L'objectif est de lire, d'apprendre et de partager les connaissances sur la recherche de base en AI. Voici en gros le programme que nous allons avoir durant 9 semaines:

1.  Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
2. LLM4Decompile: Decompiling Binary Code with Large Language Models
3. Data Formulator 2: Iteratively Creating Rich Visualizations with AI
4. Cut Your Losses in Large-Vocabulary Language Models
5. Magic 1-For-1: Generating One Minute Video Clips within One Minute
6. OmniParser for Pure Vision Based GUI Agent
7. PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
8. Flaming-hot Initiation with Regular Execution Sampling for Large Language Models