anvo.jpg

An Vo

Research Engineer @ Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
Incoming PhD student in Computer Science and Engineering @ University of Michigan

I am currently a Research Engineer at MBZUAI MBZUAI working with Thamar Solorio, and an incoming PhD student in Computer Science and Engineering at UMich University of Michigan advised by Rada Mihalcea. I am also collaborating closely with Anh Totti Nguyen. Previously, I obtained my MS from KAIST KAIST with Daeyoung Kim, where I received the Outstanding MS Thesis Award and was fully funded by the Hyundai CMK Global Scholarship. I am broadly interested in foundation models, especially in making them more trustworthy and explainable in edge/hard cases.

news

Apr 2026 I am coming to UMich University of Michigan this Fall 2026 as a Computer Science and Engineering PhD student, advised by Rada Mihalcea. It’s a dream come true!
Mar 2026 VLMs are Biased is featured on Sky News Sky News — watch the film and read the article.
Jan 2026 VLMs are Biased has been accepted to ICLR 2026!
Jan 2026 Starting a new Research Engineer position at MBZUAI. I’m thrilled to begin this next chapter.
Dec 2025 Google DeepMind and ByteDance have used my VLMs are Biased benchmark!
Dec 2025 I successfully defended my MS thesis. Relieved and proud to reach this milestone.
Jul 2025 I will attend ICML 2025 in Vancouver to present B-score and VLMs are Biased. Visit our poster to discuss or grab a coffee — happy to connect!
Jun 2025 I will serve as a reviewer for AAAI 2026.
Jun 2025 One preprint on arXiv: VLMs are Biased.
May 2025 One paper has been accepted to ICML 2025.

selected publications

* equal contribution

  1. ICLR
    vlmsarebiased_thumnell.png
    Vision Language Models are Biased
    An Vo*, Khai-Nguyen Nguyen*, Mohammad Reza Taesiri, Vy Tuong Dang, Anh Totti Nguyen, and Daeyoung Kim
    In International Conference on Learning Representations (ICLR), 2026
    Paper Website
  2. ICML
    bscore_thumnell.png
    B-score: Detecting biases in large language models using response history
    An Vo, Mohammad Reza Taesiri, Daeyoung Kim, and Anh Totti Nguyen
    In International Conference on Machine Learning (ICML), 2025
    Paper Website
  3. GECCO
    pnds_thumnell.jpg
    Efficient Multi-Objective Neural Architecture Search via Pareto Dominance-based Novelty Search
    An Vo, and Ngoc Hoang Luong
    In Genetic and Evolutionary Computation Conference (GECCO), 2024
    Paper Code

Full list of publications here.