I am working as an AI Engineer at Penta Global Limited, and was previously a research assistant at the Center for Computational & Data Sciences (CCDS), Independent University, Bangladesh. My research is in natural language processing, with a focus on LLM agents, LLM post-training, and the evaluation of language and vision-language models. Currently, I am working on reinforcement learning, adversarial policy optimization, and on-policy self-distillation for LLMs, especially in settings without labeled data. My work has been published at ACL, WACV and AACL.
Rafid Ahmed, Intesar Tahmid, Mir Sazzat Hossain, Tasnimul Hossain Tomal, Md Mahir Jawad, Anam Borhan Uddin, Md Fahim, Md Farhad Alam Bhuiyan
In Findings of the Association for Computational Linguistics: ACL 2026, pages 37362–37378, San Diego, California, United States. Association for Computational Linguistics.
Md Fahim, Md Farhan Ishmam, Mir Sazzat Hossain, M Ashraful Amin, Amin Ahsan Ali, AKM Rahman
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026, pp. 6496-6506.
Rafid Ahmed, Intesar Tahmid, Mir Sazzat Hossain, Tasnimul Hossain Tomal, Md Fahim, Md Farhad Alam Bhuiyan
Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare, PMLR 317:1-14, 2026.
Newaz Ben Alam, Akm Moshiur Rahman Mazumder, Mir Sazzat Hossain, Mysha Samiha, Md Alvi Noor Hossain, Md Fahim, Amin Ahsan Ali, Ashraful Islam, M Ashraful Amin, Akmmahbubur Rahman
In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 2178–2194, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.
How solvers and proof assistants check LLM reasoning: solver feedback on partial programs, formal logic checks inside a chain of thought, and LLM theorem provers for Lean, Isabelle and Coq that retrieve, search, repair and learn from the checker.
How outcome and process reward models judge reasoning: scoring the final answer or every step, where their step labels come from, why GRPO already contains one, how verifiers that write and run checks work, and how to train them with few or no labels.
