All news

3 articles

Min score

paperHugging Face Daily Papers·20 Oct 20263.6
AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics
Applies coding-agent post-training to agentic robotics.
robotics llm-post-training
paperarXiv (systems, data, ML)·23 Oct 20263.3
When to Follow the Teacher: Advantage-Based On-Policy Distillation
Advantage-based rule for when on-policy distillation should follow the teacher.
knowledge-distillation llm-post-training
paperarXiv (systems, data, ML)·22 Oct 20263.3
DIAL: Steerable Language Models with Distilled Instruction-Adherence Levels
DIAL distills controllable instruction-adherence levels into LLMs.
llm-post-training