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.

翻译：本文提出\textbf{生成式语言-图像预训练}（GenLIP），一个专为多模态大语言模型（MLLMs）设计的视觉Transformer（ViT）极简生成式预训练框架。为了更好地对齐视觉编码器与大语言模型的自回归特性，GenLIP采用标准语言建模目标，训练ViT直接从视觉标记预测语言标记，无需对比批量构建或额外文本解码器。该设计具备三大核心优势：（1）\textbf{简洁性}：单个Transformer联合建模视觉与文本标记；（2）\textbf{可扩展性}：有效随数据量与模型规模扩展；（3）\textbf{性能}：在多样化的多模态基准测试中达到或超越现有方法。基于Recap-DataComp-1B数据集的8B样本训练后，GenLIP在使用显著更少预训练数据的情况下仍能匹配或超越强基线模型。经持续预训练（采用原生宽高比的多分辨率图像），GenLIP进一步提升了OCR与图表理解等细节敏感任务的性能，成为MLLMs视觉编码器的强大基础。