Bagel
📌 核心贡献
这篇论文介绍了BAGEL，一个开源的统一多模态基础模型，原生支持理解和生成。其创新之处在于，BAGEL是一个解码器专用模型，通过对万亿级别的交错文本、图像、视频和网络数据进行预训练，展现出卓越的新兴能力。
📖 摘要
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/
🔍 关键信息
| 字段 | 内容 |
|---|---|
| 机构 | |
| 发表 | 2025-05-20 |
| 分类 | cs.CV |
| 链接 | arXiv |
📝 我的笔记
🔗 相关论文
同方向： Chameleon, ILLUME, Transfusion, UniFluid