Published numerous papers in top conferences such as CVPR, ICML, NeurIPS, including 'Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts' and 'Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference'.
Research Experience
Worked as a research intern at Google Mobile Vision on neural architecture search (MobileDets); also did research internships at Facebook AI and Amazon Lab 126.
Education
Ph.D. in Computer Sciences from the University of Wisconsin-Madison, under the supervision of Vikas Singh.
Background
Currently a senior research scientist at Meta Reality Labs. Research interests include natural language modeling, efficient Transformers, and neural architecture search, with a particular focus on efficient AI.