Scholar
Minh-Hao Van
Google Scholar ID: GO7SLkoAAAAJ
University of Arkansas
Citations & Impact
Citations
239
H-index
8
i10-index
8
Publications
20
Co-authors
5
list available
Publications
Resume (English only)
Academic Achievements
- Three papers accepted at NeurIPS 2025 workshops: (1) Fine-Tuning Vision-Language Models for Multimodal Polymer Property Prediction; (2) CAGUL: Cross-Modal Attention Guided Unlearning in Vision-Language Models; (3) A Machine Learning Framework for Automated Computational Ethology Using Markerless Pose Estimation
- Paper 'Soft Prompting for Unlearning in Large Language Models' accepted to NAACL-2025 main conference (Jan 2025)
- Co-authored paper accepted at IJCNN’24 (Mar 2024)
- Paper on large visual language models for medical imaging accepted at IEEE CHASE’24 (Feb 2024); awarded NSF Student Travel Award
- Paper 'Robust Influence-based Training Methods for Noisy Brain MRI' accepted as full oral paper at PAKDD’24 (Jan 2024)
- Paper 'HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks' accepted at ICDM 2023 (acceptance rate 9.37%)
- Awarded the Reginald R. ‘Barney’ & Jameson A. Baxter and EECS Graduate Fellowship for 2024–2025
- Serving as reviewer for WWW’25, PAKDD’25, and IJCNN’25
Background
- Currently a Postdoctoral Fellow in Computer Science at the University of Arkansas
- Research interests include Machine Learning and Deep Learning
- Focuses on improving trustworthiness in AI/ML models, particularly addressing robustness, safety, privacy, and fairness in Large (Vision) Language Models
- Explores resource-efficient approaches for adapting large models to new tasks
- Develops AI foundation models for scientific domains such as biomedical engineering and materials science
