How Much Training-Inference Mismatch Can On-Policy Distillation Tolerate?
Paper • 2611.11450 • Published • 8
Yang Shaofang
shaofang-1007
AI & ML interests
None yet
Recent Activity
upvoted a paper about 6 hours ago
How Much Training-Inference Mismatch Can On-Policy Distillation Tolerate?Organizations
None yet
upvoted a paper about 6 hours ago