MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models
- Published
- Source
- arXiv
- Paper number
- 385
- Field
- Robotics
- arXiv ID
- 2606.09827
Key points
- We introduce a cognition-inspired full-temporal model that combines working memory, episodic memory, and future imagination through a world model.
- The Perceptual-Cognitive Memory Bank stores low-level details and high-level semantics together, and updates memory when redundancy is detected.
- A latent-space world model imagines future states through partial denoising only, without requiring pixel-level prediction.
- We achieve 98.4% on Libero and 74.0% on SimplerEnv, with real-robot gains of +9% for general capability, +26% for memory, and +28% for imagination.
- It is especially strong on long-horizon tasks, with 4.29 on Calvin and 44.4% on Mikasa-Robo.
- It is ready for real-time deployment, with 66.4 Hz inference on an RTX 4090.
Paper links
External research summaries. These are not HDATF publications or measured product results.