Thin-film lithium niobate modulators implement electro-optic Softmax and Sigmoid alternatives for transformers that maintain competitive accuracy under 4-bit quantization and characterized noise up to 10 GBaud.
Learning multiple layers of fea- tures from tiny images
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Integrated electro-optic attention nonlinearities for transformers
Thin-film lithium niobate modulators implement electro-optic Softmax and Sigmoid alternatives for transformers that maintain competitive accuracy under 4-bit quantization and characterized noise up to 10 GBaud.