<ul><li>Discrete Diffusion with Planned Denoising (DDPD) is a novel framework that achieves state-of-the-art performance in image and language modeling tasks.</li><li>DDPD separates the generation process into a planner and a denoiser model, enabling more efficient reconstruction by identifying and denoising corruptions in the optimal order.</li><li>DDPD outperforms traditional denoiser-only mask diffusion methods on language modeling benchmarks like text8 and OpenWebText, as well as token-based image generation on ImageNet.</li><li>DDPD reduces the performance gap between diffusion-based and autoregressive methods in the field of language modeling in terms of generative perplexity.</li></ul>

Think While You Generate: Discrete Diffusion with Planned Denoising

Discover more