| --- |
| 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 (Guided Denoiser Self-Distillation), as presented in the paper [GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models](https://arxiv.org/abs/2605.29398). |
|
|
| GDSD is a reinforcement learning (RL) framework for diffusion large language models (dLLMs) that bypasses the intractability of policy likelihood. It distills the denoiser of dLLMs from an advantage-guided self-teacher derived from the closed-form optimum of reverse-KL regularized RL. This method avoids the Training-Inference Mismatch (TIM) biases common in ELBO-based approaches, leading to more stable training and improved performance on planning, math, and coding benchmarks. |
|
|
| - **Paper:** [https://arxiv.org/abs/2605.29398](https://arxiv.org/abs/2605.29398) |
| - **Repository:** [https://github.com/GaryBall/GDSD](https://github.com/GaryBall/GDSD) |
|
|
| ## Citation |
|
|
| If you find GDSD 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}, |
| } |
| ``` |
