~/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
▶ Jun 2026 Cross-Space Distillation, got into ECCV 2026! Sweden, here I come 🇸🇪 (someone teach me how to pronounce Malmö).
▶ May 2026 Apparently I review enough to earn a Golden Reviewer badge at CVPR 2026. My rebuttal-reading stamina finally pays off ✋😔
▶ 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.
▶ Oct 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