Antoine Déchappe
About me
Latest research review
Learning without training:The implicit dynamics of in-context learning
Oct 16, 2025
Recent writing
Fix Intermittent uv 401 Errors with GCP Artifact Registry
Oct 28, 2025
Mocking UUIDs in Python Tests with a Generator
Jul 28, 2025
Beware of poetry package named differently from project structure
Mar 27, 2025
Antoine Déchappe
Blog
Research review
Projects
Bookmarks
Home
❯
Research review
❯
LLMs
❯
Training
Search
Search
Research review
LLMs
Training
Branch-Train-Merge: embarrassingly parallel training of expert Language Models
Smaller, weaker, yet better: training LLM reasoners via compute-optimal sampling
About me
