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

arXiv: https://arxiv.org/abs/2609.15241 · HTML: https://mlsanity.com/paper/2609.15241/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2026.

## Abstract (arXiv)

Dynamic-vision-sensor (DVS) cameras generate events on a per-pixel basis with a μs-level temporal resolution, calling for new algorithm-hardware co-design approaches compared to standard frame-based vision. While event-driven graph neural networks (EV-GNNs) emerge as a promising algorithmic solution, they raise new HW challenges by mixing dense-regular compute operations and sparse-irregular memory accesses. We present ETHEREAL, the first EV-GNN accelerator that scales to 640×480 resolutions, thanks to a neighbor-parallel spline convolution engine and a 2D/3D-split memory hierarchy with a novel region-of-interest spatiotemporal caching mechanism. Measurement results demonstrate end-to-end inference with 25.6μs latency and 1.7μJ energy per event on state-of-the-art workloads