Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917549957971968 |
|---|---|
| author | Wang, Yifan Li, Shiyu Li, Peiming Yang, Xiaochen Tang, Yang Wei, Zheng |
| author_facet | Wang, Yifan Li, Shiyu Li, Peiming Yang, Xiaochen Tang, Yang Wei, Zheng |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_14750 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning Wang, Yifan Li, Shiyu Li, Peiming Yang, Xiaochen Tang, Yang Wei, Zheng Computation and Language Computer Vision and Pattern Recognition 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 |
| title | Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning |
| topic | Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.14750 |