Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers

Item #:

079017-2315

Details

DOI: https://doi.org/10.52202/079017-2315
Author(s): Kazuki Irie, Francesca Mignacco, Haim Sompolinsky, Lorenzo Tiberi
Pages: 72710-72753 (44 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/079017-2315
Author(s): Kazuki Irie, Francesca Mignacco, Haim Sompolinsky, Lorenzo Tiberi
Pages: 72710-72753 (44 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)