| library_name: transformers | |
| pipeline_tag: text-generation | |
| # GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models | |
| This repository contains the model weights for GDSD, as presented in the paper [GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models](https://arxiv.org/abs/2605.29398). | |
| Guided Denoiser Self-Distillation (GDSD) is a reinforcement learning (RL) framework tailored for diffusion large language models (dLLMs). It improves performance by directly distilling the denoiser from an advantage-guided self-teacher, bypassing the biases typically found in evidence lower bound (ELBO) based likelihood surrogates. | |
| ## Links | |
| - **Paper:** [arXiv:2605.29398](https://arxiv.org/abs/2605.29398) | |
| - **GitHub Repository:** [https://github.com/GaryBall/GDSD](https://github.com/GaryBall/GDSD) | |
| ## Citation | |
| If you find this work helpful, please consider citing: | |
| ```bibtex | |
| @misc{tang2026gdsdreinforcementlearningguided, | |
| title={GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models}, | |
| author={Xiaohang Tang and Keyue Jiang and Che Liu and Qifang Zhao and Xiaoxiao Xu and Sangwoong Yoon and Ilija Bogunovic}, | |
| year={2026}, | |
| eprint={2605.29398}, | |
| archivePrefix={arXiv}, | |
| primaryClass={cs.LG}, | |
| url={https://arxiv.org/abs/2605.29398}, | |
| } | |
| ``` |