Author name: Yu Pan, Andi Zhang, Yi Wang, Sibei Yang, Wenjie Wang

arXiv:2605.07399v2 Announce Type: replace
Abstract: Diffusion Vision-Language Models (dVLMs), built upon the non-causal foundations of Diffusion Large Language Models (dLLMs), have demonstrated remarkable efficacy in multimodal tasks by departing from…

arXiv:2605.07399v1 Announce Type: new
Abstract: Diffusion Vision-Language Models (dVLMs), built upon the non-causal foundations of Diffusion Large Language Models (dLLMs), have demonstrated remarkable efficacy in multimodal tasks by departing from the…