Phuc Nguyen

Phuc Minh Nguyen

Reinforcement learning, language models, and reasoning.

Hi, I’m Phuc, a CS PhD student at the University of Notre Dame adavised by Prof. Nitesh V. Chawla. Previously, I was a Research Assistant at VinUniversity, advised by Prof. Khoa D. Doan. My research interest:

  1. Reinforcement learning and post-training for language models
  2. Scaling laws for RL post-training.
  3. Understanding Pre-training behavior.

Selected Publications

On the Primacy Bias in RLVR Training

On the Primacy Bias in RLVR Training

Phuc Minh Nguyen, Ngoc-Hieu Nguyen, Parshin Shojaee, Chinh Duc La, Duy Minh Ho Nguyen, Rui Zhang, Khoa D Doan, Ting Hua, Nitesh V. Chawla.

NeurIPS 2026

Poster

BibTeX

@inproceedings{
anonymous2026on,
title={On the Primacy Bias in {RLVR} Training},
author={Anonymous},
booktitle={The Fortieth Annual Conference on Neural Information Processing Systems},
year={2026},
url={https://openreview.net/forum?id=iYqWuTaHph}
}
The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models

The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models

Phuc Minh Nguyen, Chinh Duc La, Duy Minh Ho Nguyen, Nitesh V. Chawla, Binh Nguyen, Khoa D. Doan

NeurIPS 2026

Poster

BibTeX

@inproceedings{
anonymous2026the,
title={The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models},
author={Anonymous},
booktitle={The Fortieth Annual Conference on Neural Information Processing Systems},
year={2026},
url={https://openreview.net/forum?id=gIIcM35wXp}
}
Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road

Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road

Ngoc-Hieu Nguyen, Parshin Shojaee, Phuc Minh Nguyen, Nan Zhang, Chandan K. Reddy, Khoa D Doan, Rui Zhang

COLM 2026

Poster

BibTeX

@inproceedings{
nguyen2026why,
title={Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road},
author={Ngoc-Hieu Nguyen and Parshin Shojaee and Nguyen Minh Phuc and Nan Zhang and Chandan K. Reddy and Khoa D Doan and Rui Zhang},
booktitle={Third Conference on Language Modeling},
year={2026},
url={https://openreview.net/forum?id=ivza8JIW9s}
}
Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling

Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling

Phuc Minh Nguyen, Ngoc-Hieu Nguyen, Duy H. M. Nguyen, Anji Liu, An Mai, Binh T. Nguyen, Daniel Sonntag, Khoa D. Doan

NeurIPS 2025

Poster

BibTeX

@inproceedings{
phuc2025mitigating,
title={Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling},
author={Nguyen Minh Phuc and Ngoc-Hieu Nguyen and Duy Minh Ho Nguyen and Anji Liu and An Mai and Binh T. Nguyen and Daniel Sonntag and Khoa D Doan},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=ltPRj2nthL}
}