logo
today local_bar

Trung Le

Assistant Professor, Monash University

3 papers at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 3

2 papers
Thursday, December 4, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise
#700 · Haocheng Luo, Mehrtash Harandi, Dinh Phung, Trung Le
Geometry-Aware Collaborative Multi-Solutions Optimizer for Model Fine-Tuning with Parameter Efficiency
#502 · Van-Anh Nguyen, Trung Le, Mehrtash Harandi, Ehsan Abbasnejad, Thanh-Toan Do, Dinh Phung

Poster Session 6

1 paper
Friday, December 5, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Token-Level Self-Play with Importance-Aware Guidance for Large Language Models
#3309 · Tue Le, Hoang Tran Vuong, Quyen Tran, Linh Ngo Van, Mehrtash Harandi, Trung Le

We introduce SWIFT, a token-level self-alignment and distillation method that improves LLMs by assigning token weights via a teacher model