Research map / Vision-language and multimodal / Robot action and navigation
Action-Sketcher: From Reasoning to Action via Visual Sketches for Robotic Manipulation
Huajie Tan, Peterson Co, Yijie Xu, Shanyu Rong, Yuheng Ji, Cheng Chi, Xiansheng Chen, Zhongxia Zhao, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Visual Sketch (ablation) | Action-Sketcher · RoboTwin Stack Blocks | success rate: 9.8 -> 34.5 | Improved |
| add spatial reasoning (ablation) | Action-Sketcher · RoboTwin Stack Blocks | success rate: 13.8 -> 34.5 | Improved |
| add keypoint primitives (ablation) | Action-Sketcher · RoboTwin Stack Blocks | success rate: 26.6 -> 34.5 | Improved |
| add bounding box primitives (ablation) | Action-Sketcher · RoboTwin Stack Blocks | success rate: 31.2 -> 34.5 | Improved |
| add arrow primitives (ablation) | Action-Sketcher · RoboTwin Stack Blocks | success rate: 29.9 -> 34.5 | Improved |
| include Stage 1 pretraining (ablation) | Action-Sketcher · RoboTwin Stack Blocks | success rate: 29.2 -> 34.5 | Improved |
| include Stage 2 reasoning fine-tuning (ablation) | Action-Sketcher · RoboTwin Stack Blocks | success rate: 18.1 -> 34.5 | Improved |
| include Stage 3 adaptation (ablation) | Action-Sketcher · RoboTwin Stack Blocks | success rate: 0.0 -> 34.5 | Improved |
| human-in-the-loop sketch correction | Action-Sketcher · Real-world Tidy Table | subtask completion: 52.0 -> 75.0 | Improved |
| human-in-the-loop sketch correction | Action-Sketcher · Real-world Pour Tea | subtask completion: 27.6 -> 44.0 | Improved |
| use Visual Sketch VLA vs OpenVLA-OFT | Action-Sketcher · LIBERO-Long | success rate: 94.5 -> 96.0 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PixelVLA — PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model (ICLR 2026) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Robotic Visual Instruction (CVPR 2025 · similarity 0.92)
- TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies (ICLR 2025 · similarity 0.90)
- Localizing, Structuring, and Rendering: Bridging 3D and 2D Vision-Language-Action Models for Robotic Manipulation (CVPR 2026 · similarity 0.90)
- ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning (NeurIPS 2025 · similarity 0.89)
- Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes (ICLR 2026 · similarity 0.89)
- Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulation (CVPR 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
