Léo Martin
leo-mart
·
AI & ML interests
RLHF, RLAIF, offline RL, bandits
Recent Activity
liked a dataset about 17 hours ago
jojo0217/korean_rlhf_dataset liked a model about 17 hours ago
Chaew00n/test-policy-optimization upvoted a paper about 17 hours ago
WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent StateOrganizations
None yet