TBAC-UniImage: Unified Understanding and Generation by Ladder-Side Diffusion Tuning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xu, Junzhe, Yin, Yuyang, Chen, Xi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916897840168960
author Xu, Junzhe
Yin, Yuyang
Chen, Xi
author_facet Xu, Junzhe
Yin, Yuyang
Chen, Xi
contents This paper introduces TBAC-UniImage, a novel unified model for multimodal understanding and generation. We achieve this by deeply integrating a pre-trained Diffusion Model, acting as a generative ladder, with a Multimodal Large Language Model (MLLM). Previous diffusion-based unified models face two primary limitations. One approach uses only the MLLM's final hidden state as the generative condition. This creates a shallow connection, as the generator is isolated from the rich, hierarchical representations within the MLLM's intermediate layers. The other approach, pretraining a unified generative architecture from scratch, is computationally expensive and prohibitive for many researchers. To overcome these issues, our work explores a new paradigm. Instead of relying on a single output, we use representations from multiple, diverse layers of the MLLM as generative conditions for the diffusion model. This method treats the pre-trained generator as a ladder, receiving guidance from various depths of the MLLM's understanding process. Consequently, TBAC-UniImage achieves a much deeper and more fine-grained unification of understanding and generation.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08098
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TBAC-UniImage: Unified Understanding and Generation by Ladder-Side Diffusion Tuning
Xu, Junzhe
Yin, Yuyang
Chen, Xi
Computer Vision and Pattern Recognition
This paper introduces TBAC-UniImage, a novel unified model for multimodal understanding and generation. We achieve this by deeply integrating a pre-trained Diffusion Model, acting as a generative ladder, with a Multimodal Large Language Model (MLLM). Previous diffusion-based unified models face two primary limitations. One approach uses only the MLLM's final hidden state as the generative condition. This creates a shallow connection, as the generator is isolated from the rich, hierarchical representations within the MLLM's intermediate layers. The other approach, pretraining a unified generative architecture from scratch, is computationally expensive and prohibitive for many researchers. To overcome these issues, our work explores a new paradigm. Instead of relying on a single output, we use representations from multiple, diverse layers of the MLLM as generative conditions for the diffusion model. This method treats the pre-trained generator as a ladder, receiving guidance from various depths of the MLLM's understanding process. Consequently, TBAC-UniImage achieves a much deeper and more fine-grained unification of understanding and generation.
title TBAC-UniImage: Unified Understanding and Generation by Ladder-Side Diffusion Tuning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.08098