Academic Engagements

Ahmad Beirami is an active researcher in AI, with contributions spanning foundational research to practical applications. His work has received multiple best paper awards, and he has delivered keynote talks at major venues. He has also organized workshops and tutorials, and served in leadership roles at leading conferences, including ACL and NeurIPS.

Selected Publications

• InfAlign: Inference-aware language model alignment — ICML 2025. A. Balashankar,* Z. Sun,* J. Berant, J. Eisenstein, M. Collins, A. Hutter, J. Lee, C. Nagpal, F. Prost, A. Sinha, A. T. Suresh, A. Beirami
• Safety alignment should be made more than just a few tokens deep — ICLR 2025 (Outstanding Paper Award). X. Qi, A. Panda, K. Lyu, X. Ma, S. Roy, A. Beirami, P. Mittal, P. Henderson
• Controlled decoding from language models — ICML 2024. S. Mudgal,* J. Lee,* H. Ganapathy, Y. Li, T. Wang, Y. Huang, Z. Chen, H. Cheng, M. Collins, T. Strohman, J. Chen, A. Beutel, A. Beirami
• SpecTr: Fast speculative decoding via optimal transport — NeurIPS 2023. Z. Sun,* A. T. Suresh,* J. H. Ro, A. Beirami, H. Jain, F. Yu
• On tilted losses in machine learning: Theory and applications — JMLR 2023. T. Li,* A. Beirami,* M. Sanjabi, V. Smith
• Know thy strengths: Comprehensive dialogue state tracking diagnostics — EMNLP 2022. H. Cho, C. Sankar, C. Lin, K Ram Sadagopan, S. Shayandeh, A. Celikyilmaz, J. May, A. Beirami
• Winning is not everything: enhancing game development with intelligent agents — IEEE Trans Games 2020 (Outstanding Paper Award). Y. Zhao,* I. Borovikov,* F. de Mesentier Silva,* A. Beirami,* J. Rupert, C. Somers, J. Harder, J. Kolen, J. Pinto, R. Pourabolghasem et al.

View full publication list on Google Scholar

Selected Keynote & Invited Talks

• Language model alignment: theory & practice (2024) — USC, NYU, Simons Institute, CRL Annual Symposium, Open AGI Symposium, University of Maryland, and workshops (NAACL, EACL, AAAI, etc.)
• Tutorial on Language Model Inference: Theory and Algorithms (2024) — ISIT 2024
• Information-Theoretic Methods for Trustworthy Machine Learning (2023) — Simons Institute

Selected Conference & Workshop Organization

• Machine Learning Paper Awards Session at ITA 2025
• NextGenAISafety @ ICML 2024 — Workshop on the Next Generation of AI Safety
• TF2M @ ICML 2024 — Workshop on Theoretical Foundations of Foundation Models
• R0-FoMo @ NeurIPS 2023 — Workshop on Robustness of Few-shot and Zero-shot Learning in Foundation Models
• TEACH @ ICML 2023 — Workshop on What’s left to TEACH chatbots?

Selected Editorial Service

• Senior Area Chair, EMNLP/ACL/NeurIPS/AISTATS (2024—2025)
• Associate Editor, IEEE Trans. Information Theory (2022—2024)