Research map / Vision-language and multimodal / Robot action and navigation
From Manuals to Actions: A Unified VLA Model for Chain-of-Thought Manual Generation and Robotic Manipulation
Chenyang Gu, Jiaming Liu, Hao Chen, Runzhong Huang, Qingpo Wuwu, Xiaoqi Li, Zhuoyang Liu, Ying Li, Renrui Zhang, Peng Jia, Pheng-Ann Heng, 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 Manual CoT with planning expert (ManualVLA) vs hierarchical VLM + pi0.5 | ManualVLA · 2D LEGO Assembly | success rate: 0.60 -> 0.85 | Improved |
| ManualVLA vs hierarchical baseline | ManualVLA · 3D LEGO Assembly | success rate: 0.35 -> 0.65 | Improved |
| ManualVLA vs hierarchical baseline | ManualVLA · Object Rearrangement | success rate: 0.50 -> 0.65 | Improved |
| ManualVLA vs goal-conditioned CoT-VLA | ManualVLA · 2D LEGO Assembly | success rate: 0.30 -> 0.85 | Improved |
| add more manual content (text, subgoal image, position) to the manual (ablation) | ManualVLA · 2D LEGO Assembly | success rate | Improved |
| add explicit CoT (visual-prompt image) to implicit CoT (ablation) | ManualVLA · 2D LEGO Assembly | success rate | Improved |
| add implicit CoT (latent manual features) to explicit CoT (ablation) | ManualVLA · 2D LEGO Assembly | success rate | Improved |
| use MoT (duplicate full transformer) instead of MoE (duplicate FFN only) (ablation) | ManualVLA · 2D LEGO Assembly | success rate | Improved |
| use diffusion-based action generation (ablation) | ManualVLA · 2D LEGO Assembly | success rate | Improved |
| unseen background | ManualVLA · 2D LEGO Assembly | success rate: 0.85 -> 0.65 (-23%) | Hurt |
| unseen object shape | ManualVLA · 2D LEGO Assembly | success rate: 0.85 -> 0.60 (-29%) | Hurt |
| unseen lighting | ManualVLA · 2D LEGO Assembly | success rate: 0.85 -> 0.70 (-17%) | Hurt |
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.
- CoT-VLA — CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models (CVPR 2025) · better on 3 of 3 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
- VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models (NeurIPS 2025 · similarity 0.93)
- DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge (NeurIPS 2025 · similarity 0.92)
- CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models (CVPR 2025 · similarity 0.91)
- ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning (NeurIPS 2026 · similarity 0.91)
- VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model (ICML 2026 · similarity 0.91)
- VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models (NeurIPS 2026 · similarity 0.91)
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.
