# Adaptive Swin Transformer Partitioning over AI-RAN Networks

Source: [Adaptive Swin Transformer Partitioning over AI-RAN Networks](<https://www.sota2.com/research/paper/69f03f4855a3c32af89fa29b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-29T05:00:12.215Z

Authors: Tam Thanh Nguyen, Yong Hao Pua, Tuan Van Ngo, Mao V. Ngo, Jihong Park, Binbin Chen, Tony Q. S. Quek

Published: 2026-04-26T06:29:45.000Z

## Abstract

This paper demonstrates the feasibility of transformer-based split inference for real-time video object detection over dynamic 5G AI-RAN networks. We extend throughput-aware adaptive splitting from CNNs to a Swin Transformer backbone and show that practical split execution is achievable for transformer-based vision models without retraining. To address the large intermediate activations inherent to transformers, we introduce an efficient, accuracy-preserving activation compression pipeline that substantially reduces uplink payload. The complete system -- including adaptive split selection, transformer inference, and compression -- is implemented and validated end-to-end on a real-time detection workload, with distributed UPF (dUPF) integration further reducing user-plane latency and improving runtime stability. Extensive measurements on an NVIDIA Aerial-based AI-RAN testbed jointly account for inference and 5G communication energy, quantifying the latency-energy-privacy trade-offs in realistic deployments.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.23554>)

[PDF](<https://arxiv.org/pdf/2604.23554.pdf>)
