Minh Khoi Ho — accepted AI-conference papers

2026

Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations

Tuan Dung Nguyen, Minh Khoi Ho, Qi Chen, Yutong Xie, Cam-Tu Nguyen, Minh Khoi Nguyen +5

CVPR 2026

Large vision-language models (LVLMs) achieve strong performance on visual reasoning tasks but remain highly susceptible to hallucination. Existing detection methods predominantly rely on coarse, whole-image measures of how an object token relates to the input image. This global strategy is limited:

Cited by 0 Source ↗Scholar ↗

2025

Localizing Before Answering: A Benchmark for Grounded Medical Visual Question Answering

Dung Nguyen, Minh Khoi Ho, Huy Ta, Thanh Tam Nguyen, Qi Chen, Kumar Rav +8

IJCAI 2025

Medical Large Multi-modal Models (LMMs) have demonstrated remarkable capabilities in medical data interpretation. However, these models frequently generate hallucinations contradicting source evidence, particularly due to inadequate localization reasoning. This work reveals a critical limitation in

Cited by 0 Source ↗PDF ↗Scholar ↗