Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
:::info Stub — Full Engineering Breakdown Coming This paper was featured on Hugging Face Daily Papers on 2026-07-08 with 55 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::
| Authors | Hongyu Qu et al. |
| Year | 2026 |
| HF Upvotes | 55 |
| arXiv | 2607.07608 |
| Download | |
| HF Page | View on Hugging Face |
Abstract
Mainstream Vision-Language-Action (VLA) models predict actions primarily from the current observation under a Markovian assumption, thus struggling with long-horizon, temporally dependent tasks. Existing memory-augmented VLAs either expand the observation window or retrieve history from the memory bank as auxiliary policy-side context. However, they leave memory outside the native latent embedding space of VLA reasoning, preventing historical experience from being fluidly interleaved with multimodal reasoning and action formation. To this end, we introduce LaMem-VLA, a latent-memory-native framework that reconstructs historical experience into latent memory tokens and directly interweaves them with VLA reasoning. At its core, LaMem-VLA introduces four coordinated components: (i) a curator that organizes historical experience into two complementary short-term and long-term memory vaults; (ii) a seeker that queries both vaults using the multimodal cognition to retrieve context-relevant evidence; (iii) a condenser that reconstructs the retrieved evidence into compact short-term and long-term latent memory tokens; and (iv) a weaver that injects these memory tokens with the current observation and instruction into one continuous embedding sequence. By representing, retrieving, and consuming historical experience entirely in the same continuous latent space, LaMem-VLA enables memory to directly participate in VLA reasoning and guide action generation under a bounded context. Extensive experiments on SimplerEnv and LIBERO demonstrate the superiority of our LaMem-VLA.
Engineering Breakdown
The Problem
However, they leave memory outside the native latent embedding space of VLA reasoning, preventing historical experience from being fluidly interleaved with multimodal reasoning and action formation.
The Approach
To this end, we introduce LaMem-VLA, a latent-memory-native framework that reconstructs historical experience into latent memory tokens and directly interweaves them with VLA reasoning.
Key Results
Extensive experiments on SimplerEnv and LIBERO demonstrate the superiority of our LaMem-VLA.
Research Areas
This paper contributes to the following areas of AI/ML engineering:
- Machine learning
- Deep learning
- Neural networks
- Model optimization
- AI systems
- Visionlanguageaction
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::