mlsanityData to 7 Oct 2026

MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation

arXiv 2508.19236 ↗First posted 26 Aug 2025cs.RO cs.CVcited by 183

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

Abstract (arXiv)

Temporal context is essential for robotic manipulation because such tasks are inherently non-Markovian, yet mainstream VLA models typically overlook it and struggle with long-horizon, temporally dependent tasks. Cognitive science suggests that humans rely on working memory to buffer short-lived representations for immediate control, while the hippocampal system preserves verbatim episodic details and semantic gist of past experience for long-term memory. Inspired by these mechanisms, we propose MemoryVLA, a Cognition-Memory-Action framework for long-horizon robotic manipulation. A pretrained VLM encodes the observation into perceptual and cognitive tokens that form working memory, while a Perceptual-Cognitive Memory Bank stores low-level details and high-level semantics consolidated from it. Working memory retrieves decision-relevant entries from the bank, adaptively fuses them with current tokens, and updates the bank by merging redundancies. Using these tokens, a memory-conditioned diffusion action expert yields temporally aware action sequences. We evaluate MemoryVLA on 150+ simulation and real-world tasks across three robots. On SimplerEnv-Bridge, Fractal, LIBERO-5 suites and Mikasa-Robo, it achieves 71.9%, 72.7%, 96.5%, and 41.2% success rates, respectively, all outperforming state-of-the-art baselines CogACT and pi-0, with a notable +14.6 gain on Bridge and +11.8 gain on Mikasa-Robo. On 12 real-world tasks spanning general skills and long-horizon temporal dependencies, MemoryVLA achieves 84.0% success rate, with long-horizon tasks showing a +26 improvement over state-of-the-art baseline. Project Page: https://shihao1895.github.io/MemoryVLA

Key facts. Cited by 183 papers in the map (data through 7 Oct 2026). Placed in Reasoning and chain-of-thought in VLA, one of 13 directions in Vision-language-action models. Builds on 61 of its 74 references that are in the map. First posted on arXiv 26 Aug 2025.

Builds on

61 of 74 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation23 Jul
  2. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models27 Mar

Other references · 59

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2023Visual Instruction Tuningcited by 7,792
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  9. 2022Scalable Diffusion Models with Transformerscited by 5,931
  10. 2022Classifier-Free Diffusion Guidancecited by 5,717
  11. 2017Squeeze-and-Excitation Networkscited by 4,763
  12. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
38 more
  1. 2023Qwen Technical Reportcited by 3,273
  2. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  3. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  4. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  5. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  7. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  8. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  9. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  10. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  11. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  12. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  13. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  14. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  15. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  16. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  17. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 545
  18. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  19. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  20. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  21. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 390
  22. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  23. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  24. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 344
  25. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 336
  26. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  27. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policiescited by 298
  28. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 224
  29. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Controlcited by 191
  30. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 176
  31. 2025Magma: A Foundation Model for Multimodal AI Agentscited by 138
  32. 2024Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goalscited by 131
  33. 2024DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Executioncited by 116
  34. 2025A Survey on Vision-Language-Action Models: An Action Tokenization Perspectivecited by 96
  35. 2024What Matters in Building Vision-Language-Action Models for Generalist Robotscited by 88
  36. 2025Universal Actions for Enhanced Embodied Foundation Modelscited by 80
  37. 2025GeoVLA: Empowering 3D Representations in Vision-Language-Action Modelscited by 68
  38. 20254D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibrationcited by 55

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 23; 2026: 160.

183 papers.

Sort:

By area:

  1. 2026Causal World Modeling for Robot Controlcited by 289
  2. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 285
  3. 2025Memory in the Age of AI Agentscited by 285
  4. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 140
  5. 2026π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilitiescited by 127
  6. 2026MEM: Multi-Scale Embodied Memory for Vision Language Action Modelscited by 55
  7. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
  8. 2025HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policycited by 42
  9. 2026Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Executioncited by 42
  10. 2026RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Designcited by 40
  11. 2026VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Modelscited by 38
  12. 2026RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policiescited by 35
38 more
  1. 2025ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Contextcited by 34
  2. 2025HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Modelscited by 30
  3. 2026ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Modelscited by 30
  4. 2026Native Video-Action Pretraining for Generalizable Robot Controlcited by 30
  5. 2026ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queriescited by 28
  6. 2026OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulationcited by 25
  7. 2025AVA-VLA: Improving Vision-Language-Action models with Active Visual Attentioncited by 22
  8. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 22
  9. 2026HoloBrain-0 Technical Reportcited by 20
  10. 2026Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulationcited by 19
  11. 2026EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policiescited by 18
  12. 2026How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perfcited by 17
  13. 2026Towards Generalizable Robotic Manipulation in Dynamic Environmentscited by 17
  14. 2025PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Modelcited by 16
  15. 2025AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Modelscited by 16
  16. 2025EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulationcited by 15
  17. 2026World-Value-Action Model: Implicit Planning for Vision-Language-Action Systemscited by 13
  18. 2026Gated Memory Policy: In-Context Memorization and Adaptationcited by 13
  19. 2025Dexbotic: Open-Source Vision-Language-Action Toolboxcited by 12
  20. 2026DM0: An Embodied-Native Vision-Language-Action Model towards Physical AIcited by 12
  21. 2026VLANeXt: Recipes for Building Strong VLA Modelscited by 12
  22. 2026MemoryWAM: Efficient World Action Modeling with Persistent Memorycited by 12
  23. 2025EvoVLA: Self-Evolving Vision-Language-Action Modelcited by 11
  24. 2026ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Modelscited by 11
  25. 2026Wall-OSS-0.5 Technical Reportcited by 11
  26. 2025HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policiescited by 10
  27. 2026VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memorycited by 10
  28. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulationcited by 10
  29. 2026MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generationcited by 10
  30. 2026Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflectioncited by 9
  31. 2026MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Modelscited by 9
  32. 2025Nav-R2 Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigationcited by 8
  33. 2026CORAL: Scalable Multi-Task Robot Learning via LoRA Expertscited by 8
  34. 2026HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulationcited by 8
  35. 2025LatBot: Distilling Universal Latent Actions for Vision-Language-Action Modelscited by 7
  36. 2025Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-trainingcited by 7
  37. 2026PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policiescited by 7
  38. 2026Non-Markovian Long-Horizon Robot Manipulation via Keyframe Chainingcited by 7

50 most cited of 183 All 183 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation
  2. 2025Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective
  3. 2026RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
  4. 2026Towards Neuro-Symbolic Procedural Reasoning for Long-Horizon Vision-Language-Action Manipulation
  5. 2026D2-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation
  6. 2026T2Mem: Learning Test-Time Memory for Robotics ↗
  7. 2026Remember what you did?: Learning Behavioral Memories for Partially Observable Object Manipulation
  8. 2026MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation