arXiv Computer Vision
What Makes an Efficient VLA? Navigating Action-Head Design, Scaling, and Latency
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jun 9
CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models
arXiv:2605. 21854v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have rapidly converged on a small set of architectural patterns: discrete-token autoregression (e.
arXiv AI
Jun 9
vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models
arXiv:2606. 08094v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies are typically shipped as Python/PyTorch stacks that assume a workstation-class GPU, a mismatch for the hardware on which robots actually run.
arXiv AI
Sep 18
StarVLA-$\alpha$: Reducing Complexity in Vision-Language-Action Systems
StarVLA-α is a streamlined Vision‑Language‑Action (VLA) model that reduces architectural and pipeline complexity to facilitate systematic study of VLA design choices. By employing a strong VLM backbone and minimal design, it achieves competitive performance across multiple benchmarks (LIBERO, SimplerEnv, RoboTwin, RoboCasa) and outperforms the baseline π₀.₅ by 20% on the RoboChallenge benchmark. The authors plan to release the code to support future VLA research.
arXiv AI
Oct 27
VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware
arXiv:2610.34717v1 Announce Type: cross Abstract: Vision--language--action (VLA) models increasingly run on edge devices aboard robots, where inference latency constrains closed-loop robot control. H...
arXiv Machine Learning
Sep 25
Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs
The paper introduces a framework for Flow‑Matching Vision‑Language‑Action (VLA) models that allows independent adjustment of backbone depth, action expert depth, and denoising steps. Lightweight Exit Transformers are added at intermediate layers to enable early exits, and a KV Cache synthesis mechanism manages skipped layers so the action expert can exit deeper than the backbone. Experiments on SmolVLA and π0.5 across LIBERO and Meta‑World show that joint tuning of these compute axes reduces latency by 79.2 % and FLOPs by 31.8 %, while improving mean success rate by 5.6 %.
Hugging Face Trending Papers
Jul 29
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
Vision-language-action (VLA) models commonly adopt an LLM-centric $V \to L \to A$ pathway, where visual observations are projected into the representation space of a large language model before being decoded into robot actions. Although effective, this design incurs substantial computation and memory overhead at every policy invocation.