Repo for paper Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability.
Qihan Ren
jasonrqh
AI & ML interests
explainable AI, LLM
Recent Activity
liked a dataset 1 day ago
jasonrqh/Math-CoT-20k liked a dataset 1 day ago
jasonrqh/Math-CoT-44k-Qwen3-32b-n32-16384-with-logprob-and-entropy authored a paper 1 day ago
Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration?