Nhat-Tan Bui

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

Email: tannhatb@andrew.cmu.edu | tanb@uark.edu

Greetings! My name in Vietnamese is Bùi Nhật Tân (裴日新), which typically means daily renewal 🌕 with brightness 🔆 and hope 🍀. I will join Carnegie Mellon University (CMU) as a research staff member in mid-February 2026, working with Prof. Fernando De la Torre, who is such a mensch and a brilliant researcher.

Previously, I received my M.S. from the University of Arkansas (UARK) in 2025 and my B.S. from the University of Science, VNU-HCM (HCMUS) and Auckland University of Technology (AUT) in 2022. I graduated from Le Quy Don High School, the oldest school in Ho Chi Minh City (Saigon).

Over my academic journey, I have been fortunate to work with wonderful advisors: Prof. Susan Gauch and Distinguished Prof. Truong Nguyen (UC San Diego) during my time at UARK, and Assoc. Prof. Minh-Triet Tran and Dr. Ngoc-Thao Nguyen during my time at HCMUS. I'm grateful for the unwavering support of my family, my friends and long-term collaborators: Hieu Hoang, Quoc-Huy Trinh, Quan Mai, Vuong Ho, Hai-Dang Nguyen, and Duy Le. 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 Cognitive Linguistic Understanding 📝 for Vision-Language Models.

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

Publications

"Research is for curiosity and fun, though practical implications can emerge." - Zhi-Hua Zhou
"Without the love of research, mere knowledge and intelligence cannot make a scientist." - Irène Joliot-Curie

(* indicates equal contribution)

NeIn: Telling What You Don't Want

Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2025) SyntaGen

🏆 Best Paper Award

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

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

International Symposium on Biomedical Imaging (ISBI 2024)

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

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

[Paper] [Code]

SAM3D: Segment Anything Model in Volumetric Medical Images

International Symposium on Biomedical Imaging (ISBI 2024)

Nhat-Tan Bui*, Dinh-Hieu Hoang*, Minh-Triet Tran, Gianfranco Doretto, Donald Adjeroh, ..., Ngan Le

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

Winter Conference on Applications of Computer Vision (WACV 2024)

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

TLDR: Laplacian-based Edge Information Fused with Attention Mechanism for UNet Skip Connection

[Paper] [Code]

Documents

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

Credits/Misc