UniCom: Unified Multimodal Modeling via Compressed Continuous Semantic Representations

TL;DR

UniCom introduces a novel unified multimodal framework that uses compressed continuous semantic representations to improve understanding and generation, outperforming existing models in quality, controllability, and training stability.

Contribution

It proposes a semantic compressor and a transfusion architecture to effectively unify multimodal modeling, addressing limitations of discrete tokenizers and high-dimensional continuous representations.

Findings

Achieves state-of-the-art generation performance among unified models.

Demonstrates superior controllability in image editing tasks.

Maintains image consistency without VAE.

Abstract

Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual understanding tasks. Conversely, directly modeling continuous semantic representations (e.g., CLIP, SigLIP) poses significant challenges in high-dimensional generative modeling, resulting in slow convergence and training instability. To resolve this dilemma, we introduce UniCom, a unified framework that harmonizes multimodal understanding and generation via compressed continuous representation. We empirically demonstrate that reducing channel dimension is significantly more effective than spatial downsampling for both reconstruction and generation. Accordingly, we design an attention-based semantic compressor to distill dense features into a compact unified representation. Furthermore, we validate that the transfusion architecture surpasses query-based designs in convergence and consistency. Experiments demonstrate that UniCom achieves state-of-the-art generation performance among unified models. Notably, by preserving rich semantic priors, it delivers exceptional controllability in image editing and maintains image consistency even without relying on VAE.