AI Paper Atlas

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

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

Yihao Wang, Pengxiang Ding, Lingxiao Li, Can Cui, Zirui Ge, Xinyang Tong, Wenxuan Song, Han Zhao, Wei Zhao, Pengxu Hou, Siteng Huang, Yifan Tang and 4 more

AAAI 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 23 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
use VLA-Adapter bridge instead of OpenVLA-OFT bridgePrismatic Qwen2.5-0.5B (no robotic pretraining) · LIBERO-Longsuccess rate (%): 85.8 -> 95.0Improved
use VLA-Adapter bridge instead of OpenVLA-OFT bridgePrismatic LLaMA2-7B · LIBERO-Longsuccess rate (%): 87.5 -> 95.2Improved
use VLA-Adapter bridge instead of OpenVLA-OFT bridgeOpenVLA-7B (robot-pretrained) · LIBERO-Longsuccess rate (%): 94.5 -> 95.4Improved
freeze the VLM backbone with OpenVLA-OFT bridgeOpenVLA-OFT · LIBERO-Longsuccess rate (%): 0.0Hurt
use middle-layer raw features instead of deep-layer raw features (ablation)VLA-Adapter policy · LIBERO-Longsuccess rateImproved
use all-layer features instead of a single layer (ablation)VLA-Adapter policy · LIBERO-Longsuccess rateImproved
add ActionQuery features alongside all-layer raw features (ablation)VLA-Adapter · LIBERO-Longsuccess rate (%): 90.6 -> 95.0Improved
add raw features to all-layer ActionQuery condition (ablation)VLA-Adapter · LIBERO-Longsuccess rate (%): 92.6 -> 95.0Improved
mid-layer raw features vs all-layer ActionQuery on hard subtasks (ablation)VLA-Adapter · LIBERO-Long subtask 7success rate (%): 90 (raw layer 9) vs 82 (AQ layer 1)Mixed
use learnable tanh(g) gate for raw feature injection instead of fixed 1 (ablation)VLA-Adapter Bridge Attention · LIBERO-Longsuccess rate (%): 91.4 -> 95.0Improved
also gate ActionQuery injection with tanh(g) (ablation)VLA-Adapter Bridge Attention · LIBERO-Longsuccess rate (%): 95.0 -> 92.6Hurt
use very few or very many ActionQuery tokens vs 64 (ablation)VLA-Adapter · LIBERO-Longsuccess rateHurt

Later papers that compared with this method

9 later accepted papers report VLA-Adapter as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.

1 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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