EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies

• URL: http://arxiv.org/abs/2606.20092v1
• Date: Thu, 18 Jun 2026 11:11:37 GMT
• Title: EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies
• Abstract summary: EventVLA is an end-to-end framework founded on the concept of sparse visual evidence memory.<n>KEM directly predicts future probabilities from the VLA's latent embeddings to autonomously capture and store sparse, task-critical visual events.<n>We propose RoboTwin-MeM, a diagnostic benchmark designed to evaluate non-Markovian manipulation tasks with interactive visual evidence.
• Score: 68.812675280427
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Memory remains a critical bottleneck for long-horizon robotic manipulation, as standard Vision-Language-Action (VLA) policies often fail when task-relevant cues become occluded or unobservable over time. While existing memory-augmented methods utilize historical context, they either suffer from severe information bottlenecks, incur high latency via decoupled dual systems, or rely on unselective buffers that accumulate massive visual redundancies. To address these limitations, we introduce EventVLA, an end-to-end framework founded on the concept of sparse visual evidence memory that comprises two core components: foundational visual anchors to retain initial and short-term contexts, and a dynamic Keyframe Evidence Memory (KEM) module. Specifically, KEM directly predicts future keyframe probabilities from the VLA's latent embeddings to autonomously capture and store sparse, task-critical visual events. This foresight-driven mechanism empowers the policy to dynamically evaluate the future causal utility of current observations, preserving transient visual evidence before it becomes unobservable. Furthermore, we propose RoboTwin-MeM, a diagnostic benchmark specifically designed to evaluate non-Markovian manipulation tasks with interactive visual evidence. Extensive evaluations show that across 17 memory-requiring simulation tasks and 4 real-world bimanual tasks, EventVLA achieves an average success rate improvement of +40% over state-of-the-art memory-augmented VLAs.

Related papers

• MemVLN: Episodic and Procedural Memory for Vision-and-Language Navigation [68.89913903899101]
  We propose a novel VLN framework that achieves state-of-the-art performance with real-time inference efficiency (14 FPS)<n>MemVLN utilizes a visual encoder to process continuous observations and a Large Language Model (LLM) to interpret instructions and generate actions.<n> Experiments on VLN-CE show that MemVLN-4B surpasses the baseline Qwen3-VL-4B architecture by 5.8% SR in R2R and 9.7% SR in RxR, while achieving a 7$times$ speedup in inference latency.
  arXiv  Detail & Related papers  (2026-07-26T07:08:30Z)
• Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation [96.18832998704329]
  We introduce LaMem-VLA, a latent-memory-native framework that reconstructs historical experience into latent memory tokens.<n>LaMem-VLA enables memory to directly participate in VLA reasoning and guide action generation under a bounded context.
  arXiv  Detail & Related papers  (2026-07-08T16:26:06Z)
• VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies [58.65913948991329]
  We present VISUALTHINK-VLA, a visual intermediate-reasoning framework for accurate, low-latency VLA policies.<n>Our bootstrapping philosophy is to guide action with effective visual thinking.<n>It bootstraps action prediction through a compact visual-evidence interface that preserves spatial precision while avoiding decoding overhead.
  arXiv  Detail & Related papers  (2026-05-28T14:36:53Z)
• Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action [33.511005694762126]
  We introduce SOMA, the Spatial Memory framework for Out-of-Vision Manipulation in Vision-Language-Action (VLA) models.<n>The framework consists of three components: Spatial Memory Construction, Dynamic Memory Refinement, and Contextual Memory Retrieval.<n>We evaluate SOMA on five challenging real-world out-of-vision manipulation tasks, including multi-step and dual-arm scenarios.
  arXiv  Detail & Related papers  (2026-05-21T10:32:53Z)
• ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queries [45.23935281952228]
  We introduce ReMem-VLA, a vision-language-action (VLA) model equipped with two sets of learnable queries.<n>These queries are trained end-to-end to aggregate and maintain relevant context over time.<n>We demonstrate that ReMem-VLA exhibits strong memory capabilities across multiple dimensions.
  arXiv  Detail & Related papers  (2026-03-13T12:38:42Z)
• 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)
• CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling [84.51372201195132]
  CronusVLA is a unified framework that extends single-frame VLA models to the multi-frame paradigm.<n>CronusVLA achieves leading performance and superior robustness, with a 70.9% success rate.<n>These results highlight the potential of efficient multi-frame adaptation in VLA models for more powerful and robust real-world deployment.
  arXiv  Detail & Related papers  (2025-06-24T17:30:27Z)
• FindingDory: A Benchmark to Evaluate Memory in Embodied Agents [49.18498389833308]
  We introduce a new benchmark for long-range embodied tasks in the Habitat simulator.<n>This benchmark evaluates memory-based capabilities across 60 tasks requiring sustained engagement and contextual awareness.
  arXiv  Detail & Related papers  (2025-06-18T17:06:28Z)

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.