# Characterizing VLA Models: Identifying the Action Generation Bottleneck for Edge AI Architectures

arXiv: https://arxiv.org/abs/2603.02271 · HTML: https://mlsanity.com/paper/2603.02271/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models.
- Builds on 2 of its 8 references that are in the map.
- First posted on arXiv 1 Mar 2026.

## Placed in

- Vision-language-action models / [Efficient VLA inference and adaptation](https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/)

## Builds on (most cited first, 2 of 2)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [MolmoAct: Action Reasoning Models that can Reason in Space](https://mlsanity.com/paper/2508.07917/) (2025)

## Built on by (most cited first, 3 of 3)

- [vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models](https://mlsanity.com/paper/2606.08094/) (2026)
- [vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation](https://mlsanity.com/paper/2609.24274/) (2026)
- [EdgeVLN: Runtime-Aware Deployment Ready Quantized Vision Language Navigation Model](https://mlsanity.com/paper/2609.35570/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models are an emerging class of workloads critical for robotics and embodied AI at the edge. As these models scale, they demonstrate significant capability gains, yet they must be deployed locally to meet the strict latency requirements of real-time applications. This paper characterizes VLA performance on two generations of edge hardware, viz. the Nvidia Jetson Orin and Thor platforms. Using MolmoAct-7B, a state-of-the-art VLA model, we identify a primary execution bottleneck: up to 75% of end-to-end latency is consumed by the memory-bound action-generation phase. Through analytical modeling and simulations, we project the hardware requirements for scaling to 100B parameter models. We also explore the impact of high-bandwidth memory technologies and processing-in-memory (PIM) as promising future pathways in edge systems for embodied AI.