Virgo：关于复现类o1多模态大语言模型的初步探索
Virgo: A Preliminary Exploration on Reproducing o1-like MLLM
AI总结：
本文通过少量文本长思维链数据微调多模态大语言模型，构建慢思考系统Virgo，发现文本推理数据比视觉推理数据更能激发慢思考能力，并证明该能力主要源于语言模型组件且可跨模态迁移。
摘要：
近年来，基于大语言模型（LLMs）构建的慢思考推理系统，通过在推理过程中扩展思考时间而受到广泛关注。将这种能力迁移到多模态大语言模型（MLLMs）的兴趣也日益增长。考虑到MLLMs需要处理跨模态的更复杂数据语义，实现多模态慢思考系统在直觉上更具挑战性。为了解决这一问题，本文探索了一种直接的方法：通过使用少量文本形式的长思维链数据微调一个能力较强的MLLM，从而构建出多模态慢思考系统Virgo（Visual reasoning with long thought，即“带长思考的视觉推理”）。我们发现，这些以自然语言表达的长形式推理过程可以有效地迁移到MLLMs中。此外，在激发MLLMs的慢思考能力方面，此类文本推理数据似乎比视觉推理数据更为有效。尽管这项工作尚属初步探索，但它表明慢思考能力从根本上与语言模型组件相关，并且可以跨模态或跨领域迁移。这一发现可用于指导更强大的慢思考推理系统的开发。我们在 https://github.com/RUCAIBox/Virgo 发布了相关资源。
英文摘要：
Recently, slow-thinking reasoning systems, built upon large language models (LLMs), have garnered widespread attention by scaling the thinking time during inference. There is also growing interest in adapting this capability to multimodal large language models (MLLMs). Given that MLLMs handle more complex data semantics across different modalities, it is intuitively more challenging to implement multimodal slow-thinking systems. To address this issue, in this paper, we explore a straightforward approach by fine-tuning a capable MLLM with a small amount of textual long-form thought data, resulting in a multimodal slow-thinking system, Virgo (Visual reasoning with long thought). We find that these long-form reasoning processes, expressed in natural language, can be effectively transferred to MLLMs. Moreover, it seems that such textual reasoning data can be even more effective than visual reasoning data in eliciting the slow-thinking capacities of MLLMs. While this work is preliminary, it demonstrates that slow-thinking capacities are fundamentally associated with the language model component, which can be transferred across modalities or domains. This finding can be leveraged to guide the development of more powerful slow-thinking reasoning systems. We release our resources at https://github.com/RUCAIBox/Virgo.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
