Duy-Tung Pham
PhD Student in CS @ Northeastern University · Boston, MA, United States
Email: pham.duy at northeastern dot edu | phamduytung2002 at gmail dot com
About me
Hello! I am a PhD student at Khoury College of Computer Sciences, Northeastern University, advised by Prof. Huy Nguyen. Before that, I was an AI Research Resident at FPT Software AI Center, where I had the great opportunity to work under the guidance of Prof. Thieu Vo and Prof. Tan Minh Nguyen.
I completed my Bachelor's degree in Computer Science through the Talented (Honors) Program at the School of Information and Communication Technology (SoICT), Hanoi University of Science and Technology (HUST). During my undergraduate studies, I was also a research student at the Data Science Laboratory, where I was mentored by Dr. Linh Ngo Van and Prof. Khoat Than.
In Vietnamese, my name is written as Phạm Duy Tùng (/fam zwi tuŋ/). You can call me Duy-Tung, or simply Tung.
Publications
(*) equal contribution · (**) equal advising · bold = me
12. First-Token Attraction in Mamba Dynamics
Trinh Tien Nguyen, Duy-Tung Pham, Minh-Khoi Nguyen-Nhat, Hoang-Son Do, Tan M. Nguyen, Thieu Vo
Annual Conference on Neural Information Processing Systems (NeurIPS), 2026, Spotlight
11. Two-Clustering Regime of Token Dynamics in Causal Attention
Trinh Tien Nguyen, Duy-Tung Pham, Hoang-Son Do, Tan M. Nguyen, Thieu Vo
Annual Conference on Neural Information Processing Systems (NeurIPS), 2026
10. Mixed-Curvature Tree-Sliced Wasserstein Distance
Duy-Tung Pham*; Viet-Hoang Tran*; Thieu Vo; Tan M. Nguyen
International Conference on Learning Representations (ICLR), 2026
Paper · Bibtex
9. Revisiting Tree-Sliced Wasserstein Distance Through the Lens of the Fermat-Weber Problem
Viet-Hoang Tran*; Thanh Tran*; Thanh Chu*; Trung-Khang Tran; Duy-Tung Pham; Tam Le**; Tan M. Nguyen**
International Conference on Learning Representations (ICLR), 2026
Paper · Bibtex
8. Tree-Sliced Sobolev IPM
Viet-Hoang Tran*; Thanh Tran*; Thanh Chu; Duy-Tung Pham; Trung-Khang Tran; Tam Le**; Tan M. Nguyen**
International Conference on Learning Representations (ICLR), 2026
Paper · Bibtex
7. Dynamical Properties of Tokens in Self-Attention and Effects of Positional Encoding
Duy-Tung Pham*; An Nguyen The*; Viet-Hoang Tran; Nhan-Phu Chung; Xin T. Tong; Tan M. Nguyen**; Thieu Vo**
Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
Paper · Bibtex
6. TopiCOT: Neural topic model aligning with pre-trained clustering and optimal transport
Tung Nguyen*; Duy-Tung Pham*; Quang Duc Nguyen; Linh Ngo Van; Duc Anh Nguyen; Sang Dinh Viet
Neurocomputing, 2025
Paper · Bibtex
5. Equivariant Polynomial Functional Networks
Thieu Vo*; Viet-Hoang Tran*; Tho Tran Huu; An Nguyen The; Thanh Tran; Minh-Khoi Nguyen-Nhat; Duy-Tung Pham; Tan M. Nguyen
International Conference on Machine Learning (ICML), 2025
Paper · Bibtex
4. Demystifying the Token Dynamics of Deep Selective State Space Models
Thieu Vo; Duy-Tung Pham; Xin T. Tong**; Tan M. Nguyen**
International Conference on Learning Representations (ICLR), 2025, Spotlight
Paper · Bibtex · Code
3. Equivariant Neural Functional Networks for Transformers
Viet-Hoang Tran*; Thieu Vo*; An Nguyen The*; Tho Tran Huu; Minh-Khoi Nguyen-Nhat; Thanh Tran; Duy-Tung Pham; Tan M. Nguyen
International Conference on Learning Representations (ICLR), 2025
Paper · Bibtex · Code
2. Out-of-vocabulary handling and topic quality control strategies in streaming topic models
Tung Nguyen*; Duy-Tung Pham*; Linh Ngo Van; Ha-Bang Ban; Khoat Than
Neurocomputing, 2025
Paper · Bibtex
1. NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization
Duy-Tung Pham*; Trang Nguyen*; Tung Nguyen*; Linh Ngo Van; Duc Anh Nguyen; Thien Huu Nguyen
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024, Findings
Paper · Bibtex · Code