mlsanityData to 14 Oct 2026

WeaveLA: Event Driven Cross-Subtask Latent Memory Weaving for Repetitive Robot Manipulation

arXiv 2606.17463 ↗First posted 16 Jun 2026cs.CV cs.ROcited by 2

On the map: Vision-language-action models → Reasoning and chain-of-thought in VLA

Abstract (arXiv)

Repetitive tasks are common in real-world manipulation, yet current vision-language-action (VLA) policies remain unreliable for repeated actions. We present LoopVLA, a cross-subtask event-memory interface for looped task execution. Its central idea is to compress a just-completed subtask into memory for the next subtask's action expert, making completed execution available for subsequent repetition and stopping decisions. Learnable event latents query the closed segment's tokens, while action features query history and joint history--event context; the two action-side readouts are residually fused and injected directly into the action head. On a memory benchmark, LoopVLA achieves 80.22% success on the repetition task group with online subgoal prediction, bringing evaluation closer to realistic deployment while improving overall success over strong memory baselines.

Key facts. Cited by 2 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 34 of its 46 references that are in the map. First posted on arXiv 16 Jun 2026.

Builds on

34 of 46 references.

Closest ancestors · 6

Same direction, newest first

  1. 2026ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queries13 Mar
  2. 2026RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies4 Mar
  3. 2026Non-Markovian Long-Horizon Robot Manipulation via Keyframe Chaining2 Mar
  4. 2025MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation12 Nov
  5. 2025HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy1 Oct
  6. 2025SeqVLA: Sequential Task Execution for Long-Horizon Manipulation with Completion-Aware Vision-Language-Action Model17 Sep

Other references · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  3. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  4. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  5. 2025Qwen3-VL Technical Reportcited by 2,793
  6. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  7. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  8. 2019Root Mean Square Layer Normalizationcited by 1,480
  9. 2024PaliGemma: A versatile 3B VLM for transfercited by 696
  10. 2016The Option-Critic Architecturecited by 448
  11. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 109
  12. 2021Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulationcited by 83
16 more
  1. 2024HiRT: Enhancing Robotic Control with Hierarchical Robot Transformerscited by 75
  2. 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RLcited by 74
  3. 2020Counting Out Time: Class Agnostic Video Repetition Counting in the Wildcited by 68
  4. 2023LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discoverycited by 67
  5. 2025MemER: Scaling Up Memory for Robot Control via Experience Retrievalcited by 67
  6. 2025Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulationcited by 48
  7. 2025ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Contextcited by 35
  8. 2025ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoningcited by 25
  9. 2025Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Countingcited by 18
  10. 2026ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulationcited by 18
  11. 2026BPP: Long-Context Robot Imitation Learning by Focusing on Key History Framescited by 18
  12. 2024Every Shot Counts: Using Exemplars for Repetition Counting in Videoscited by 9
  13. 2025TriVLA: A Triple-System-Based Unified Vision-Language-Action Model with Episodic World Modeling for General Robot Controlcited by 9
  14. 2025Spatial-Temporal Aware Visuomotor Diffusion Policy Learningcited by 9
  15. 2026StreamVLA: Breaking the Reason-Act Cycle via Completion-State Gatingcited by 7
  16. 2025A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Groundingcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Modelscited by 3
  2. 2026Recompose and Refine Latent Reasoning Flows for Vision-Language-Action Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ChainVLA: Chaining Vision-Language-Action Queries through a Unified Execution State for Long-Horizon Manipulation
  2. 2026MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation
  3. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
  4. 2026HELM: Harness-Enhanced Long-horizon Memory for Vision-Language-Action Manipulation
  5. 2026D2-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation
  6. 2026VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
  7. 2026EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies
  8. 2025EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation