Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
By Chengyue Wu, Xiaokang Chen, Zhiyu Wu, Yiyang Ma, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, Chong Ruan and 1 more. Computer Vision and Pattern Recognition, 2024
446 citations recorded by the source corpus.
We introduce Janus, an autoregressive framework that unifies multimodal understanding and generation. Prior research often relies on a single visual encoder for both tasks, such as Chameleon. However, due to the differing levels of information granularity required by multimodal understanding and generation, this approach can lead to suboptimal performance, particularly in multimodal understanding. To address this issue, we decouple visual encoding into separate pathways, while still leveraging a single, unified transformer architecture for processing. The decoupling not only alleviates the conflict between the visual encoder’s roles in understanding and generation, but also enhances the framework’s flexibility. For instance, both the multi-modal understanding and generation components can independently select their most suitable encoding methods. Experiments show that Janus surpasses previous unified model and matches or exceeds the performance of task-specific models. The simplicity, high flexibility, and effectiveness of Janus make it a strong candidate for next-generation unified multimodal models. The code will be made available.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/b438a496045feccd1c028f1ce034062636a1ee04
Citations in the corpus
- Emerging Properties in Unified Multimodal Pretraining (2025, unknown): “Typical design choices for unified multi-modal generation and understanding models include: Quantized AR. Autoregressive visual generation [11, 48, 59, 70, 79, 83–85, 90 ] Unfortunately, the visual generation quality of autoregressive models is empirically inferior to diffusion-based models.”
- CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models (2025, unknown): “Recent advances in unified multimodal models [55, 59, 63, 73] suggest promising directions for improvements.”