Hao Phung

CS PhD student @ Cornell University, Cornell Tech, NYC

prof_pic.jpg

Manhattan, NYC

Greetings! I am a PhD student in Computer Science at Cornell Tech, NYC, advised by Hadar Averbuch-Elor. Previously, I was an AI Research Resident at VinAI, where I was fortunate to work under the mentorship of Dr. Anh Tran. Before that, I received my Bachelor of Computer Science from Ho Chi Minh City University of Science (HCMUS) in Vietnam.

My primary research interests center on generative models in vision and language domains, with an increasing focus on multimodal systems.

news

Sep 18, 2025 :sparkles: E2D2, a paper I co-authored, has been accepted to NeurIPS 2025.
Jun 2, 2025 :sunny: I have joined Apple AIML as a research intern, working with Haoxuan You.
Jan 22, 2025 :sparkles: Discrete Diffusion Guidance has been accepted to ICLR 2025.
Dec 9, 2024 :sparkles: Self-Corrected Flow Distillation has been accepted to AAAI 2025.
Sep 25, 2024 :sparkles: DiMSUM has been accepted to NeurIPS 2024.
Aug 26, 2024 :baby_chick: I started my PhD studies at Cornell University.
Jul 14, 2023 :sparkles: Anti-DreamBooth has been accepted to ICCV 2023.
Feb 28, 2023 :sparkles: WaveDiff has been accepted to CVPR 2023.

selected publications

  1. discrete_guidance.gif
    Simple Guidance Mechanisms for Discrete Diffusion Models
    Yair Schiff*, Subham Sekhar Sahoo*, Hao Phung*, Guanghan Wang*, Sam Boshar, Hugo Dalla-torre, Bernardo P Almeida, Alexander Rush, Thomas Pierrot, and Volodymyr Kuleshov
    In ICLR, 2025
  2. scflow.gif
    Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Image Generation
    In AAAI, 2025
  3. dimsum.gif
    DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation
    In NeurIPS, 2024
  4. antidb_trump.gif
    Anti-DreamBooth: Protecting users from personalized text-to-image synthesis
    Thanh Van Le*Hao Phung*Thuan Hoang Nguyen*Quan Dao*, Ngoc Tran, and Anh Tran
    In ICCV, 2023
  5. wavediff_denoising.gif
    Wavelet Diffusion Models are fast and scalable Image Generators
    Hao Phung*Quan Dao*, and Anh Tran
    In CVPR, 2023
Contact: hao (at) cs (dot) cornell (dot) edu | tienhaophung (at) gmail (dot) com
hao-pt.github.io's clustrmaps 🌎