arXiv Machine Learning June 30, 2026 By Ho Fung Tsoi, Dylan Rankin, Vladimir Loncar, Philip Harris

SparsePixels: Efficient Convolution for Sparse Data on FPGAs

Read the original on arXiv Machine Learning →

arXiv:2512. 06208v3 Announce Type: replace-cross Abstract: Inference of standard convolutional neural networks (CNNs) on FPGAs often incurs high latency and a long initiation interval due to the deep nested loops required to densely convolve every input pixel regardless of its feature value.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

efficiency

arXiv AI

Jun 2

HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces

arXiv:2606. 01117v1 Announce Type: cross Abstract: Extreme multi-label classification (XMC) involves learning models over large output spaces with millions of labels, making the output layer a memory-compute bottleneck.

By Nasib Ullah, Jinbin Zhang, Jean Lucien Randrianantenaina, Erik Schultheis, Rohit Babbar

efficiency benchmarks safety

arXiv Machine Learning

Aug 4

CascadeLUT: Information-Ordered Streaming Inference for Bandwidth-Constrained FPGAs

arXiv:2608. 00720v1 Announce Type: cross Abstract: Mapping neural networks to FPGAs enables low-latency, energy-efficient inference, particularly for lookup table (LUT)-based models that eliminate multipliers and map directly to reconfigurable fabric.

By Oliver Cassidy, Marta Andronic, George A. Constantinides

efficiency

arXiv Machine Learning

Jun 9

Convolutional Sparse Coding via the Locally Competitive Algorithm on Loihi 2

arXiv:2606. 08584v1 Announce Type: new Abstract: Sparse coding provides a principled framework for signal representation by expressing an input as a linear combination of only a small number of basis functions.

By Geoffrey Kasenbacher, Daniel Ruepp, Gerrit A. Ecke

benchmarks

Hugging Face Trending Papers

Jun 24

Energy-Efficient CNN Acceleration with MSDF Digit-Serial Arithmetic on FPGA

This paper presents an energy-efficient hardware acceleration of the convolutional layers in the U-Net architecture for image segmentation, implemented on FPGA. While digit-serial arithmetic, particularly most-significant-digit-first (MSDF) techniques, offers a compact hardware footprint, it suffers from initial latency before producing the first output digit.

computer-vision efficiency

arXiv Machine Learning

Jul 3

WBMM: Windowed Batch Matrix Multiplication for Efficient Large Receptive Field Convolution

arXiv:2607. 02097v1 Announce Type: cross Abstract: Large kernel depthwise convolutions achieve strong performance but suffer from significant degradation as kernel size grows due to irregular memory access from gather-based computation; while Large Kernel Acceleration (LKA) helps on small feature maps, it becomes counterproductive on large feature maps, even slower than non-accelerated implementations.

By Wan Song, Wei Zhou, Rui Wang, Jun Yu, Toru Kurihara, Jiajia Xu, Shu Zhan

efficiency benchmarks safety

arXiv Machine Learning

Jul 27

Unified Static-Dynamic Pruning for Efficient LLM Inference

arXiv:2607. 21985v1 Announce Type: cross Abstract: The increasing deployment of large language models (LLMs) has magnified the computational and memory bottlenecks of autoregressive decoding, where low compute intensity and bandwidth-bound kernels dominate inference cost.

By Jinhyeok Kim, Yejoon Lee, Jaeyoung Do

llms efficiency

Related stories

HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces

CascadeLUT: Information-Ordered Streaming Inference for Bandwidth-Constrained FPGAs

Convolutional Sparse Coding via the Locally Competitive Algorithm on Loihi 2

Energy-Efficient CNN Acceleration with MSDF Digit-Serial Arithmetic on FPGA

WBMM: Windowed Batch Matrix Multiplication for Efficient Large Receptive Field Convolution

Unified Static-Dynamic Pruning for Efficient LLM Inference