// PERSON
Trung Tuan Dao
ROLE LEAD AUTHORMENTIONS 1LAST SEEN SEPTEMBER 21, 2026
// BIO
Trung Tuan Dao is a first-year PhD student in computer science at the University of Wisconsin–Madison, advised by Professor Yong Jae Lee, where he researches vision-language-action models and world models. Prior to beginning his PhD in January 2026, he was a Staff Machine Learning Engineer at Qualcomm AI Research and an AI Research Resident at VinAI Research. He is best known for his work on efficient generative image models, including SwiftBrush v2 for one-step diffusion distillation, DiMSUM (Diffusion Mamba), and Self-Corrected Flow Distillation, with publications at NeurIPS, ECCV, ICCV, AAAI, and CVPR.
// RECENT MENTIONS
// SIGNALS
1 SIGNAL
01
mention·arXiv Physical AI·SEPTEMBER 21, 2026
“We add one feature-alignment term to ordinary VLA training”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.