AI Paper Atlas

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

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models

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 changedWhereMeasuredEffect
add visual affordance (ablation)CoA-VLA · LIBERO averagesuccess rate: 78.6 -> 79.8Improved
add textual affordance (ablation)CoA-VLA · LIBERO averagesuccess rate: 76.0 -> 79.8Improved
add dynamic affordance selection (ablation)CoA-VLA · LIBERO averagesuccess rate: 79.5 -> 79.8Improved
add dynamic affordance selection (ablation)CoA-VLA · LIBERO inference speedspeed (Hz): 1Hz -> 6HzImproved
chain-of-affordance reasoning vs vanilla reasoningDiffusionVLA · Real Franka in-distributionavg success rate: 76.60 -> 85.54Improved
chain-of-affordance reasoning vs vanilla reasoningDiffusionVLA · Real Franka visual generalizationavg success rate: 44.44 -> 57.14Improved
add CoA-VLA over OpenVLAOpenVLA · LIBERO averagesuccess rate: 76.5 -> 79.8Improved
dynamic selection on LIBERO-Long (ablation)CoA-VLA · LIBERO-Longsuccess rate: 55.2 -> 55.0No 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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy