MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation
Paper • 2610.41104 • Published • 11
Amit Chandak
chandakamit
·
AI & ML interests
Transformers, Mixture-Of-Experts, Ensembles
Recent Activity
upvoted a paper about 9 hours ago
MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation upvoted a paper 9 days ago
Function-Space Temporal Self-Distillation for Policy Optimization upvoted a paper 22 days ago
SALD: Self-Referenced Advantage Learning for Diffusion ModelsOrganizations
None yet