Weak-to-Strong Generalization via Direct On-Policy Distillation
Paper • 2607.05394 • Published • 140
Eyot
Eyotoye
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 23 days ago
Weak-to-Strong Generalization via Direct On-Policy Distillation upvoted a paper 5 months ago
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation updated a model 8 months ago
SemiNAT/HAR_OMI2_2kOrganizations
