Search Results for author:
Found 10 papers, 2 papers with code
Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling
Large language models are trained on massive scrapes of the web, which are often unstructured, noisy, and poorly phrased.
REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation
In online F-TTA, a pre-trained model is adapted using a stream of test samples by minimizing a self-supervised objective, such as entropy minimization.
Spatial LibriSpeech: An Augmented Dataset for Spatial Audio Learning
We present Spatial LibriSpeech, a spatial audio dataset with over 650 hours of 19-channel audio, first-order ambisonics, and optional distractor noise.
Understanding the Robustness of Multi-Exit Models under Common Corruptions
Furthermore, the lack of calibration increases the inconsistency in the predictions of the model across exits, leading to both inefficient inference and more misclassifications compared with evaluation on in-distribution data.
On the role of Lip Articulation in Visual Speech Perception
Previous research has shown that traditional metrics used to optimize and assess models for generating lip motion from speech are not a good indicator of subjective opinion of animation quality.
FORML: Learning to Reweight Data for Fairness
Machine learning models are trained to minimize the mean loss for a single metric, and thus typically do not consider fairness and robustness.
HALO: Learning to Prune Neural Networks with Shrinkage
Deep neural networks achieve state-of-the-art performance in a variety of tasks by extracting a rich set of features from unstructured data, however this performance is closely tied to model size.
CAZSL: Zero-Shot Regression for Pushing Models by Generalizing Through Context
The purpose of these agents is to quickly adapt and/or generalize their notion of physics of interaction in the real world based on certain features about the interacting objects that provide different contexts to the predictive models.
A Double Parametric Bootstrap Test for Topic Models
Non-negative matrix factorization (NMF) is a technique for finding latent representations of data.
Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognition
Accurate and computationally efficient means for classifying human activities have been the subject of extensive research efforts.
