AI Paper Atlas

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

Gripper-aware Vision Language Action Models

Hanyi Zhang, Zihong Luo, Tianyu Li, Khang Nguyen, Basu Hela, Shreyas Kumar, Ngoc Tran, Feng Dai, Charith Munasinghe, Jorge Queralta, Giovanni Toffetti, Khoa Vo and 7 more

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 0 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 gripper-aware tokenizer and dual MoA to pi0.5pi0.5 · MiGA sim averagesuccess rate: 58.38 -> 66.00Improved
add gripper-aware tokenizer and MoA to pi0pi0 · MiGA sim averagesuccess rate: 38.13 -> 48.13Improved
add GVLA to pi0 on flat taskspi0 · MiGA sim flatsuccess rate: 30.00 -> 27.50No clear effect
add GVLA to pi0.5 on flat taskspi0.5 · MiGA sim flatsuccess rate: 52.50 -> 53.00No clear effect
add GVLA to pi0.5 on stacked taskspi0.5 · MiGA sim stackedsuccess rate: 71.00 -> 76.00Improved
use multi-level tokenizer vs MLP embeddingsGVLA · tokenizer comparisonprediction error: 0.053 -> 0.032Improved
use multi-level tokenizer vs VQ-VAEGVLA · tokenizer comparisonCAPD: 0.70 -> 1.34Improved
add platform token (ablation)GVLA · unseen-gripper adaptationadaptation success: 0.54 -> 0.92Improved
add type token (ablation)GVLA · unseen-gripper adaptationadaptation success: 0.86 -> 0.92Improved
add instance token (ablation)GVLA · unseen-gripper adaptationadaptation success: 0.90 -> 0.92Improved
add dual MoA (ablation)GVLA · unseen-gripper adaptationadaptation success: 0.52 -> 0.92Improved
add dual MoA (ablation)GVLA · MiGAprediction error: 0.037 -> 0.032Improved

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