Emu3: Next-Token Prediction is All You Need
By Xinlong Wang, Xiaosong Zhang, Zhengxiong Luo, Quan Sun, Yufeng Cui, Jinsheng Wang, Fan Zhang, Yueze Wang, Zhen Li, Qiying Yu and 15 more. arXiv.org, 2024
751 citations recorded by the source corpus.
While next-token prediction is considered a promising path towards artificial general intelligence, it has struggled to excel in multimodal tasks, which are still dominated by diffusion models (e.g., Stable Diffusion) and compositional approaches (e.g., CLIP combined with LLMs). In this paper, we introduce Emu3, a new suite of state-of-the-art multimodal models trained solely with next-token prediction. By tokenizing images, text, and videos into a discrete space, we train a single transformer from scratch on a mixture of multimodal sequences. Emu3 outperforms several well-established task-specific models in both generation and perception tasks, surpassing flagship models such as SDXL and LLaVA-1.6, while eliminating the need for diffusion or compositional architectures. Emu3 is also capable of generating high-fidelity video via predicting the next token in a video sequence. We simplify complex multimodal model designs by converging on a singular focus: tokens, unlocking great potential for scaling both during training and inference. Our results demonstrate that next-token prediction is a promising path towards building general multimodal intelligence beyond language. We open-source key techniques and models to support further research in this direction.
Subfields: Pulmonary and Respiratory Medicine
View Paper: https://www.semanticscholar.org/paper/3281d5a46c9de4f7d80c28f58f3aea03e445bd0a
Citations in the corpus
- CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models (2025, neutral): “Recent advances in unified multimodal models [55, 59, 63, 73] suggest promising directions for improvements.”
- Emerging Properties in Unified Multimodal Pretraining (2025, neutral): “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.”
- Infinity∞: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis (2024, neutral): “AutoRegressive models encounter significant challenges in high-resolution text-to-image synthesis[58, 70, 79].”