Trust-Region Behavior Blending for On-Policy Distillation
Paper • 2605.31159 • Published • 66
Dias Ilyas
diaslmb
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 10 days ago
Trust-Region Behavior Blending for On-Policy Distillation new activity 18 days ago
InflexionLab/VibeVoice-ASR-Kazakh:Transformers VibeVoice-ASR-HF adoption updated a dataset 20 days ago
diaslmb/KSC2Organizations
upvoted a paper 10 days ago