Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning
Paper • 2606.24133 • Published • 11
Adam M
r0b0tlab
AI & ML interests
None yet
Recent Activity
liked a model about 7 hours ago
tencent/Hy3 liked a model about 8 hours ago
SupraLabs/reasoning-summarizer-800m-pre liked a model about 8 hours ago
SupraLabs/Supra-Router-51MOrganizations
upvoted a paper 11 days ago