React When You Need To: Event-Triggered Asynchronous Inference for VLA Policies
New in Vision-language-action models; no direction yet. Vision-language-action models
Abstract (arXiv)
Vision-Language-Action (VLA) models commonly predict action chunks, limiting their ability to react to environmental changes during execution. Existing asynchronous inference methods improve reactivity but typically rely on a fixed inference gap. In this paper, we propose an event-guided dynamic inference strategy that adapts the inference gap according to scene changes observed since the previous inference. Thereby, it simultaneously preserves motion consistency and prompt reactivity. Across static and dynamic real-world settings, our method consistently performs best, averaging 95% success and exceeding the strongest baseline by 55 percentage points. The code will be made publicly available upon acceptance. The project page is available at https://react-when-you-need-to.github.io/.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 24 references that are in the map. First posted on arXiv 18 Sep 2026.
Builds on
23 of 24 references.
References · 23
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
- 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
- 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
- 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
- 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
- 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
- 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
- 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
- 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
- 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
- 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 883
11 more
- 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
- 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 530
- 2025Real-Time Execution of Action Chunking Flow Policiescited by 216
- 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 181
- 2025ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Modelcited by 113
- 2024Prediction with Action: Visual Policy Learning via Joint Denoising Processcited by 70
- 2025Training-Time Action Conditioning for Efficient Real-Time Chunkingcited by 64
- 2025VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inferencecited by 58
- 2025Leave No Observation Behind: Real-time Correction for VLA Action Chunkscited by 46
- 2026DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulationcited by 34
- 2026ABPolicy: Asynchronous B-Spline Flow Policy for Real-Time and Smooth Robotic Manipulationcited by 10
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Understanding Asynchronous Inference Methods for Vision-Language-Action Models
- 2026Reflective VLA: In-Context Action Consequences Make VLAs Generalize
- 2026FASTER: Rethinking Real-Time Flow VLAs
- 2026Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models
- 2025VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robots
- 2026FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference
- 2026VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
- 2026How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf