y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#graph-topology News & Analysis

1 article tagged with #graph-topology. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

1 articles
AINeutralarXiv – CS AI · 3h ago6/10
🧠

RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs

Researchers present a novel framework analyzing how reinforcement learning (RL) and supervised fine-tuning (SFT) differently shape reasoning in large language models. The study reveals that RL compresses incorrect reasoning paths while SFT expands correct ones, explaining why the two-stage training approach produces superior reasoning capabilities across models of 1.5B to 14B parameters.