Research map / Vision-language and multimodal / Robot action and navigation
MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
Hao Shi, Bin Xie, Yingfei Liu, Lin Sun, Fengrong Liu, Tiancai Wang, Erjin Zhou, Haoqiang Fan, Xiangyu Zhang, Gao Huang
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 |
|---|---|---|---|
| use both perceptual and cognitive memory instead of cognitive only (ablation) | MemoryVLA · SimplerEnv-Bridge | avg success rate (%): 63.5 -> 71.9 | Improved |
| use both memories instead of perceptual only (ablation) | MemoryVLA · SimplerEnv-Bridge | avg success rate (%): 64.6 -> 71.9 | Improved |
| set memory length to 16 instead of 4 (ablation) | MemoryVLA · SimplerEnv-Bridge | avg success rate (%): 67.7 -> 71.9 | Improved |
| set memory length to 16 instead of 64 (ablation) | MemoryVLA · SimplerEnv-Bridge | avg success rate (%): 67.7 -> 71.9 | Improved |
| add timestep positional encoding to retrieval (ablation) | MemoryVLA · SimplerEnv-Bridge | avg success rate (%): 69.8 -> 71.9 | Improved |
| use gate fusion instead of simple addition (ablation) | MemoryVLA · SimplerEnv-Bridge | avg success rate (%): 67.7 -> 71.9 | Improved |
| use token-merge consolidation instead of FIFO (ablation) | MemoryVLA · SimplerEnv-Bridge | avg success rate (%): 66.7 -> 71.9 | Improved |
| add perceptual-cognitive memory (MemoryVLA over CogACT) | MemoryVLA · Real-world long-horizon temporal tasks | avg success score (%): 57 -> 83 | Improved |
| add perceptual-cognitive memory (MemoryVLA over CogACT) | MemoryVLA · Mikasa-Robo | avg success rate (%): 29.4 -> 41.2 | Improved |
| unseen camera view (distribution shift) | MemoryVLA · Pick Coke Can (sim OOD) | success rate (%): 92.0 -> 42.0 | Hurt |
Later papers that compared with this method
8 later accepted papers report MemoryVLA as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.
- ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models (NeurIPS 2026 · better on 4 of 4 shared results)
- World-in-Loop: Online Correction via Event-Triggered World Models for Robust VLA Policies (ECCV 2026 · better on 4 of 4 shared results)
- X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model (ICLR 2026 · better on 3 of 3 shared results)
- From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model (ICML 2026 · better on 1 of 1 shared result)
- World–Value–Action Model: Implicit Planning for Vision–Language–Action Systems (NeurIPS 2026 · better on 1 of 1 shared result)
- PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models (NeurIPS 2026 · better on 1 of 1 shared result)
- Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation (CVPR 2026 · better on 1 of 1 shared result)
- HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models (CVPR 2026 · 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
- SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation (ICML 2025 · similarity 0.92)
- VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models (NeurIPS 2026 · similarity 0.91)
- TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies (ICLR 2025 · similarity 0.91)
- DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge (NeurIPS 2025 · similarity 0.90)
- ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models (NeurIPS 2026 · similarity 0.90)
- ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models (NeurIPS 2026 · similarity 0.90)
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.
