yjyddq/DARE

[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Democratizing Reinforcement Learning for LLMs

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

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

AllenAI's post-training codebase

Drift: DLM Reinforcement Learning Training Framework

dLLM: Simple Diffusion Language Modeling

Easy and Efficient dLLM Fine-Tuning