.
Focuses on developing interpretable, efficient, intuitive, and easy-to-use imaging algorithms rather than merely pursuing high performance.
Combines the rigor of signal processing with the creativity of machine learning to build algorithms that analyze and synthesize images, audio, and video, constructing comprehensive 'world models'.
Seeks to uncover mathematical insights and reveal the beauty of hidden patterns in nature, pushing the frontier of signal modeling and interpretation.