Antoine Déchappe
About me
Latest research review
Benchmarks saturate when the model gets smarter than the judge
Mar 07, 2026
Recent writing
On This Day - Introduction
Jul 24, 2026
How to correctly type a Python function that returns an instance of a Pydantic class passed as an argument?
Dec 04, 2025
Efficient LLMs in production
Nov 27, 2025
Antoine Déchappe
Blog
Research review
Projects
Bookmarks
Home
❯
Research review
❯
Deep Learning
Search
Search
Research review
Deep Learning
Averaging weights leads to wider optima and better generalization
Distilling the knowledge in a neural network
Effect of the initial configuration of weights on the training and function of artificial neural networks
About me
