Privileged-information design shapes on-policy self-distillation gains
An error-step KL contrast predicted training gains better than a utility score that can leak information.
Stories per day · 30 days
3 RSS
2 stories, newest first · one card per story
Stories tagged #agentic-training
TokenRhythm/NeoHorse-1-9B — new model trending #30 on Hugging Face
TokenRhythm released NeoHorse-1-9B, an Apache-2.0 9B model post-trained from Qwen3.5-9B with routing-guided agentic post-training toward recursive self-improvement.
6