This repository contains the model checkpoint for
GDSD (Guided Denoiser Self-Distillation), as introduced in the paper
GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models.
GDSD is a reinforcement learning (RL) framework designed to improve the denoiser of diffusion large language models (dLLMs). It reduces RL to a likelihood-free self-distillation objective by matching the dLLM's denoiser logits to an advantage-guided self-teacher. This approach bypasses the training–inference mismatch (TIM) biases common in ELBO-based methods and leads to more stable training dynamics.
1@misc{tang2026gdsdreinforcementlearningguided,
2 title={GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models},
3 author={Xiaohang Tang and Keyue Jiang and Che Liu and Qifang Zhao and Xiaoxiao Xu and Sangwoong Yoon and Ilija Bogunovic},
4 year={2026},
5 eprint={2605.29398},
6 archivePrefix={arXiv},
7 primaryClass={cs.LG},
8 url={https://arxiv.org/abs/2605.29398},
9}
