{"title":"WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokens","authors":"Jian Yang, Dacheng Yin, Xiaoxuan He, Xiao Song, Fengyun Rao, Jing Lyu, Wei Zhai, Yang Cao, Zheng-Jun Zha","doi":"10.48550/arxiv.2512.02536","DOIUrl":"https://doi.org/10.48550/arxiv.2512.02536","url":null,"abstract":"Recent progress in multimodal large language models (MLLMs) has highlighted the challenge of efficiently bridging pre-trained Vision-Language Models (VLMs) with Diffusion Models. While methods using a fixed number of learnable query tokens offer computational efficiency, they suffer from task generalization collapse, failing to adapt to new tasks that are distant from their pre-training tasks. To overcome this, we propose Noisy Query Tokens, which learn a distributed representation space between the VLM and Diffusion Model via end-to-end optimization, enhancing continual learning. Additionally, we introduce a VAE branch with linear projection to recover fine-grained image details. Experimental results confirm our approach mitigates generalization collapse and enables stable continual learning across diverse tasks.","PeriodicalId":522653,"journal":{"name":"ArXiv.org","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://arxiv.org/pdf/2512.02536","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147901006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}