← Back to all news
arXiv Computer Vision By Adrian Kneip, Martin Lefebvre, Daniel Gehrig, Victoria Catal\'an Pastor, Davide Scaramuzza, Marian Verhelst, Charlotte Frenkel

A 25-$\mu$s/inf Event-driven Graph Neural Network Processor with Spatiotemporal Caching and Spline Convolution for Ultra-low-latency AI at the Edge

Read the original on arXiv Computer Vision →

The paper introduces ETHEREAL, the first accelerator for event-driven graph neural networks (EV‑GNNs) that can handle 640×480 resolution inputs. It achieves this through a neighbor‑parallel spline convolution engine and a 2D/3D‑split memory hierarchy that includes a novel region‑of‑interest spatiotemporal caching mechanism. Measurements show end‑to‑end inference latency of 25.6 µs and energy consumption of 1.7 µJ per event on state‑of‑the‑art workloads.

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 Computer Vision.

Related stories

arXiv Computer Vision
Aug 27

FLEET: Token-Based Feature Extraction for Event Camera-based Reinforcement Learning

FLEET is a token‑based feature extractor that processes event camera data directly, using random Fourier features and cross‑attention to compress variable‑length event streams into fixed‑size latent representations. By decoupling inference cost from sensor resolution, it avoids the high compute and temporal blurring associated with CNN‑based grid aggregation. Experiments on a new high‑throughput benchmark show that FLEET outperforms state‑of‑the‑art methods and remains robust across different observation frequencies.

By Tristan Gottwald, Maximilian Schier, Melanie Schaller, Bodo Rosenhahn
nlpreinforcement-learningefficiencybenchmarks
More like this →