Class-frequency Guided Noise Schedule for Diffusion Models

arXiv:2607.06609v1 Announce Type: cross Abstract: We propose D2PO (Dynamic Direct Preference Optimization), a principled framework for optimizing diffusion sampling policies with

arXiv:2603.22364v1 Announce Type: cross Abstract: Diffusion models have achieved state-of-the-art performance in generative modeling, but their success often relies heavily on

arXiv:2610.14136v1 Announce Type: new Abstract: Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images

arXiv:2608.23807v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) can in principle generate text faster than autoregressive (AR) models, since they denoise

arXiv:2605.04215v1 Announce Type: cross Abstract: Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative AI, offering fully parallel token

arXiv:2604.09035v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) with autoregressive world models suffers from compounding errors, whereas diffusion world