Transformers need glasses! Information over-squashing in language tasks

Item #:

079017-3114

Details

DOI: https://doi.org/10.52202/079017-3114
Author(s): João Araújo, Andrea Banino, Federico Barbero, Steven Kapturowski, Dharshan Kumaran, Razvan Pascanu, Petar Veličković, Alex Vitvitskyi
Pages: 98111-98142 (32 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/10.52202/079017-3114
Author(s): João Araújo, Andrea Banino, Federico Barbero, Steven Kapturowski, Dharshan Kumaran, Razvan Pascanu, Petar Veličković, Alex Vitvitskyi
Pages: 98111-98142 (32 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)