Render-of-Thought: 将文本思维链渲染为图像以进行视觉潜在推理
Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning
AI总结：
提出Render-of-Thought框架，通过将思维链的文本步骤渲染为图像，利用视觉语言模型的视觉编码器进行语义对齐，实现3-4倍令牌压缩和推理加速，同时保持竞争性能。
摘要：
思维链提示在解锁大型语言模型的推理能力方面取得了显著成功。尽管思维链提示增强了推理能力，但其冗长性带来了巨大的计算开销。最近的工作通常只关注结果对齐，缺乏对中间推理过程的监督。这些缺陷掩盖了潜在推理链的可分析性。为了解决这些挑战，我们引入了Render-of-Thought，这是第一个通过将文本步骤渲染为图像来具体化推理链的框架，使潜在推理过程显式且可追溯。具体来说，我们利用现有视觉语言模型的视觉编码器作为语义锚点，将视觉嵌入与文本空间对齐。这种设计确保了即插即用的实现，而无需额外的预训练开销。在数学和逻辑推理基准上的大量实验表明，与显式思维链相比，我们的方法实现了3-4倍的令牌压缩和显著的推理加速。此外，它与其他方法相比保持了竞争性能，验证了这种范式的可行性。我们的代码可在https://github.com/TencentBAC/RoT获取。
英文摘要：
Chain-of-Thought (CoT) prompting has achieved remarkable success in unlocking the reasoning capabilities of Large Language Models (LLMs). Although CoT prompting enhances reasoning, its verbosity imposes substantial computational overhead. Recent works often focus exclusively on outcome alignment and lack supervision on the intermediate reasoning process. These deficiencies obscure the analyzability of the latent reasoning chain. To address these challenges, we introduce Render-of-Thought (RoT), the first framework to reify the reasoning chain by rendering textual steps into images, making the latent rationale explicit and traceable. Specifically, we leverage the vision encoders of existing Vision Language Models (VLMs) as semantic anchors to align the vision embeddings with the textual space. This design ensures plug-and-play implementation without incurring additional pre-training overhead. Extensive experiments on mathematical and logical reasoning benchmarks demonstrate that our method achieves 3-4x token compression and substantial inference acceleration compared to explicit CoT. Furthermore, it maintains competitive performance against other methods, validating the feasibility of this paradigm. Our code is available at https://github.com/TencentBAC/RoT
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。
