Reinforcement-aware Knowledge Distillation for LLM Reasoning

发布

2026年04月13日

采集 2026年04月13日 04:31

行业动态 8.4 分 — High-relevance AI research with significant insights or practical impact

原文： cs.LG updates on arXiv.org

评分 8.4 · 来源：cs.LG updates on arXiv.org · 发布于 2026-04-13

评分依据：High-relevance AI research with significant insights or practical impact

Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models

Large Reasoning Models Learn Better Alignment from Flawed Thinking