AI Paper Atlas

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

Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation

Zaijing Li, Bing Hu, Rui Shao, Gongwei Chen, Dongmei Jiang, Pengwei Xie, Jianye Hao, Liqiang Nie

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 22 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 GPM (retrieved task-level prior initialization) (ablation)OptimusVLA · CALVIN ABC->Daverage completion length: 4.28 -> 4.45Improved
add GPM (ablation)OptimusVLA · Real-world Generalization Taskssuccess rate (%): 77.0 -> 85.0Improved
add GPM (ablation)OptimusVLA · LIBERO-Longsuccess rate (%): 93.2 -> 96.4Improved
add LCM (local consistency memory) (ablation)OptimusVLA · LIBERO-Longsuccess rate (%): 94.8 -> 96.4Improved
add LCM (ablation)OptimusVLA · CALVIN ABC->Daverage completion length: 4.38 -> 4.45Improved
add LCM (ablation)OptimusVLA · Real-world Generalization Taskssuccess rate (%): 79.5 -> 85.0Improved
add both GPM and LCM to pi0.5 (ablation)pi0.5 · LIBERO-Longsuccess rate (%): 92.4 -> 96.4Improved
increase memory bank from 1300 to 6500 trajectories (k=8) (ablation)OptimusVLA · LIBERO-Longsuccess rate (%): 95.2 -> 96.4Improved
shrink memory to 130 trajectories (k=8) (ablation)OptimusVLA · LIBERO-Longsuccess rate (%): 96.4 -> 93.6Hurt
retrieve k=8 instead of k=1 (ablation)OptimusVLA · LIBERO-Longsuccess rate (%): 92.6 -> 96.4Improved
retrieve k=8 instead of k=16 (ablation)OptimusVLA · LIBERO-Longsuccess rate (%): 94.8 -> 96.4Improved
add GPM and LCM to pi0.5pi0.5 · LIBERO (average)success rate (%): 96.9 -> 98.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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