arxiv:2402.00159
Xinxi Lyu
alrope
AI & ML interests
None yet
Recent Activity
upvoted a paper about 3 hours ago
Selecting Diverse SFT Traces Improves Post-RL Generalization upvoted a paper about 3 hours ago
Learning from Teacher Continuations at Student States updated a model 2 days ago
alrope/rexgradient_flex_from_avg_untrainedOrganizations
None yet