arXiv:2603.10210v2 Announce Type: replace-cross
Abstract: While Diffusion Models excel in text-to-image synthesis, they frequently suffer from catastrophic concept omission when generating complex mu...
By Zitong Wang, Zijun Shen, Haohao Xu, Zhengjie Luo, Weibin Wu
The paper introduces Representation-based Masked Diffusion Model (RMDM), a new framework for language modeling that improves upon existing Masked Diffusion Models by incorporating global semantic guidance. RMDM encodes text into a continuous semantic space with a pretrained encoder, normalizes this representation to a Gaussian prior via an invertible transformation, and then trains a masked diffusion model conditioned on this latent representation to coordinate parallel token updates. Experiments show that RMDM yields higher generation quality, especially when using aggressive few‑step sampling.
By Yangrong Hu, Ding Huang, Xueyu Zhou, Jian Huang
Diffusion Language Models (DLMs) have recently achieved substantial progress in natural language generation tasks. Recent research demonstrates that adaptive token generation ordering can significantly improve performance in mathematical reasoning and code synthesis applications.
VISTA is a gradient‑based test‑time alignment framework designed for next‑scale visual autoregressive (VAR) image generation. It optimizes intermediate representations within the frozen transformer to enforce compositional constraints, without altering model weights or requiring extra training. Experiments on two benchmarks and two model scales show that VISTA improves compositional accuracy by up to 20% on a 2B backbone and 6% on an 8B backbone, while preserving image quality and enabling a smaller model to outperform a larger one.
By Hossein Shahabadi, Niki Sepasian, Mahdieh Soleymani Baghshah
arXiv:2607. 06445v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly utilized as the conditioning backbone for diffusion-based image editing due to their remarkable multimodal reasoning capabilities.
By Yoav Baron, Sara Dorfman, Roni Paiss, Daniel Cohen-Or, Or Patashnik
arXiv:2609.23717v1 Announce Type: new
Abstract: Global vision--language similarities compress an image and a caption into one vector, preserving semantics but not which word corresponds to which regi...
By Liuyang Song, Yi Zhang, Zhongyi Deng, Daqian Yang, Hongbo Zhang