3rd Edition of Mathematics for and by Large Language Models

Contribution List

1. TBA

Quentin Berthet (Google DeepMind)

5/28/26, 9:30 AM

TBA

2. The Expressive Power of Large Language Models

Gabriel Peyré (CNRS, DMA, École Normale Supérieure)

5/28/26, 10:30 AM

Large language models process vast sequences of input tokens by alternating between classical multi-layer perceptron layers and self-attention mechanisms. While the approximation capabilities of perceptrons are relatively well understood, those of attention mechanisms remain less explored. In this talk, I will compare the proof techniques and approximation results associated with these two...

3. ReLU and Softplus Neural Nets as Zero-Sum, Turn-Based, Stopping Games

Yiannis Vlassopoulos (Athena Research Center & IHES)

5/28/26, 12:00 PM

Neural networks are for the most part treated as black boxes.
In an effort to understand the mathematical structure that underlies them we will explain how ReLU neural nets can be interpreted as zero-sum, turn-based, stopping games.

The game runs in the opposite direction to the net. The input to the net is the terminal reward of the game, the output of every neuron turns out to be equal...

4. Why AI Needs Formal Mathematics

Edward Lockhart (Google DeepMind)

5/28/26, 2:00 PM

Current reinforcement learning methods train Large Language Models to generate outputs that satisfy an automated judge. While this drives impressive feats of reasoning, it inadvertently incentivises the superficial appearance of correctness. Models may learn to "reward hack" by glossing over logical flaws or confidently making false claims.
In this talk, I will explore how some AI researchers...