UniVLR: 统一文本与视觉的视觉潜在推理用于多模态大语言模型
UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
AI总结：
UniVLR提出一种统一的视觉潜在推理框架，将文本推理和辅助视觉证据视为共享的视觉工作空间，通过压缩统一表示提升多模态大语言模型的视觉推理效率。
摘要：
多模态大语言模型日益被期望能够进行图像思考，但现有视觉潜在推理方法仍依赖于显式文本链式思维与视觉潜在标记的交替。这种交替设计限制了效率，并使推理在文本和视觉通道之间碎片化。我们提出UniVLR，一种统一的视觉潜在推理框架，将文本推理和辅助视觉证据视为共享的视觉工作空间。而不是将文本CoT作为独立的推理路径保留，UniVLR将推理痕迹与辅助图像一起渲染，并学习将这种统一的表示压缩成紧凑的视觉潜在标记。在推理过程中，模型仅通过视觉潜在标记进行推理，并直接解码最终答案，避免了外部工具调用和冗长的文本推理。在真实世界感知和视觉推理任务上的实验表明，UniVLR在使用显著更少生成推理标记的情况下优于先前的视觉潜在推理方法，表明了一种更统一和高效的多模态大语言模型视觉思考范式。
英文摘要：
Multimodal large language models are increasingly expected to perform thinking with images, yet existing visual latent reasoning methods still rely on explicit textual chain-of-thought interleaved with visual latent tokens. This interleaved design limits efficiency and keeps reasoning fragmented across separate text and vision channels. We propose UniVLR, a unified visual latent reasoning framework that treats textual reasoning and auxiliary visual evidence as a shared visual workspace. Instead of preserving text CoT as an independent inference-time path, UniVLR renders reasoning traces together with auxiliary images and learns to compress this unified representation into compact visual latent tokens. At inference time, the model reasons only through visual latents and directly decodes the final answer, avoiding both external tool calls and verbose text reasoning. Experiments on real-world perception and visual reasoning tasks show that UniVLR outperforms prior visual latent reasoning methods while using substantially fewer generated reasoning tokens, suggesting a more unified and efficient paradigm for visual thinking in MLLMs.
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。
