Teahose.
SIGN IN
NEW HERE — WHAT TEAHOSE DOES
We read the entire AI & tech firehose — so you don't have to.
PODPodcastsAll-In, No Priors, Acquired…
NEWNewslettersStratechery, Newcomer…
PAPPapersPhysical AI research
PHProduct Huntdaily launches
VCInvestor ScoutSequoia, a16z, Benchmark…
CLAUDE DISTILLS →
7 reads, 30 sec each — free, 6 AM ET.
+ a live graph of the companies, people & themes underneath.
HOME/PEOPLE/TRUNG TUAN DAO
// 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.

Trung Tuan Dao · Lead author — 1 mention on Teahose