AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning

Zhenghao Peng, Wenhao Ding, Yurong You, Yuxiao Chen, Wenjie Luo, Thomas Tian, Yulong Cao, Apoorva Sharma, Danfei Xu, Boris Ivanovic, Boyi Li, Yan Wang and 1 more

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 17 citations (OpenAlex)

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 meta-actions as intermediate representation (ablation)traj-only VLA · Internal driving val (no route)minADE: 0.9283 -> 0.8411Improved
add language reasoning supervision to meta-act (ablation)meta-act · Internal driving val (no route)minADE: 0.8411 -> 0.8021Improved
add counterfactual reasoning (round1) on top of meta-actmeta-act · Internal driving val (no route)minADE: 0.8411 -> 0.7650Improved
add counterfactual reasoning (round1) on top of meta-actmeta-act · Internal driving val (with route)minADE: 0.7263 -> 0.6712Improved
add counterfactual reasoning (round1) to meta-actmeta-act · Internal driving val (no route)collision rate: 0.0224 -> 0.0191Improved
add second round of counterfactual training (ablation)CF-VLA (with route) · Internal driving val (with route)avgADE: 1.4574 -> 1.3898Mixed
force reasoning on every sample (ablation)CF-VLA (adaptive) · Internal driving val (no route)minADE: 0.7650 -> 0.9319Hurt
let model decide when to think instead of never thinking (ablation)CF-VLA · Internal driving val (no route)minADE: 0.7897 -> 0.7650 (minADE); avgADE 1.4890 -> 1.5606Mixed
filter CF data by trajectory disagreement instead of using whole dataset (ablation)CF-VLA (with route) · Internal driving val (with route)minADE: 0.6811 -> 0.6712 (minADE); avgADE 1.4185 -> 1.4574Mixed
use CF editing of meta-actions instead of reusing filtered data as fixed meta-act labels (ablation)meta-act · Internal driving val (no route)minADE: 0.7906 -> 0.7650Improved
pre-fill ground-truth meta-actions (oracle) (ablation)meta-act · Internal driving val (no route)minADE: 0.8411 -> 0.4831Improved

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