mlsanityData to 14 Oct 2026

Catch Me If You Can: Real-Time Feedback Denoising for Responsive VLAs

arXiv 2609.21022 ↗First posted 17 Sep 2026cs.ROcited by 0

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

also in 1 more
Abstract (arXiv)

Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation by combining semantic knowledge from pretrained vision-language models with expressive action-generation policies. Diffusion-based action generators are particularly effective for modeling temporally coherent action chunks, but these chunks are typically executed open-loop after inference. This limits responsiveness when objects move, contacts change, or the scene evolves during execution. We propose VLA-Feedback, a two-timescale architecture that combines low-frequency diffusion planning with high-frequency visual feedback. Rather than fully denoising an action chunk before execution, VLA-Feedback retains its final denoising step as a lightweight feedback interface, allowing each action to be corrected using the latest observation before it is executed. This design preserves the expressiveness of the diffusion planner while enabling real-time action correction without rerunning the full vision-language diffusion model. VLA-Feedback matched GR00T on static LIBERO tasks while improving average success on dynamic simulation tasks from 27.5% to 85.0%. On real-robot tasks, it improved average success from 51% to 73%. Additional materials can be found on our project page: https://vla-feedback.github.io.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 50 of its 55 references that are in the map. First posted on arXiv 17 Sep 2026.

Builds on

50 of 55 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey20 Oct
  2. 2025VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation10 Oct
  3. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics2 Jun
  4. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control9 Feb
  5. 2024HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers12 Sep

Other references · 45

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2022Scalable Diffusion Models with Transformerscited by 6,054
  4. 2022Classifier-Free Diffusion Guidancecited by 5,847
  5. 2022Flow Matching for Generative Modelingcited by 5,702
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  7. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  8. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  9. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  10. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  11. 2023Consistency Modelscited by 1,822
  12. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
33 more
  1. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  2. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  3. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  4. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 691
  5. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  6. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 339
  7. 2025Real-Time Execution of Action Chunking Flow Policiescited by 216
  8. 2024Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillationcited by 166
  9. 2023Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Modelscited by 161
  10. 2025EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Modelscited by 93
  11. 2024One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillationcited by 89
  12. 2025PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decodingcited by 88
  13. 2024EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learningcited by 75
  14. 2025Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policycited by 74
  15. 2024Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulationcited by 73
  16. 2024Policy Decorator: Model-Agnostic Online Refinement for Large Policy Modelcited by 70
  17. 2025VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inferencecited by 58
  18. 2025Leave No Observation Behind: Real-time Correction for VLA Action Chunkscited by 46
  19. 2024A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLMcited by 44
  20. 2025ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Modelscited by 43
  21. 2025SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruningcited by 43
  22. 2025Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulationcited by 34
  23. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  24. 2026DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulationcited by 34
  25. 2025Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoningcited by 31
  26. 2025Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Modelscited by 30
  27. 2026Adaptive Action Chunking at Inference-time for Vision-Language-Action Modelscited by 28
  28. 2026How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perfcited by 19
  29. 2024Language-Guided Object-Centric Diffusion Policy for Generalizable and Collision-Aware Robotic Manipulationcited by 14
  30. 2025HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworkscited by 7
  31. 2026DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executorscited by 4
  32. 2026Understanding Asynchronous Inference Methods for Vision-Language-Action Modelscited by 4
  33. 2025Enhancing Diffusion Policy with Classifier-Free Guidance for Temporal Robotic Taskscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Self-Improving VLA Policies: Selected Diffusion Noise for Spurious-Robust Action Smoothing
  2. 2026FASA: Feedback-Aware Sampling Adaptation for Efficient Diffusion-Based VLA Models
  3. 2026StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models
  4. 2025E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion
  5. 2026ReactVLA: Fast and Lightweight Reactive Robot Manipulation via Improved Mean Flow Action Generation
  6. 2026REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models
  7. 2026Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference
  8. 2026A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model