MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models

• URL: http://arxiv.org/abs/2606.09827v1
• Date: Mon, 08 Jun 2026 17:59:53 GMT
• Title: MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models
• Abstract summary: Temporal modeling is essential for robotic manipulation, as effective control requires memory of past interactions and imagination of future states.<n>We propose MemoryVLA++, a full temporal modeling framework that equips VLA models with memory and imagination for robotic manipulation.<n>Our method achieves strong performance across Libero, SimplerEnv, Mikasa-Robo, Calvin, Libero-Plus, and diverse real-robot tasks.
• Score: 80.70528162709276
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Temporal modeling is essential for robotic manipulation, as effective control requires both memory of past interactions and imagination of future states. However, most VLA models rely primarily on the current observation and therefore struggle with long-horizon, temporally dependent tasks. Cognitive science suggests that humans rely on working memory to buffer short-lived context, the hippocampal system to preserve episodic memory of past experience, and internal models to imagine possible future state evolution. Inspired by these mechanisms, we propose MemoryVLA++, a full temporal modeling framework that equips VLA models with memory and imagination for robotic manipulation. A pretrained VLM encodes the current observation into perceptual and cognitive tokens, forming working memory. These tokens query a Perceptual-Cognitive Memory Bank to retrieve relevant historical context. This bank stores low-level details and high-level semantics from past interactions, and is updated through redundancy-aware consolidation. A world model imagines future states in a denoising latent space, and the imagined latents are integrated under memory guidance to form full temporal-aware tokens. The resulting tokens condition a diffusion action expert to predict temporally consistent action sequences. We conduct extensive experiments on 5 simulation benchmarks and 3 categories of real-robot tasks across 3 robots, covering general manipulation, long-horizon temporal tasks, robustness, and generalization. Our method achieves strong performance across Libero, SimplerEnv, Mikasa-Robo, Calvin, Libero-Plus, and diverse real-robot tasks, validating the effectiveness of full temporal modeling with memory and imagination. For example, on real robots, it achieves +9%, +26%, +28% gains on general, memory-dependent, and imagination-dependent tasks. Project Page: https://shihao1895.github.io/MemoryVLA-PP-Web

Related papers

• MemoryWAM: Efficient World Action Modeling with Persistent Memory [80.90899269062128]
  We introduce MemoryWAM, a world action model with efficient persistent memory.<n>A tailored attention mechanism enables retrieval of both detailed short-term context and compressed long-term context.<n>MemoryWAM outperforms strong vision-language-action (VLA) and WAM baselines in both simulation and the real world.
  arXiv  Detail & Related papers  (2026-06-18T17:59:51Z)
• HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation [12.167895321305464]
  We present HiMem-WAM, a Hierarchical Memory-Gated WAM that integrates motion-centric latent actions, high-level skill latents, and boundary-triggered memory updates.<n>Specifically, we develop a hierarchical latent action framework that jointly learns low-level motion and high-level skill latents.<n>A boundary-aware memory gate writes compact task states at predicted skill transitions, enabling causal inference without test-time generation of future video or optical flow estimation.
  arXiv  Detail & Related papers  (2026-06-09T03:22:34Z)
• WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction [72.1620416874118]
  Multimodal large language models are increasingly deployed as long-horizon agents.<n>Existing benchmarks measure recall over static dialogue, collapse memory into a single end-of-task accuracy, and reduce visual observations to captions.<n>We formulate multimodal agent memory as an Action-World Interaction Loop with an observable four-stage lifecycle.
  arXiv  Detail & Related papers  (2026-05-28T04:27:20Z)
• RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies [54.23445842621374]
  Memory is critical for long-horizon and history-dependent robotic manipulation.<n>Recent vision-language-action (VLA) models have begun to incorporate memory mechanisms.<n>We introduce RoboMME: a large-scale standardized benchmark for evaluating and advancing VLA models.
  arXiv  Detail & Related papers  (2026-03-04T21:59:32Z)
• MEM: Multi-Scale Embodied Memory for Vision Language Action Models [73.3883864595845]
  We introduce Multi-Scale Embodied Memory (MEM), an approach for mixed-modal long-horizon memory in robot policies.<n>MEM combines video-based short-horizon memory, compressed via a video encoder, with text-based long-horizon memory.<n>MEM enables robot policies to perform tasks that span up to fifteen minutes, like cleaning up a kitchen, or preparing a grilled cheese sandwich.
  arXiv  Detail & Related papers  (2026-03-04T00:03:02Z)
• On Memory: A comparison of memory mechanisms in world models [0.0]
  We investigate the effective memory span of transformer-based world models through an analysis of several memory augmentation mechanisms.<n>We introduce a taxonomy that distinguishes between memory encoding and memory injection mechanisms, motivating their roles in extending the world model's memory.<n>Our findings show that memory mechanisms improve the effective memory span in vision transformers and provide a path to completing loop closures within a world model's imagination.
  arXiv  Detail & Related papers  (2025-12-07T20:29:20Z)
• MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation [59.31354761628506]
  Temporal context is essential for robotic manipulation because such tasks are inherently non-Markovian, yet mainstream VLA models typically overlook it.<n>We propose MemoryVLA, a Cognition-Memory-Action framework for long-horizon robotic manipulation.<n>We evaluate it on 150+ simulation and real-world tasks across three robots.
  arXiv  Detail & Related papers  (2025-08-26T17:57:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.