# ETH Zurich's Optmax Moves AI Attention Math From Silicon to Light — retained record

> Retained news record from news:ml-alphasignal.

Canonical: https://highsignal.app/data/records/7ea8c1c972aae05a

[← sources](https://highsignal.app/data)


source: [news](https://highsignal.app/data/news) (news:ml-alphasignal)  published 2026-10-28 18:01 ingested 2026-10-29 03:02

[original source ↗](https://alphasignal.ai/news/eth-zurich-s-optmax-moves-ai-attention-math-from-silicon-to-light)

## retained text



```
A research team proposes using thin-film lithium niobate modulators as analog replacements for Softmax and Sigmoid inside transformer attention.
```



document fetched 2026-10-29 03:02