Search Results for author:
Found 3 papers, 0 papers with code
Eigenpruning
We introduce eigenpruning, a method that removes singular values from weight matrices in an LLM to improve its performance in a particular task.
Bridging the visual gap in VLN via semantically richer instructions
In this work, we hypothesize that poor use of the visual information available is at the core of the low performance of current models.
DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference
Large-scale pre-trained language models have shown remarkable results in diverse NLP applications.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
