arXiv Computer Vision
Elastoformer: Enabling Dynamic Adaptivity via Elastic Model Transformation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
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.
arXiv AI
Oct 15
EV-JEPA: Elastic V-JEPA for Any Device and Cross-Device Inference
arXiv:2610.14324v1 Announce Type: cross Abstract: Foundation models like V-JEPA are increasingly deployed across a heterogeneous edge-cloud continuum spanning smart glasses, phones, robots, and serve...
arXiv AI
Aug 19
Adaptive AI Task Partitioning and Safe Offloading in Heterogeneous Edge-Cloud Continuum
The paper introduces a dynamic framework for partitioning neural network layers across a heterogeneous edge‑cloud continuum, adapting to runtime changes in network conditions and device capabilities. It profiles models at startup, measures link quality, and periodically re‑evaluates the partitioning to optimize performance. Experiments on a Raspberry Pi, laptop, and desktop using VGG16, AlexNet, and MobileNetV2 demonstrate energy savings of 27.09–35.82% and latency reductions of 6.34–22.92% over static partitioning.
arXiv Machine Learning
Oct 19
HydraLLM: Adaptive Width Slicing for Elastic Text and Vision-Language Models
arXiv:2610.23455v1 Announce Type: cross Abstract: LLMs and LVLMs are increasingly deployed across heterogeneous hardware, ranging from data-center GPUs to resource-constrained edge devices. Their fix...
arXiv Machine Learning
Jul 21
Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator
arXiv:2607. 18101v1 Announce Type: new Abstract: On-device model adaptation is essential to enable lifelong personalization on resource-constrained hardware, but compute, power, and memory limitations of such devices make end-to-end backpropagation impractical for modern deep neural networks.
arXiv Machine Learning
Jul 9
Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization
arXiv:2607. 06922v1 Announce Type: new Abstract: Deep learning applications have been widely adopted on edge devices, to mitigate the privacy and latency issues of accessing cloud servers.