PofoliaShared via Pofolia

Zenodo (CERN European Organization for Nuclear Research)· 2026· Preprint

Axiom: A Householder-Parameterized Pure Unitary RNN for Long-Range Sequence Modeling

Chaudhary, Sanyam

Short summary

Axiom, a novel unitary RNN, achieves 76.5–99.9% accuracy on the delayed copy task with 13x fewer parameters than LSTM (8,584 vs 111,368), demonstrating lossless information preservation for long-range sequence modeling.

AI-generated from the title and abstract; the full text is not read.

TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app

The rest is in the Pofolia app

Takeaways, key points and questions to the paper; new summaries every day for your field. Free.

Sign in on the web to open

Field: Artificial Intelligence

Artificial IntelligenceComputer Science