Nebularaid2000/rethink_sft_generalization

Fully open reproduction of DeepSeek-R1

Fully open data curation for reasoning models

Official code for Fold2Reason: Enhancing general reasoning in language models through protein-structure post-training.

A curated atlas of post-training reasoning data, verifiers, and recipes. Based on the paper: A Primer in Post-Training Reasoning Data. https://arxiv.org/abs/2606.02113. Project development team: Peking University、Tsinghua University.

✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models

Awesome paper list for reasoning generalization in LLMs.

[ICLR 2026] SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs

[NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.

Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"