~/trung-dao/whoami.lua
NVIM v0.10.0
--- whoami.lua · ":h trung" for help
--- press ? any time for keymaps · type :help below
local me = {
name = "Trung Dao",
role = "PhD Student",
institute = "University of Wisconsin–Madison",
advisor = require("prof").load("Yong Jae Lee"),
research = { "vision-language-action", "world models" },
prev = {
{ org = "Qualcomm AI Research", title = "Staff ML Engineer" },
{ org = "VinAI Research", title = "AI Engineer & Research Resident" },
},
}
return me
$ cat about.txt
Trung Dao at the Leaning Tower of Pisa
-- loc="Pisa, IT"

Hi! I'm Trung Dao — a 1st-year PhD student at UW-Madison, advised by Prof. Yong Jae Lee. These days I poke at vision-language-action models and world models — basically trying to convince a neural net to look at the world, imagine what happens next, and not bonk into the wall when it finally moves. The dream: agents that perceive, simulate, and actually do useful stuff in the physical world. Before grad school I was a Staff ML Engineer at Qualcomm AI Research (squeezing generative & multimodal models onto phone-sized silicon), and an AI Engineer / Research Resident at VinAI Research with Dr. Anh Tran & Dr. Cuong Pham, mostly hacking on diffusion distillation and GANs. Outside of research: cold brew, naps, and arguing with my cats.

scholar github linkedin goodreads CV
$ tail -f changelog.md
Jan 2026 Started my PhD at UW-Madison, joining Prof. Yong Jae Lee's group to work on vision-language-action models and world models. Excited & terrified in equal measure.
Nov 2025 Promoted to Staff Machine Learning Engineer after a 5/5 ("Far Exceeds Expectations") rating in Qualcomm's 2025 review. Yay!!
Sep 2025 Improved Training Technique for Shortcut Models accepted to NeurIPS 2025.
Jun 2025 SNOOPI accepted to ICCV 2025.
Dec 2024 Self-Corrected Flow accepted to AAAI 2025.
Sep 2024 DiMSUM accepted to NeurIPS 2024.
Jul 2024 SwiftBrushV2 accepted to ECCV 2024.
Mar 2024 EFHQ accepted to CVPR 2024.
$ grep -r '@inproceedings' ./publications/
03 pub_selfflow.bib AAAI, 2025
Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Image Generation

Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Image Generation

Quan Dao*, Hao Phung*, Trung Dao, Dimitris Metaxas, Anh Tran

A comprehensive distillation framework for latent flow matching models that excels in generating high-quality and consistent images in both one-step and few-step sampling

04 pub_dimsum.bib NeurIPS, 2024
DiMSUM : Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation

DiMSUM : Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation

Hao Phung*, Quan Dao*, Trung Dao, Hoang Phan, Dimitris Metaxas, Anh Tran

A hybrid Mamba-Transformer diffusion model that synergistically leverages both spatial and frequency information for high-quality image synthesis.

06 pub_efhq.bib CVPR, 2024
EFHQ: Multi-purpose ExtremePose-Face-HQ dataset.

EFHQ: Multi-purpose ExtremePose-Face-HQ dataset.

Trung Dao*, Duc Vu*, Anh Tran

A high-quality dataset centered on extreme pose faces, supporting face synthesis, reenactment, recognition benchmarking, and more.

$ cat contact.json
{
  "email":    "tdao6 [at] wisc [dot] edu",
  "office":   "CS @ UW-Madison",
  "github":   "@trungdt880",
  "scholar":  "FZmxEYYAAAAJ",
  "open_to":  ["collabs", "chats about VLA / world models", "book recs"]
}
: ? help · gg top · G bottom · j/k scroll