Léo Martin
leo-mart
·
AI & ML interests
RLHF, RLAIF, offline RL, bandits
Recent Activity
upvoted a paper about 22 hours ago
Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models liked a dataset 3 days ago
jojo0217/korean_rlhf_dataset liked a model 3 days ago
Chaew00n/test-policy-optimizationOrganizations
None yet