# Integrated electro-optic attention nonlinearities for transformers

Source: [Integrated electro-optic attention nonlinearities for transformers](<https://www.sota2.com/research/paper/69dc78a67d0172140ec78c49>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-14T05:00:11.147Z

Authors: Luis Mickeler, Kai Lion, Alfonso Nardi, Jost Kellner, Pierre Didier, Bhavin J. Shastri, Niao He, Rachel Grange

Published: 2026-04-10T17:30:51.000Z

## Abstract

Transformers have emerged as the dominant neural-network architecture, achieving state-of-the-art performance in language processing and computer vision. At the core of these models lies the attention mechanism, which requires a nonlinear, non-negative mapping using the Softmax function. However, although Softmax operations account for less than 1% of the total operation count, they can disproportionately bottleneck overall inference latency. Here, we use thin-film lithium niobate (TFLN) Mach-Zehnder modulators (MZMs) as analog nonlinear computational elements to drastically reduce the latency of nonlinear computations. We implement electro-optic alternatives to digital Softmax and Sigmoid, and evaluate their performance in Vision Transformers and Large Language Models. Our system maintains highly competitive accuracy, even under aggressive 4-bit input-output quantization of the analog units. We further characterize system noise at encoding speeds up to 10 GBaud and assess model robustness under various noise conditions. Our findings suggest that TFLN modulators can serve as nonlinear function units within hybrid co-packaged hardware, enabling high-speed and energy-efficient nonlinear computation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Hardware Sequence Processing Performance on Sequence length n=64 at 10 GBaud](<https://www.sota2.com/research/sota/hardware-sequence-processing-performance-on-sequence-length-n-64-at-10-gbaud.md>): Hardware Sequence Processing Performance; Sequence length n=64 at 10 GBaud; Latency (s): 6.5e-9.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.09512>)

[PDF](<https://arxiv.org/pdf/2604.09512.pdf>)
