Ao Yu
YongYuanDeAo
AI & ML interests
None yet
Recent Activity
authored a paper about 1 month ago
DuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation upvoted a paper about 2 months ago
DuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation upvoted a paper 3 months ago
Learning beyond Teacher: Generalized On-Policy Distillation with Reward ExtrapolationOrganizations
None yet