Mathematics for an by Large Language Models – 2025 Edition

Collection Mathematics for an by Large Language Models – 2025 Edition

Organizer(s) François Charton, Michael Douglas, Amaury Hayat, Yiannis Vlassopoulos

Date(s) 22/05/2025 - 22/05/2025

linked URL https://indico.math.cnrs.fr/event/14253/

00:00:00 / 00:00:00

5 6

Universal Optimal Control, Reinforcement Learning, and Reaching Goals in LLMs

By Yann Ollivier

Information about the video

Date of recording 22/05/2025
Date of publication 30/05/2025
Institution IHES
Language English
Audience Researchers
Format MP4

Domain(s)

Last related questions on MathOverflow

You have to connect your Carmin.tv account with mathoverflow to add question

Ask a question on MathOverflow

All the collection videos

56:56

published on May 30, 2025

Project Numina and AI for Theorem Proving

By Yann Fleureau

47:17

published on June 23, 2025

Deciding What Game to Play, What Mathematics Problem to Solve

By Katie Collins

54:01

published on May 27, 2025

Why are LLMs not Better at Finding Proofs?

By Timothy Gowers

55:16

published on June 23, 2025

Machine Learning in PDE: Discovering New, Unstable Solutions

By Javier Gómez-Serrano

54:02

published on May 30, 2025

Universal Optimal Control, Reinforcement Learning, and Reaching Goals in LLMs

By Yann Ollivier

53:39

published on May 30, 2025

Search, Reason or Recombine? Paradigms for Scaling Formal Proving

By Fabian Glöckle

Copyright Carmin.tv 2025

Give feedback