Jean-Baptiste Cordonnier

Sparsified SGD with Memory

Sebastian U. Stich, Jean-Baptiste Cordonnier, Martin Jaggi · arXiv (Cornell University) · 2018 · 233 citations · Full text

Computing, Communication, Computer Science +17

Attention is Not All You Need: Pure Attention Loses Rank Doubly\n Exponentially with Depth

Yihe Dong, Jean-Baptiste Cordonnier, Andreas Loukas · arXiv (Cornell University) · 2021 · 90 citations · Full text

Computing, Computer Science, Artificial Intelligence +11

On the Relationship between Self-Attention and Convolutional Layers

Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi · arXiv (Cornell University) · 2019 · 89 citations · Full text

Computing, Computer Science, Vision Science +11

Multi-Head Attention: Collaborate Instead of Concatenate

Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi · arXiv (Cornell University) · 2020 · 76 citations · Full text

Computing, Computer Science, Computer Vision +11

Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Yihe Dong, Jean-Baptiste Cordonnier, Andreas Loukas · arXiv (Cornell University) · 2021 · 71 citations · Full text

Computing, Computer Science, Artificial Intelligence +11