YanJiangJerry/Block-R1

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

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

[COLM 2026] Official repository of DARE: Diffusion Large Language Models Alignment and Reinforcement Executor

[Neurips 2026] Official repository for the paper "Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models"

[EMNLP 2026 (Oral)] Multi-Block Diffusion Language Models

RL with Experience Replay

ORL: On-Policy Residual Learning for Diffusion Language Models

Drift: DLM Reinforcement Learning Training Framework

Democratizing Reinforcement Learning for LLMs