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

• URL: http://arxiv.org/abs/2603.02271v1
• Date: Sun, 01 Mar 2026 01:09:55 GMT
• Title: Characterizing VLA Models: Identifying the Action Generation Bottleneck for Edge AI Architectures
• Abstract summary: Vision-Language-Action (VLA) models are an emerging class of workloads critical for robotics and embodied AI at the edge.<n>This paper characterizes VLA performance on two generations of edge hardware, viz. the Nvidia Jetson Orin and Thor platforms.
• Score: 4.6111834169518735
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents [71.09493646932046]
  We introduce HY-Embodied-0.5, a family of foundation models specifically designed for real-world embodied agents.<n>The HY-Embodied-0.5 suite comprises two primary variants: an efficient model with 2B activated parameters designed for edge deployment, and a powerful model with 32B activated parameters targeted for complex reasoning.<n>Our MoT-2B model outperforms similarly sized state-of-the-art models on 16 benchmarks, while the 32B variant achieves performance comparable to frontier models such as Gemini 3.0 Pro.
  arXiv  Detail & Related papers  (2026-04-08T17:59:48Z)
• MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling [80.48332380100915]
  MiniCPM-SALA is a hybrid model that integrates the high-fidelity long-context modeling of sparse attention with the global efficiency of linear attention.<n>On a single NVIDIA A6000D GPU, the model achieves up to 3.5x the inference speed of the full-attention model at the sequence length of 256K tokens.
  arXiv  Detail & Related papers  (2026-02-12T09:37:05Z)
• Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs [49.99513618431772]
  We propose a hardware co-design law that captures model accuracy and inference performance.<n>We empirically evaluate 1,942 candidate architectures on NVIDIA Jetson Orin.<n>Our architecture achieves 19.42% lower perplexity on WikiText-2.
  arXiv  Detail & Related papers  (2026-02-10T23:51:00Z)
• mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs [5.109732854501585]
  We introduce mimic-video, a novel Video-Action Model (VAM) that pairs a pretrained Internet-scale video model with a flow matching-based action decoder conditioned on its latent representations.<n>Our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.
  arXiv  Detail & Related papers  (2025-12-17T18:47:31Z)
• MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation [22.063033063941788]
  Memory-Augmented Prompting for Vision-Language-Action model (MAP-VLA) is a novel framework that empowers pre-trained VLA models with demonstration-derived memory prompts to augment action generation for long-horizon robotic manipulation tasks.<n>Results show that MAP-VLA delivers up to 7.0% absolute performance gains in the simulation benchmark and 25.0% on real robot evaluations for long-horizon tasks, surpassing the current state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-11-12T17:56:13Z)
• DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving [52.63591791507895]
  We propose textbfDriveVLA-W0, a training paradigm that employs world modeling to predict future images.<n>This task generates a dense, self-supervised signal that compels the model to learn the underlying dynamics of the driving environment.<n>Experiments on the NAVSIM v1/v2 benchmark and a 680x larger in-house dataset demonstrate that DriveVLA-W0 significantly outperforms BEV and VLA baselines.
  arXiv  Detail & Related papers  (2025-10-14T17:59:47Z)
• SVTime: Small Time Series Forecasting Models Informed by "Physics" of Large Vision Model Forecasters [86.38433605933515]
  Time series AI is crucial for analyzing dynamic web content.<n>Given their energy-intensive training, inference, and hardware demands, using large models as a one-fits-all solution raises serious concerns about carbon footprint and sustainability.<n>This paper introduces SVTime, a novel Small model inspired by large Vision model (LVM) forecasters for long-term Time series forecasting (LTSF)
  arXiv  Detail & Related papers  (2025-10-10T18:42:23Z)
• Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs [24.657525276719365]
  Vision-Language-Action (VLA) models have emerged as powerful generalist policies for robotic control.<n>This work presents an evaluation of five representative VLA models.<n>We measure accuracy alongside system-level metrics, including latency, throughput, and peak memory usage.
  arXiv  Detail & Related papers  (2025-09-15T00:00:37Z)
• EdgeVLA: Efficient Vision-Language-Action Models [0.4005096060512278]
  This paper introduces Edge VLA, a novel approach designed to significantly enhance the inference speed of Vision-Language-Action (VLA) models.<n>We achieve this through two key innovations: 1) Eliminating the autoregressive requirement for end-effector position prediction, leading to a 7x speedup in inference, and 2) Leveraging the efficiency of Small Language Models (SLMs)<n>Our early results demonstrate that EVLA achieves comparable training characteristics to OpenVLA while offering substantial gains in inference speed and memory efficiency.
  arXiv  Detail & Related papers  (2025-07-18T16:15:09Z)
• NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks [37.03331507197761]
  Existing Visual-Language-Action (VLA) models have shown promising performance in zero-shot scenarios.<n>These models typically suffer from high computational overhead due to their large sizes.<n>We propose NORA, a model designed to reduce computational overhead while maintaining strong task performance.
  arXiv  Detail & Related papers  (2025-04-28T14:47:34Z)
• CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation [100.25567121604382]
  Vision-Language-Action (VLA) models have improved robotic manipulation in terms of language-guided task execution and generalization to unseen scenarios.<n>We present a new advanced VLA architecture derived from Vision-Language-Models (VLM)<n>We show that our model not only significantly surpasses existing VLAs in task performance and but also exhibits remarkable adaptation to new robots and generalization to unseen objects and backgrounds.
  arXiv  Detail & Related papers  (2024-11-29T12:06:03Z)
• Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robust [9.647148940880381]
  Vision-language-action (VLA) models trained on large-scale internet data and robot demonstrations have the potential to serve as generalist robot policies. We introduce Bring Your Own VLA (BYOVLA): a run-time intervention scheme that dynamically identifies regions of the input image that the model is sensitive to. We show that BYOVLA enables state-of-the-art VLA models to nearly retain their nominal performance in the presence of distractor objects and backgrounds.
  arXiv  Detail & Related papers  (2024-10-02T19:29:24Z)
• Fine-Tuning and Deploying Large Language Models Over Edges: Issues and Approaches [64.42735183056062]
  Large language models (LLMs) have evolved from specialized deep models to versatile foundation models.<n>LLMs require fine-tuning on local datasets and substantial memory for deployment over the network edges.<n>LLMs have been expanded beyond text generation to create images, audio, video, and multi-modal content.<n>Model fine-tuning and model-compression techniques have been developed to support the sustainable growth of LLMs.
  arXiv  Detail & Related papers  (2024-08-20T09:42:17Z)
• Energy-efficient Task Adaptation for NLP Edge Inference Leveraging Heterogeneous Memory Architectures [68.91874045918112]
  adapter-ALBERT is an efficient model optimization for maximal data reuse across different tasks. We demonstrate the advantage of mapping the model to a heterogeneous on-chip memory architecture by performing simulations on a validated NLP edge accelerator.
  arXiv  Detail & Related papers  (2023-03-25T14:40:59Z)

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.