arXiv Machine Learning

ShiftQAT: Quantization-Aware Training for the Numerical Contract of a Fixed-Function Edge CNN Accelerator

ShiftQAT is a quantization‑aware training workflow designed for the MAX7800x family of fixed‑function CNN accelerators. It enforces the accelerator’s numerical contract—power‑of‑two, per‑tensor symmetric scales, 8‑bit activations and biases, integer‑only arithmetic, and a single statically configured shift per layer—by training weights and biases on a joint power‑of‑two grid and resolving dependencies so that activation scales propagate statically. Compared to other methods, ShiftQAT uniquely satisfies all contract constraints while matching the accuracy of less constrained QAT approaches, achieving ImageNet performance within 2.9 percentage points of FP32 at W4A8 and enabling fast, energy‑efficient inference on MAX78002 silicon.

arXiv Machine Learning

Sep 24

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

The paper introduces RAMP, a method for robust adaptive mixed‑precision quantization of vision models on edge CPUs. It evaluates 13 sensitivity metrics across four neural networks, finding that Jensen‑Shannon Divergence consistently identifies layers that can be safely quantized. Using K‑Means clustering on these metrics, RAMP achieves near‑lossless accuracy with an average 1.81× speed‑up, while cautioning against excluding low‑speed‑up layers that can fragment the computational graph.

By David Poblaci\'on-Criado, Dario Garcia-Gasulla, Eduardo Quinones

efficiency

arXiv AI

Jul 2

Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects

arXiv:2505. 03303v4 Announce Type: replace-cross Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints.

By Tasnim Shahriar

fine-tuning benchmarks

arXiv AI

Aug 7

APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuning

arXiv:2608. 05499v1 Announce Type: cross Abstract: Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices.

By Sadegh Jafari, Mohiuddin Bilwal, Fan Zhou, Brian Gelder, Ali Jannesari

llms agents fine-tuning efficiency

arXiv Machine Learning

Aug 10

MiCoPro: End-to-End Mixed Precision HW/SW Co-design with HW-aware Proxy Model

arXiv:2608. 06916v1 Announce Type: new Abstract: Quantized Neural Networks~(QNN) with low-bitwidth data have proven promising in efficient storage and computation on edge devices.

By Zijun Jiang, Yangdi Lyu

efficiency

arXiv AI

4d ago

VLCQ: Post-training quantization for deep neural networks using variable length coding

arXiv:2610.15092v1 Announce Type: cross Abstract: Quantization plays a crucial role in efficiently deploying deep learning models on resource-constrained devices. Post-training quantization does not...

By Reem Abdel-Salam, Ahmed H. Abdel-Gawad, Amr G. Wassal

computer-vision fine-tuning efficiency benchmarks

arXiv AI

Jul 1

A Reproducible Benchmark of Lightweight CNNs: Accuracy, Efficiency, and the Impact of Pretrained Initialization

arXiv:2505. 03303v3 Announce Type: replace-cross Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints.

By Tasnim Shahriar

fine-tuning 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

Hugging Face Trending Papers

Aug 6

APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuning

Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices. Pruning and quantization address this, but rely on manual, expert choices and on algorithms that are hard to apply across architectures.

llms agents fine-tuning efficiency

arXiv Computer Vision

Sep 22

GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers

arXiv:2506.11784v2 Announce Type: replace Abstract: Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too. Model quantization, particularly to low bit-wid...

By Guang Liang, Xinyao Liu, Jianxin Wu

llms computer-vision efficiency

arXiv AI

Jun 8

Scale When Needed: Adaptive Neuron-level Mixed Precision Quantization Aware Training

arXiv:2605. 25054v2 Announce Type: replace-cross Abstract: Deploying deep neural networks on resource-constrained 6G edge devices demands aggressive compression with minimal accuracy loss.

By Ayush K. Varshney, Konstantinos Vandikas, \v{S}ar\=unas Girdzijauskas, Adam Orucu, Aneta Vulgarakis Feljan

efficiency

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.

By Mateusz Piechocki, Alessandro Capotondi, Marek Kraft

fine-tuning efficiency

arXiv AI

4d ago

Memory-Efficient Integer-Only Training of Deep Neural Networks

arXiv:2610.16298v1 Announce Type: new Abstract: Training neural networks in reduced precision can yield significant efficiency gains, yet all existing methods that scale to standard computer vision b...

By Hazem Hesham Yousef Shalby, Fabrizio Pittorino, Manuel Roveri

llms computer-vision benchmarks

Related stories