AI RESEARCH
DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models
arXiv CS.CV
•
ArXi:2512.15713v3 Announce Type: replace Diffusion-based decoding has recently emerged as an appealing alternative to autoregressive (AR) generation, offering the potential to update multiple tokens in parallel and reduce latency. However, diffusion vision language models (dVLMs) still lag significantly behind mainstream autoregressive vision language models. This is due to the scarcity and weaker performance of base diffusion language models (dLLMs) compared with their autoregressive counterparts.