AI Paper Atlas

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

AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention

Lei Xiao, Jifeng Li, Juntao Gao, Feiyang Ye, Yan Jin, Jingjing Qian, Jing Zhang, Yong Wu, Xiaoyuan Yu

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 20 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 AVA-VLA (recurrent state + active visual attention)OpenVLA-OFT · LIBERO (one policy for all 4 suites)success rate (%): 96.8 -> 98.0Improved
add AVA-VLAOpenVLA-OFT · CALVIN ABC->Daverage length: 4.28 -> 4.65Improved
add AVA-VLAOpenVLA-OFT · LIBERO+ (one policy per suite)success rate (%): 69.6 -> 74.7Improved
add AVA-VLA on non-robot-pretrained LLaMA2-7B backboneOpenVLA-OFT · LIBERO-Long (single-task)success rate (%): 90.0 -> 92.6Improved
add AVA-VLA on Qwen2.5-0.5B backboneOpenVLA-OFT · LIBERO-Long (single-task)success rate (%): 89.4 -> 90.8Improved
add state-based initialization to OpenVLA-OFT (ablation)OpenVLA-OFT · LIBERO (one policy for all 4 suites)success rate (%): 96.8 -> 97.5Improved
add AVA module to state-based initialization (ablation)AVA-VLA · LIBERO (one policy for all 4 suites)success rate (%): 97.5 -> 98.0Improved
add L_omega L2 regularizer (ablation)AVA-VLA · LIBERO (one policy for all 4 suites)success rate (%): 97.5 -> 98.0Improved
add AVA module to state-based initialization on CALVIN (ablation)AVA-VLA · CALVIN ABC->Daverage length: 4.63 -> 4.65Improved
prune 50% of visual tokens using AVA weights (ablation)AVA-VLA · LIBERO (one policy for all 4 suites)success rate (%): 98.0 -> 97.3Hurt
prune 90% of visual tokens using AVA weights (ablation)AVA-VLA · LIBERO (one policy for all 4 suites)success rate (%): 98.0 -> 93.9Hurt
train baseline and AVA-VLA under matched computeAVA-VLA vs OpenVLA-OFT · LIBERO matched training (100K steps, batch 256)success rate (%): 96.8 -> 98.3Improved

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