Léo Martin
leo-mart
·
AI & ML interests
RLHF, RLAIF, offline RL, bandits
Recent Activity
liked a Space about 13 hours ago
huggingface-projects/Deep-Reinforcement-Learning-Leaderboard upvoted a paper about 13 hours ago
MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning upvoted a paper about 13 hours ago
Function-Space Temporal Self-Distillation for Policy OptimizationOrganizations
None yet