让ViT直接预测文本，实现高效多模态预训练。
Let ViT Speak: Generative Language-Image Pre-training
- 用单个Transformer让ViT直接预测语言令牌，无需对比学习或额外解码器。
- 在80亿样本上训练，性能媲美甚至超过更强基线，数据量更少。
- 适合构建多模态大模型的视觉编码器，尤其擅长图表、文字识别等细节任务。
本文提出一种极简生成式多模态预训练框架GenLIP，专为视觉变换器（ViT）设计，用于多模态大语言模型（MLLMs）。为更好对齐视觉编码器与自回归语言模型的特性，GenLIP让ViT通过标准语言建模目标，直接从视觉令牌预测语言令牌，无需对比损失或额外文本解码器。该设计具有三大优势：（1）简洁性：单一Transformer联合建模视觉与文本令牌；（2）可扩展性：在数据和模型规模上均表现良好；（3）高性能：在多种多模态基准测试中达到或超越现有基线。在Recap-DataComp-1B的80亿样本上训练，即使使用远少于基线的数据量，仍取得优异效果。经过在原生长宽比多分辨率图像上的持续预训练，其在文字识别、图表理解等细节敏感任务中进一步提升，成为MLLM视觉编码器的理想基础。
原文摘要 · Abstract (English)
In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers (ViTs) designed for multimodal large language models (MLLMs). To better align vision encoders with the autoregressive nature of LLMs, GenLIP trains a ViT to predict language tokens directly from visual tokens using a standard language modeling objective, without contrastive batch construction or an additional text decoder. This design offers three key advantages: (1) \textbf{Simplicity}: a single transformer jointly models visual and textual tokens; (2) \textbf{Scalability}: it scales effectively with both data and model size; and (3) \textbf{Performance}: it achieves competitive or superior results across diverse multimodal benchmarks. Trained on 8B samples from Recap-DataComp-1B, GenLIP matches or surpasses strong baselines despite using substantially less pretraining data. After continued pretraining on multi-resolution images at native aspect ratios, GenLIP further improves on detail-sensitive tasks such as OCR and chart understanding, making it a strong foundation for vision encoders in MLLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。