| pipeline_tag: text-generation | |
| library_name: transformers | |
| # 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://huggingface.co/papers/2605.29398). | |
| Guided Denoiser Self-Distillation (GDSD) is a reinforcement learning framework for diffusion language models (dLLMs). It improves the denoiser of dLLMs by distilling from an advantage-guided self-teacher, bypassing the biases associated with evidence lower bound (ELBO) surrogates used in prior methods. GDSD provides a more stable and effective RL procedure, achieving significant performance gains on planning, math, and coding benchmarks. | |
| ## Resources | |
| - **Paper:** [GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models](https://arxiv.org/abs/2605.29398) | |
| - **GitHub Repository:** [https://github.com/GaryBall/GDSD](https://github.com/GaryBall/GDSD) | |
| ## Citation | |
| ```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}, | |
| } | |
| ``` |