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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add GPM (retrieved task-level prior initialization) (ablation) | OptimusVLA · CALVIN ABC->D | average completion length: 4.28 -> 4.45 | Improved |
| add GPM (ablation) | OptimusVLA · Real-world Generalization Tasks | success rate (%): 77.0 -> 85.0 | Improved |
| add GPM (ablation) | OptimusVLA · LIBERO-Long | success rate (%): 93.2 -> 96.4 | Improved |
| add LCM (local consistency memory) (ablation) | OptimusVLA · LIBERO-Long | success rate (%): 94.8 -> 96.4 | Improved |
| add LCM (ablation) | OptimusVLA · CALVIN ABC->D | average completion length: 4.38 -> 4.45 | Improved |
| add LCM (ablation) | OptimusVLA · Real-world Generalization Tasks | success rate (%): 79.5 -> 85.0 | Improved |
| add both GPM and LCM to pi0.5 (ablation) | pi0.5 · LIBERO-Long | success rate (%): 92.4 -> 96.4 | Improved |
| increase memory bank from 1300 to 6500 trajectories (k=8) (ablation) | OptimusVLA · LIBERO-Long | success rate (%): 95.2 -> 96.4 | Improved |
| shrink memory to 130 trajectories (k=8) (ablation) | OptimusVLA · LIBERO-Long | success rate (%): 96.4 -> 93.6 | Hurt |
| retrieve k=8 instead of k=1 (ablation) | OptimusVLA · LIBERO-Long | success rate (%): 92.6 -> 96.4 | Improved |
| retrieve k=8 instead of k=16 (ablation) | OptimusVLA · LIBERO-Long | success rate (%): 94.8 -> 96.4 | Improved |
| add GPM and LCM to pi0.5 | pi0.5 · LIBERO (average) | success rate (%): 96.9 -> 98.6 | Improved |
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.
- MemoryVLA — MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation (ICLR 2026) · better on 1 of 1 shared result
- Seer — SEER: Backdoor Detection for Vision-Language Models through Searching Target Text and Image Trigger Jointly (AAAI 2024) · better on 1 of 1 shared result
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
- ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models (NeurIPS 2026 · similarity 0.94)
- PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models (NeurIPS 2026 · similarity 0.93)
- ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning (NeurIPS 2026 · similarity 0.93)
- VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models (NeurIPS 2026 · similarity 0.92)
- NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models (NeurIPS 2026 · similarity 0.92)
- VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching (NeurIPS 2025 · similarity 0.92)
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.
