Large multimodal models (LMM) have recently shown encouraging progress with visual instruction tuning. In this note, we show that the fully-connected vision-language cross-modal connector in LLaVA is surprisingly powerful and data-efficient. With simple modifications to LLaVA, namely, using CLIP-ViT-L-336px with an MLP projection and adding academic-task-oriented VQA data with simple response formatting prompts, we establish stronger baselines that achieve state-of-the-art across 11 benchmarks. Our final 13B checkpoint uses merely 1.2M publicly available data, and finishes full training in ~1 day on a single 8-A100 node. We hope this can make state-of-the-art LMM research more accessible. Code and model will be publicly available.

翻译：大型多模态模型（LMM）近期通过视觉指令微调展现出令人鼓舞的进展。本文表明，LLaVA中全连接视觉-语言跨模态连接器具有惊人的强大性能和高效的数据利用率。通过对LLaVA进行简单改进，即采用带MLP投影的CLIP-ViT-L-336px，并添加面向学术任务的VQA数据及简单响应格式化提示，我们建立了更强的基线，在11项基准测试中达到最优性能。最终13B检查点仅使用1.2M公开数据，在单台8-A100节点上完成全部训练约需1天。我们期望这能促进最优LMM研究的更广泛可及性。代码和模型将公开提供。