About me

I am a Research Scientist at the Institute of Foundation Models, MBZUAI on the World Model team. My current research focuses on video generation and world model pretraining, particularly improving model capabilities through large-scale video data curation, concept balancing, pretraining curricula, and data mixture design.

I completed my PhD in Computer Engineering at University of California, Davis in March 2026, advised by Prof. Chen-Nee Chuah. My PhD research focused on computer vision, multimodal learning, and security & privacy, with work spanning privacy-preserving visual learning, multimodal retrieval, domain adaptation, and generative models.

Previously:

Research Interests: World Models, Privacy-Preserving Computer Vision, Multi-Modal LLMs, Physical/Embodied AI


Select Publications

See more publications…


News

June 2026

📄✅ One paper accepted at ECCV 2026 !

April 2026

📄✅ Our paper “Privacy-Complaint Human Data Synthesis in Images for GDPR” is accepted at IEEE FG 2026 !

March 2026

💼📊 Joined Institute of Foundation Models, MBZUAI (Sunnyvale, CA) as a Research Scientist! I will be working in the World Model team.

February 2026

📄✅ One first-author paper is accepted at CVPR 2026 !

See more…