Post-Trained MoE Can Skip Half Experts via Self-Distillation
Paper • 2605.18643 • Published • 25
Hongyi Liu
hongyi-liu
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 9 hours ago
Post-Trained MoE Can Skip Half Experts via Self-Distillation authored a paper about 14 hours ago
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution upvoted a paper about 17 hours ago
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to EvolutionOrganizations
upvoted a paper about 9 hours ago
upvoted a paper about 17 hours ago
upvoted a paper 5 days ago
upvoted 4
papers 8 months ago
From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones
Paper • 2509.25123 • Published • 22
FlowRL: Matching Reward Distributions for LLM Reasoning
Paper • 2509.15207 • Published • 118
SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
Paper • 2509.09674 • Published • 81
A Survey of Reinforcement Learning for Large Reasoning Models
Paper • 2509.08827 • Published • 193