4 citations · 4 across the 6 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Graphical einops: bridging tensor networks and computation graphs
Vincent Wang-Maścianica, Nikhil Khatri
Architecture diagrams are ubiquitous in deep learning, but they are usually only representational: the tensor-program identities they suggest are still proved by prose and tensor-a…
cs.LG2024
On the Anatomy of Attention
Nikhil Khatri, Tuomas Laakkonen, Jonathon Liu +1
We introduce a category-theoretic diagrammatic formalism in order to systematically relate and reason about machine learning models. Our diagrams present architectures intuitively…