Search Results for author:
Found 3 papers, 0 papers with code
Effective Interplay between Sparsity and Quantization: From Theory to Practice
In addition, through rigorous analysis, we demonstrate that sparsity and quantization are not orthogonal; their interaction can significantly harm model accuracy, with quantization error playing a dominant role in this degradation.
Machine Translation Models Stand Strong in the Face of Adversarial Attacks
Through our investigation, we provide evidence that machine translation models display robustness displayed robustness against best performed known adversarial attacks, as the degree of perturbation in the output is directly proportional to the perturbation in the input.
Uncertainty Estimation of Transformers' Predictions via Topological Analysis of the Attention Matrices
Additionally, we introduce topological features to compare attention patterns across heads and layers.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
