Pavel Izmailov is an Assistant Professor in Computer Science and Engineering at New York University and a Researcher at Anthropic. His work focuses on reasoning, AI for science, AI alignment, reinforcement learning, planning and search, interpretability, and robustness in machine learning. Previously, he worked on language-model reasoning and weak-to-strong generalization at OpenAI.
Pavel Izmailov is an Assistant Professor in Computer Science and Engineering at New York University and a Researcher at Anthropic. His work focuses on reasoning, AI for science, AI alignment, reinforcement learning, planning and search, interpretability, and robustness in machine learning. Previously, he worked on language-model reasoning and weak-to-strong generalization at OpenAI.
Career
Pavel Izmailov studied at New York University (Ph.D. in Computer Science), Cornell University (M.Sc. in Operations Research and Information Engineering), and Lomonosov Moscow State University (B.Sc. in Applied Mathematics and Computer Science).