3rd Edition of Mathematics for and by Large Language Models

Liste des Contributions

1. MIND: Monge Inception Distance for Generative Models Evaluation

Quentin Berthet (Google DeepMind)

28/05/2026 09:30

We propose the Monge Inception Distance (MIND), a metric for evaluating generative models that addresses key limitations of the widely adopted Fréchet Inception Distance (FID). The MIND metric leverages the sliced Wasserstein distance to compare distributions by averaging one-dimensional optimal transport distances, efficiently computed via sorting. This approach circumvents the estimation of...

2. The Expressive Power of Large Language Models

Gabriel Peyré (CNRS, DMA, École Normale Supérieure)

28/05/2026 10:30

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)

28/05/2026 12:00

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)

28/05/2026 14:00

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...