| library_name: transformers | |
| pipeline_tag: text-generation | |
| license: mit | |
| # GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models | |
| 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](https://huggingface.co/papers/2605.29398). | |
| 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. | |
| ## Resources | |
| - **Paper:** [GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models](https://arxiv.org/abs/2605.29398) | |
| - **GitHub Repository:** [GaryBall/GDSD](https://github.com/GaryBall/GDSD) | |
| ## Citation | |
| If you find GDSD helpful, please consider citing the following work: | |
| ```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}, | |
| } | |
| ``` |