# μVLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models

arXiv: https://arxiv.org/abs/2606.12497 · HTML: https://mlsanity.com/paper/2606.12497/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning and chain-of-thought in VLA, one of 13 directions in Vision-language-action models.
- Builds on 71 of its 83 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Placed in

- Vision-language-action models / [Reasoning and chain-of-thought in VLA](https://mlsanity.com/vla/reasoning-and-chain-of-thought-in-vla/)

## Builds on (most cited first, 30 of 71)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation](https://mlsanity.com/paper/2411.19650/) (2024)
- [X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model](https://mlsanity.com/paper/2510.10274/) (2025)
- [Recurrent Memory Transformer](https://mlsanity.com/paper/2207.06881/) (2022)
- [MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2508.19236/) (2025)
- [EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos](https://mlsanity.com/paper/2507.12440/) (2025)
- [DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping](https://mlsanity.com/paper/2502.20900/) (2025)
- [F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions](https://mlsanity.com/paper/2509.06951/) (2025)
- [Universal Actions for Enhanced Embodied Foundation Models](https://mlsanity.com/paper/2501.10105/) (2025)
- [MemER: Scaling Up Memory for Robot Control via Experience Retrieval](https://mlsanity.com/paper/2510.20328/) (2025)
- [MEM: Multi-Scale Embodied Memory for Vision Language Action Models](https://mlsanity.com/paper/2603.03596/) (2026)
- [RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies](https://mlsanity.com/paper/2603.04639/) (2026)
- [Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation](https://mlsanity.com/paper/2508.19958/) (2025)

## Built on by (most cited first, 8 of 8)

- [MemBodied: Recurrent Associative Memory for Vision-Language-Action Models](https://mlsanity.com/paper/2609.28256/) (2026)
- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)
- [Skills in Weights, Memory in Code: Hybrid Learning for Memory-Dependent Robot Manipulation](https://mlsanity.com/paper/2608.09410/) (2026)
- [SmoLSTM: A Compact Vision-Language-Action Model with Recurrent Memory that Persists](https://mlsanity.com/paper/2609.22854/) (2026)
- [DRAM: Delta-rule Recurrent Associative Memory for Robot Manipulation Policies](https://mlsanity.com/paper/2609.32453/) (2026)
- [ECHO: Event-Augmented Context with Hindsight and Outlook for Wrist-Only Manipulation](https://mlsanity.com/paper/2609.34893/) (2026)
- [ReCAT: Remember, Count, and Time: Structured Recurrent Memory for Robot Manipulation](https://mlsanity.com/paper/2609.35200/) (2026)
- [Recompose and Refine Latent Reasoning Flows for Vision-Language-Action Models](https://mlsanity.com/paper/2610.12090/) (2026)

## Abstract (arXiv)

Vision-language-action (VLA) models predict chunks of future actions from the current observation, an assumption that fails under partial observability, where decisions depend on information no longer visible. Existing memory-augmented VLAs simultaneously introduce recurrence, retrieval, compression modules, auxiliary objectives, hierarchical memory, or task-specific architectural changes, so the contribution of recurrence itself remains entangled with surrounding machinery. We present a controlled isolation study of recurrence in a strong pretrained VLA backbone. Our formulation augments the transformer with a small set of learnable memory tokens carried across timesteps and updated through self-attention, trained end to end with truncated backpropagation through time, with no auxiliary losses and no architectural changes. We instantiate this as μVLA, a family of OpenVLA-OFT variants parameterized by memory width m, TBPTT length K, and the memory update rule (cross-step gradients or a detached EMA), so that recurrence is the only varying factor. On MIKASA-Robo, μVLA improves average success rate on five training tasks from 0.42 to 0.84 at the strongest setting and reaches 0.23 on held-out tasks with the same memory structure versus 0.07 for the memoryless baseline. On tasks requiring different memory structure, performance remains near baseline. On LIBERO, the strongest recurrent variant achieves 96.2% average success, indicating no regression under full observability. We interpret these results as a calibration of the capability envelope of minimal in-backbone recurrence, identifying the regime in which it is sufficient and the regime where additional memory structure is required. Demos and videos can be found in https://avanturist322.github.io/mu-vla/.