Every Token Needs Its Own Teacher Through Adaptive Multi-Teacher On-Policy Self-Distillation
Multi-teacher adaptive on-policy self-distillation lets each LLM token choose a teacher, improving Qwen3 math reasoning by up to 5.9 over base model.
Multi-teacher adaptive on-policy self-distillation lets each LLM token choose a teacher, improving Qwen3 math reasoning by up to 5.9 over base model.
EDEN is an LLM math post-training method that adds anchored Gaussian noise to prompt embeddings during RLVR rollouts. This creates directional variation instead of repeated near-identical samples, giv…