Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning 事件

Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning arXiv:2601.14750v4 Announce Type: replace-cross Abstract: 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 p