研究人员开发了一种新的参数高效微调技术，用于多模态大语言模型，称为ART（基于艺术的强化训练）。与修改计算图的现有方法不同，ART仅优化冻结模型的原始视觉输入。这种方法允许在预编译的高吞吐量引擎上进行微调，并将优化后的视觉输入风格化为计算艺术品。ART在数学和结构化工具使用基准测试中已显示出与LoRA相当的准确性，证实了其在各种Qwen模型尺寸上的有效性。 AI
影响 能够更有效地微调多模态模型，可能加速开发和部署。
排序理由 该集群包含一篇详细介绍微调多模态大语言模型新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2606.11854v1 Announce Type: cross Abstract: There are two main Parameter-Efficient Fine-Tuning (PEFT) techniques for Large Language Models (LLMs). While Low-Rank Adaptation (LoRA) introduces additional weights between the LLM layers, Soft Prompting introduces additional fin…
There are two main Parameter-Efficient Fine-Tuning (PEFT) techniques for Large Language Models (LLMs). While Low-Rank Adaptation (LoRA) introduces additional weights between the LLM layers, Soft Prompting introduces additional fine-tuning-specific raw tokens to an LLM input. Howe…
ART enables parameter-efficient fine-tuning of frozen multimodal language models by optimizing raw visual input through gradient backpropagation, achieving performance comparable to LoRA while supporting pre-compiled computational graphs.