mlsanityData to 7 Oct 2026

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

arXiv 2603.02271 ↗First posted 1 Mar 2026cs.PF cs.AI cs.ARcited by 3

On the map: Vision-language-action models → Efficient VLA inference and adaptation

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.

Key facts. Cited by 3 papers in the map (data through 7 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.

Builds on

2 of 8 references.

References · 2

  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  2. 2025MolmoAct: Action Reasoning Models that can Reason in Spacecited by 189

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026vla.cpp: A Unified Inference Runtime for Vision-Language-Action Modelscited by 4
  2. 2026vla.simd: Efficient CPU Inference for Language-Conditioned Manipulationcited by 0
  3. 2026EdgeVLN: Runtime-Aware Deployment Ready Quantized Vision Language Navigation Modelcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs
  2. 2026Beyond LLM Serving: Characterizing Vision-Language-Action Workloads for Embodied AI System Design
  3. 2026How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf
  4. 2026Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment
  5. 2026Efficient Vision-Language-Action Management and Serving for Robot Factories
  6. 2025EdgeVLA: Efficient Vision-Language-Action Models
  7. 2025ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge
  8. 2026Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification