Emerging Properties in Unified Multimodal Pretraining
This work addresses the need for open-source, unified multimodal models to facilitate research, though it is incremental as it builds on existing paradigms.
The authors tackled the problem of unifying multimodal understanding and generation by introducing BAGEL, an open-source foundational model pretrained on trillions of tokens from diverse interleaved data, which significantly outperforms existing open-source unified models in multimodal generation and understanding across benchmarks.
Unifying multimodal understanding and generation has shown impressive capabilities in cutting-edge proprietary systems. In this work, we introduce BAGEL, an open-source foundational model that natively supports multimodal understanding and generation. BAGEL is a unified, decoder-only model pretrained on trillions of tokens curated from large-scale interleaved text, image, video, and web data. When scaled with such diverse multimodal interleaved data, BAGEL exhibits emerging capabilities in complex multimodal reasoning. As a result, it significantly outperforms open-source unified models in both multimodal generation and understanding across standard benchmarks, while exhibiting advanced multimodal reasoning abilities such as free-form image manipulation, future frame prediction, 3D manipulation, and world navigation. In the hope of facilitating further opportunities for multimodal research, we share the key findings, pretraining details, data creation protocal, and release our code and checkpoints to the community. The project page is at https://bagel-ai.org/