"True scholar is shown by phronesis, not imagination."

Greetings! My name is Nhat-Tan Bui (Vietnamese: Bùi Nhật Tân), which typically means daily renewal 🌕 with brightness 🔆 and hope 🍀. I’m currently a Master’s student at the University of Arkansas (UARK) 🇺🇸, where I'm fortunate to be advised by Prof. Susan Gauch and Distinguished Prof. Truong Nguyen (UC San Diego). I initially worked with Asst Prof. Ngan Le during my first year in the US.

I earned my Bachelor's degree in Computer & Information Science from the University of Science, VNU-HCM (HCMUS) 🇻🇳 and Auckland University of Technology (AUT) 🇳🇿. I was lucky to work as a Research Assistant at the Software Engineering Lab (SELab) under the supervision of Assoc Prof. Minh-Triet Tran and Dr. Ngoc-Thao Nguyen.

I graduated from Le Quy Don High School, the oldest school in Saigon. I'm grateful for the unwavering support of my family, my friends and long-term collaborators: Hieu Hoang (HCMUS), Quoc-Huy Trinh (Aalto University), Quan Mai (Walmart), Vuong Ho (SBU), Hai-Dang Nguyen (HCMUS), and Duy Le (MBZUAI). All of the people mentioned are those to whom I owe a debt of gratitude.

Research Keywords: Deep Learning 🧠, Computer Vision 👀, and Multimodal Learning 🎏 with applications in Mechanistic Interpretability 🔍 and Linguistic Understanding 📝 for Vision-Language Models. The long-term questions I aim to figure out are (i) how the training phase of VLMs alters the linguistic representations of their language components—in other words, whether vision–language integration enables models to better mimic human cognition and (ii) whether interpreting VLMs can help us better understand human behavior and cognitive processes—in other words, whether VLMs can serve as cognitive models.

Please feel free to drop me an email if you have any questions about my research, or even me 😁

Master of Science in Computer Science

University of Arkansas, USA, 2023 - 2025, fully-funded by Graduate Assistantships

GPA: 4.00 / 4.00

Bachelor of Science in Computer & Information Science

University of Science, VNU-HCM, Vietnam & Auckland University of Technology, New Zealand, 2018 - 2022

GPA: 3.84 / 4.00

"Research is for curiosity and fun, though practical implications can emerge." - Zhi-Hua Zhou

NeIn: Telling What You Don't Want

Nhat-Tan Bui, Dinh-Hieu Hoang, Quoc-Huy Trinh, Minh-Triet Tran, Truong Nguyen, and Susan Gauch

Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2025) SyntaGen, Tennessee, USA (🏆 Best Paper Award)

TLDR: First Large-Scale Vision-Language Negation Dataset for Text-Guided Image Editing [Paper] [Project Page]

TSRNet: Simple Framework for Real-time ECG Anomaly Detection with Multimodal Time and Spectrogram Restoration Network

Nhat-Tan Bui*, Dinh-Hieu Hoang*, Thinh Phan, Minh-Triet Tran, Brijesh Patel, Donald Adjeroh, and Ngan Le

International Symposium on Biomedical Imaging (ISBI 2024), Athens, Greece

TLDR: Time-Spectrogram Fusion with Cross-Attention Mechanism and Prioritizing R-peaks during Inference [Paper] [Code]

SAM3D: Segment Anything Model in Volumetric Medical Images

Nhat-Tan Bui*, Dinh-Hieu Hoang*, Minh-Triet Tran, Gianfranco Doretto, Donald Adjeroh, Brijesh Patel, Arabinda Choudhary, and Ngan Le

International Symposium on Biomedical Imaging (ISBI 2024), Athens, Greece

TLDR: Frozen SAM’s Encoder, Stack Output Slice Embeddings, and Decode with a 3D CNN Decoder [Paper] [Code]

MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation

Nhat-Tan Bui, Dinh-Hieu Hoang, Quang-Thuc Nguyen, Minh-Triet Tran, and Ngan Le

Winter Conference on Applications of Computer Vision (WACV 2024), Hawaii, USA

TLDR: Laplacian-based Edge Information Fused with Attention Mechanism for UNet Skip Connection [Paper] [Code]

"In the end, when it’s over, all that matters is what you’ve done." - Alexander the Great

• Outstanding Reviewer, CVPR 2025 (top 5% of 12,593 reviewers)
• Travel Support Award, CVPR 2025
• The Fund for Opportunity and eXperience (FOX) Award, UARK 2025
• The GPSC Tiffany Marcantonio Research Grant, UARK 2025
• Department of Electrical Engineering and Computer Science Fellowship, UARK 2025
• The Reginald R. ‘Barney’ & Jameson A. Baxter Graduate Fellowship, UARK 2024
• Rank 1st place team at OS-MN40 dataset in Open-Set 3D Object Retrieval track, SHREC 2022
• Rank 3rd place team at OS-MN40-Miss dataset in Open-Set 3D Object Retrieval track, SHREC 2022
• Rank 1st place team in Visual Sentiment Analysis task, MediaEval 2021

"What I cannot create, I do not understand." - Richard Feynman

Tutorial on Introduction to Neural Networks for Natural Language Processing

Tutorial on Recurrent Neural Network and its Variants

Tutorial on Sequence-to-Sequence and Attention

Tutorial on Transformer

Tutorial on Contextualized Representations and Pretraining Language Models

"It is your work in life that is the ultimate seduction." - Pablo Picasso

Program Committee:

• International Joint Conference on Artificial Intelligence (IJCAI), 2024 - 2025
• European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2025

Conference Reviewer:

• IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR)
• IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
• European Conference on Computer Vision (ECCV)
• ACM International Conference on Multimedia (ACMMM)
• International Conference on Multimedia and Expo (ICME)
• European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)
• International Conference on Multimedia Modeling (MMM)
• International Conference on Pattern Recognition (ICPR)
• International Symposium on Biomedical Imaging (ISBI)
• Medical Image Understanding and Analysis (MIUA)
• International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)

Journal Reviewer:

• Medical Image Analysis
• Biomedical Signal Processing and Control
• Computational and Structural Biotechnology Journal (CSBJ)
• Computer Vision and Image Understanding (CVIU)
• IEEE Journal of Biomedical and Health Informatics (JBHI)