arXiv cs.AI / cs.LG / cs.CL·1d agoComposing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts#distillation#on-policy#multi-teacherAI research 2 sources1
Hugging Face daily papers·8d agoFrom Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation#distillation#qwen3#on-policy
Hugging Face daily papers·8d agoLatent-MOPD: Latent Multi-Teacher On-Policy Distillation#distillation#on-policy#multi-teacher
Hugging Face daily papers·11d agoBeyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation#distillation#multi-teacher#qwen3.5
Hugging Face daily papers·11d agoPMOPD: Task Ordering, Cycling, and Parameter-Update Subspace Protection in Multi-Teacher On-Policy Distillation#distillation#on-policy#multi-teacher
Hugging Face daily papers·14d agoMOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation#distillation#multi-teacher#on-policy