arXiv AI September 17, 2026 By Mahdi Taheri, Pramit Kumar Bhaduri, Mohammad Masoumi, Ali Mahani

WARD: Runtime Workload-Adaptive Vision TRansformer Framework for Dependable Edge AI

WARD is a runtime‑adaptive Vision Transformer framework designed for edge AI that combines channel‑wise subnetwork partitioning, reliability‑aware continual learning, and dynamic operating‑mode scheduling. It operates two physically isolated subnetworks across four modes—Full‑Precision, Low‑Power, High‑Reliability, and Adaptive—to balance computational cost and fault tolerance while maintaining uninterrupted inference. Implemented on a lightweight FPGA accelerator with minimal area overhead, WARD achieves a network‑level failure rate of 1.79% under high Bit Error Rates and supports rapid mode transitions within a few clock cycles.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 14

Edge Physical AI Deployment of Vision Transformers on Heterogeneous Edge GPU Targeting Autonomous Vehicles

arXiv:2607. 10942v1 Announce Type: cross Abstract: Physical AI systems, such as autonomous vehicles and intelligent machines, require transformer-based perception models that satisfy stringent edge latency and energy constraints.

By Ashiyana Abdul Majeed, Mahmoud Meribout, Neethu Joseph, Abel Kidane Haile, Mohammad Abdullah Al Faruque

llms agents computer-vision efficiency

arXiv Computer Vision

Sep 10

Elastoformer: Enabling Dynamic Adaptivity via Elastic Model Transformation

arXiv:2609.10018v1 Announce Type: new Abstract: EdgeAI systems are increasingly employing computer vision applications to enable intelligent, on-device decision-making in real-time. However, these de...

By Sudaksh Kalra, Dolly Sapra

llms computer-vision

arXiv Computer Vision

Sep 14

Adaptive AI: Energy Efficient Multi-exit TinyML on Intelligent Vision Systems at the Edge

The paper presents a novel multi‑exit computational scheme for TinyML on an ultra‑low‑power GAP9 SoC, adding confidence‑based gating points to a MobileNetV2 CNN for ImageNet‑100. By allowing inference to stop early, the approach cuts average MAC operations by 41 % (from 313 MMAC to 185 MMAC), reduces inference time by 29 % (49 ms to 35 ms), and saves 24 % in energy (2.1 mJ to 1.6 mJ per frame) with only a ~1 % drop in accuracy. Compared to a state‑of‑the‑art adaptive CNN on the same hardware, the method more than doubles computational efficiency, raising MAC/cycle from 8.1 to 17.2.

By Luca Crupi, Lorenzo Lamberti, Alessandro Giusti, Daniele Palossi

benchmarks

arXiv Machine Learning

Jul 1

FlexViT: A Flexible FPGA-based Accelerator for Edge Vision Transformers

arXiv:2606. 31938v1 Announce Type: cross Abstract: Deploying Vision Transformer (ViT) models on edge platforms remains challenging due to their high computational demands and the architectural heterogeneity of modern hybrid ViT models, which incorporate both fully connected and convolutional layers.

By Hubert Dymarkowski, Xingjian Fu, Rappy Saha, Jude Haris, Jos\'e Cano

llms computer-vision efficiency

arXiv AI

Jul 7

Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers

arXiv:2607. 02612v1 Announce Type: cross Abstract: Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative.

By Aravind Pradeep, Samira Nazari, Mahdi Taheri, Christian Herglotz

llms computer-vision efficiency benchmarks

Hugging Face Trending Papers

Sep 23

RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models

Deploying deep learning models on edge CPUs is bottlenecked by computational and memory constraints. Mixed-precision quantization promises to reduce inference latency while preserving accuracy. Howeve...

efficiency