Search Results for author:
Found 1 papers, 0 papers with code
Adaptivity and Modularity for Efficient Generalization Over Task Complexity
We investigate how the use of a mechanism for adaptive and modular computation in transformers facilitates the learning of tasks that demand generalization over the number of sequential computation steps (i. e., the depth of the computation graph).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
