Trust-Region Behavior Blending for On-Policy Distillation
Paper • 2605.31159 • Published • 69
Dias Ilyas
diaslmb
·
AI & ML interests
None yet
Recent Activity
liked a model 12 days ago
nur-dev/kk-ru-asr-tdt-accuracy liked a model 12 days ago
AMAImedia/NOESIS-OmniAudio-1B-Darwin-Sozkz-KZ-RU-BF16 upvoted a paper 2 months ago
Trust-Region Behavior Blending for On-Policy DistillationOrganizations
upvoted a paper 2 months ago