News

Sep 27, 2026 Our paper “Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework” was accepted as a poster at NeurIPS 2026, Sydney, Australia. Catch us at the poster session on Dec 10, 2026 (10:00 AM – 1:00 PM AEDT, Hall 1-4).
May 06, 2026 Started ongoing research on unsupervised reinforcement learning for LLM reasoning (submitted to NeurIPS’26).
Jun 01, 2025 Joined BRAC University as Adjunct Lecturer in the CSE department.
Apr 01, 2025 Joined ACI Ltd. as a part-time Machine Learning Engineer.