Minh Khoi Ho

Master's student in Computer Vision at MBZUAI, class of 2027.

profil.jpg

I am a Master’s student in Computer Vision at MBZUAI, supervised by Assistant Prof. Yutong Xie. From 2024-2025, I was a research assistant at the Institute for AI Innovation and Societal Impact (AI4LIFE) under Assoc.Prof.Phi Le Nguyen in a collaboration with the Australian Institute for Machine Learning (AIML). Before that, I earned my Bachelor’s degree in Data Science and AI at Hanoi University of Science and Technology.

My research interest revolves around applying vision-language models, mostly in medical contexts. I also welcome all research ideas and collaboration initiatives, and you can contact me via my email: hominhkhoi2701@gmail.com.

news

Jul 09, 2026 1 paper, “Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?”, is accepted at COLM 2026.
Jun 13, 2026 1 paper, “Attention-Based Prototype Calibration for Multi-Rater Few-Shot Medical Image Segmentation”, accepted at MICCAI 2026. See you in Strasbourg!
Mar 03, 2026 2 papers (1 main, 1 findings) accepted at CVPR 2026
May 26, 2025 Selected to receive the 2025 Australia-Vietnam Strategic Technologies Scholarship.
Apr 26, 2025 1 paper accepted at IJCAI 2025.

selected publications

  1. Preprint
    Main_EmoDoc.png
    MedEmoBench: Revealing and Mitigating Emotion-Induced Inconsistency in Medical Vision-Language Models
    Minh Khoi Ho, Omar Abdelshafi Mohamed, Xinyue Bi, and 4 more authors
    Under review, 2026
  2. COLM
    EmotionAgent2.png
    Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
    Minh Khoi Ho, Zihao Zhu, Runchuan Zhu, and 4 more authors
    In Third Conference on Language Modeling, 2026
  3. multirater_seg.png
    Attention-Based Prototype Calibration for Multi-rater Few-Shot Medical Image Segmentation
    Truong Vu, Minh Khoi Ho, and Yutong Xie
    In International Conference on Medical Image Computing and Computer-Assisted Intervention, 2026
  4. CVPR
    beyond_scores.png
    Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
    Tuan Dung Nguyen, Minh Khoi Ho, Qi Chen, and 8 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026
  5. IJCAI
    loba.png
    Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs
    Dung Nguyen*, Minh Khoi Ho*, Huy Ta, and 11 more authors
    2025
  6. CVPR
    trafficVLM.png
    TrafficVLM: A controllable visual language model for traffic video captioning
    Quang Minh Dinh, Minh Khoi Ho, Anh Quan Dang, and 1 more author
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024