Yi Hu (胡逸)
  • about
  • blog (current)
  • publications
  • slides
  • cv
  • submenus
    publications
    cv blog

调研 reasoning models 的推理机制

Created in April 13, 2025

2025   ·   reasoning   interpretability   ·   research-notes

调研 reasoning models 的推理机制。

paper list:

  • Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?



    Enjoy Reading This Article?

    Here are some more articles you might like to read next:

  • Reading Notes of "The Origin of Concepts"
  • Reading Notes: Attention Sinks in Language Models
  • Reading Notes: Layer Normalization in Transformers
  • Reading Notes: Latent Reasoning and Reinforcement Learning
  • Reading Notes: Latent Chain-of-Thought and Recurrent Computation
  • © Copyright 2026 Yi Hu. Powered by Jekyll with al-folio theme. Last updated: November 03, 2026.