DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging

Item #:

079017-4336

Details

DOI: https://doi.org/10.52202/079017-4336
Author(s): Francois Fleuret, Martin Jaggi, Amirkeivan Mohtashami, Matteo Pagliardini
Pages: 136479-136508 (30 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/10.52202/079017-4336
Author(s): Francois Fleuret, Martin Jaggi, Amirkeivan Mohtashami, Matteo Pagliardini
Pages: 136479-136508 (30 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)