FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference

• URL: http://arxiv.org/abs/2608.27384v1
• Date: Thu, 27 Aug 2026 17:19:29 GMT
• Title: FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference
• Abstract summary: FlashVLA is a streaming action decoding framework for Vision-Language-Action (VLA) models.<n>It substantially improves inference speed while maintaining strong task performance.<n>It can achieve $geq$30,Hz control frequency on a single GPU with smooth asynchronous inference in real-world deployment.
• Score: 13.128933240091419
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language-Action (VLA) models are increasingly promising for robotic manipulation, yet their real-world deployment remains bottlenecked by high inference latency and unstable asynchronous execution. This challenge is particularly pronounced in flow-matching-based VLA models, where action decoding requires multiple iterative steps conditioned on the VLM context. While efficient inference methods improve control frequency and asynchronous methods reduce execution idle time, existing approaches often fail to jointly achieve low-latency inference and accurate, temporally consistent asynchronous execution. We introduce \textbf{FlashVLA}, a streaming action decoding framework that addresses both challenges in a unified formulation. FlashVLA maintains a streaming action buffer with multiple chunks at different noise levels and decodes them using chunk-wise causal attention. This design allows FlashVLA to produce one executable action chunk per inference step. Moreover, its chunk-wise autoregressive formulation implicitly preserves action continuity, enabling smooth asynchronous execution without extra future-state conditioning. Across extensive simulated and real-world experiments, FlashVLA substantially improves inference speed while maintaining strong task performance. It can achieve $\geq$30\,Hz control frequency on a single GPU with smooth asynchronous inference in real-world deployment.

Related papers

• StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models [84.17128030384099]
  StreamPI is a streaming multimodal temporal modeling framework.<n>It equips single-frame VLA with temporal reasoning capability without introducing any additional parameters.<n> Experiments on real-robot tasks spanning memory-dependent and precise perception scenarios, as well as the simulation benchmark LIBERO, demonstrate that StreamPI outperforms pi0.5 across diverse tasks.
  arXiv  Detail & Related papers  (2026-08-26T17:33:19Z)
• Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Models [26.864668803085888]
  Vision-Language-Action models (VLAs) have demonstrated strong task understanding and generalization in robotic manipulation.<n>We propose an asynchronous semantic-action decoupling framework that separates semantic understanding from action generation.<n>We show that the proposed framework achieves up to 35.6 Hz server-side action- module inference throughput and offers a low-intrusion path to high-frequency closed-loop control.
  arXiv  Detail & Related papers  (2026-06-13T12:49:42Z)
• TBD-VLA: Temporal Block Diffusion Vision Language Action Model [7.861095039299131]
  We introduce TBD-VLA, a discrete token-based VLA framework that incorporates block diffusion to enable temporal action generation.<n>We partition action sequences into temporal blocks and perform masked discrete diffusion within each block, while maintaining autoregressive generation across blocks.<n>This design unifies temporal autoregression and parallel action decoding, achieving both strong temporal coherence and improved inference speed.
  arXiv  Detail & Related papers  (2026-06-05T23:10:43Z)
• StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation [30.881585159777714]
  Vision-language-action (VLA) models have demonstrated exceptional performance in natural language-driven perception and control.<n>High computational cost of VLA models poses significant efficiency challenges.<n>We propose enabling VLAs with the ability to asynchronously parallelize across VLA stages in a "streaming" manner.
  arXiv  Detail & Related papers  (2026-03-30T15:23:27Z)
• AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge [49.66156306240961]
  High latency breaks the control loop, rendering powerful models unsafe for real-time deployment.<n>We propose AsyncVLA, an asynchronous control framework that decouples semantic reasoning from reactive execution.<n>AsyncVLA achieves a 40% higher success rate than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-13T21:31:19Z)
• VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robots [5.308743386891208]
  Vision-Language-Action (VLA) models have achieved remarkable breakthroughs in robotics.<n>The strategies for fusing a queue of successive action chunks have a profound impact on the overall performance of VLA models.<n>Existing methods suffer from jitter, stalling, or even pauses in robotic action execution.<n>This paper introduces VLA-RAIL, a novel framework designed to conduct model inference and robot motion control asynchronously.
  arXiv  Detail & Related papers  (2025-12-31T06:59:42Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference [24.248289541718275]
  Asynchronous inference offers a promising solution to achieve continuous and low-latency control.<n>We propose VLASH, a general asynchronous inference framework for Vision-Language-Action models.<n>It delivers smooth, accurate, and fast reaction control without additional overhead or architectural changes.
  arXiv  Detail & Related papers  (2025-11-30T18:59:24Z)
• dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought [66.78110237549087]
  Vision-Language-Action (VLA) models are emerging as a next-generation paradigm for robotics.<n>We introduce dVLA, a diffusion-based VLA that unifies visual perception, language reasoning, and robotic control in a single system.
  arXiv  Detail & Related papers  (2025-09-30T02:36:11Z)
• NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows [75.70583906344815]
  Diffusion models have been widely adopted as action decoders due to their ability to model complex, multimodal action distributions.<n>We present NinA, a fast and expressive alternative to diffusion-based decoders for Vision-Language-Action (VLA) models.
  arXiv  Detail & Related papers  (2025-08-23T00:02:15Z)
• SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration [70.72227437717467]
  Vision-Language-Action (VLA) models have attracted increasing attention for their strong control capabilities.<n>Their high computational cost and low execution frequency hinder their suitability for real-time tasks such as robotic manipulation and autonomous navigation.<n>We propose SP-VLA, a unified framework that accelerates VLA models by jointly scheduling models and pruning tokens.
  arXiv  Detail & Related papers  (2025-06-15T05:04:17Z)

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.