SJTU-DENG-Lab/LightningRL-8B-b32-HumanEval

Diffusion Large Language Models with a SOTA Accuracy–Parallelism Trade-off

We introduce LightningRL, a reinforcement learning post-training framework for block-wise diffusion Large Language Models (dLLMs) that breaks the accuracy–parallelism trade-off. Applied to SDAR-8B, LightningRL achieves 7.32 average TPF and 497.9 AUP — simultaneously improving both generation quality and inference speed.

• LightningRL-8B-32b-MATH500, LightningRL-8B-32b-GSM8K, LightningRL-8B-32b-MBPP, and LightningRL-8B-32b-HumanEval are task-specific variants fine-tuned with different reward weight configurations for targeted deployment.

Citation

@article{hu2026lightningrl,
  title={LightningRL: Breaking the Accuracy--Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning},
  author={Hu, Yanzhe and Jin, Yijie and Liu, Pengfei and Yu, Kai and Deng, Zhijie},
  journal={arXiv preprint},
  year={2026},
  note={Coming soon}
}