Research map / Vision-language and multimodal / Robot action and navigation
CoA-VLA: Improving Vision-Language-Action Models via Visual-Text Chain-of-Affordance
Jinming Li, Yichen Zhu, Zhibin Tang, Junjie Wen, Minjie Zhu, Xiaoyu Liu, Chengmeng Li, Ran Cheng, Yaxin Peng, Yan Peng, Feifei Feng
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 affordance (ablation) | CoA-VLA · LIBERO average | success rate: 78.6 -> 79.8 | Improved |
| add textual affordance (ablation) | CoA-VLA · LIBERO average | success rate: 76.0 -> 79.8 | Improved |
| add dynamic affordance selection (ablation) | CoA-VLA · LIBERO average | success rate: 79.5 -> 79.8 | Improved |
| add dynamic affordance selection (ablation) | CoA-VLA · LIBERO inference speed | speed (Hz): 1Hz -> 6Hz | Improved |
| chain-of-affordance reasoning vs vanilla reasoning | DiffusionVLA · Real Franka in-distribution | avg success rate: 76.60 -> 85.54 | Improved |
| chain-of-affordance reasoning vs vanilla reasoning | DiffusionVLA · Real Franka visual generalization | avg success rate: 44.44 -> 57.14 | Improved |
| add CoA-VLA over OpenVLA | OpenVLA · LIBERO average | success rate: 76.5 -> 79.8 | Improved |
| dynamic selection on LIBERO-Long (ablation) | CoA-VLA · LIBERO-Long | success rate: 55.2 -> 55.0 | No clear effect |
Later papers that compared with this method
1 later accepted paper reports CoA-VLA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation (CVPR 2026 · better on 1 of 1 shared result)
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
- CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models (CVPR 2025 · similarity 0.91)
- Beyond Data Scaling: Representation-Centric Pre-training for Vision-Language-Action Models (NeurIPS 2026 · similarity 0.91)
- FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies (NeurIPS 2026 · similarity 0.91)
- PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models (NeurIPS 2026 · similarity 0.90)
- Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes (ICLR 2026 · similarity 0.90)
- UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent (ICML 2025 · similarity 0.90)
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.
