Algorithmic Thinking Theory for Foundation Models

Seminar

Speaker

  • Vincent Cohen-Addad Research Scientist at Google Research

When

  • – ET

Where

Flatiron Institute

162 5th Avenue

New York, NY 10010, United States

Title: Algorithmic Thinking Theory for Foundation Models

Abstract: The last few months have witnessed tremendous advances on Large Language Model (LLM) reasoning capabilities with Gemini and GPT winning a gold medal at the International Mathematical Olympiad (IMO) [1] and International Collegiate Programming Contest (ICPC) [2], and more recently to prove new theoretical computer science results [3]. Several papers have shown that inference scaling techniques significantly improve the reasoning performances of the LLM, in particular for the IMO [4]. We will discuss these results and how one can frame the problem as an optimization problem, relate it to empirical results shown in [4], and derive optimal (algorithmic) thinking strategies. We will also discuss avenues for refining the model and improving inference scaling methods.

A glowing blue sphere with a soft, fuzzy edge appears centered on a reddish-orange background.

Event Series

Machine Learning at the Flatiron Institute Seminar Series

ML@FI is focused on machine learning and its applications to science. Each seminar is followed by a reception to encourage cross-center interactions.

See events

More Events

Computational Biology

CCB Seminar: Avi Flamholz, Ph.D.

Seminar

December 2, 2026

11 a.m.–12 p.m. ET

Speaker

Avi Flamholz, Ph.D.

Computational Biology

CCB Seminar: Anand Srinivasan

Seminar

December 8, 2026

10–11:15 a.m. ET

Speaker

Anand Srinivasan

Speaker

Colin McManus, Ph.D.