Emu3.5: Native Multimodal Models are World Learners
📌 核心贡献
Emu3.5是一个大规模多模态世界模型，通过统一的下一个token预测目标，在万亿级视频数据上进行端到端预训练，原生实现视觉和语言间的下一状态预测。该模型通过大规模强化学习提升多模态推理能力，并引入离散扩散适应（DiDA）技术，将逐token解码转换为双向并行预测，显著加速图像推理。
📖 摘要
We introduce Emu3.5, a large-scale multimodal world model that natively predicts the next state across vision and language. Emu3.5 is pre-trained end-to-end with a unified next-token prediction objective on a corpus of vision-language interleaved data containing over 10 trillion tokens, primarily derived from sequential frames and transcripts of internet videos. The model naturally accepts interleaved vision-language inputs and generates interleaved vision-language outputs. Emu3.5 is further post-trained with large-scale reinforcement learning to enhance multimodal reasoning and generation. To improve inference efficiency, we propose Discrete Diffusion Adaptation (DiDA), which converts token-by-token decoding into bidirectional parallel prediction, accelerating per-image inference by about 20x without sacrificing performance. Emu3.5 exhibits strong native multimodal capabilities, including long-horizon vision-language generation, any-to-image (X2I) generation, and complex text-rich image generation. It also exhibits generalizable world-modeling abilities, enabling spatiotemporally consistent world exploration and open-world embodied manipulation across diverse scenarios and tasks. For comparison, Emu3.5 achieves performance comparable to Gemini 2.5 Flash Image (Nano Banana) on image generation and editing tasks and demonstrates superior results on a suite of interleaved generation tasks. We open-source Emu3.5 at https://github.com/baaivision/Emu3.5 to support community research.
🔍 关键信息
| 字段 | 内容 |
|---|---|
| 机构 | BAAI |
| 发表 | 2025-10-30 |
| 分类 | cs.CV |
| 链接 | arXiv |