Search Results for author:
Found 16 papers, 8 papers with code
Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones
Early Exiting (EE) is a promising technique for speeding up inference by adaptively allocating compute resources to data points based on their difficulty.
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks
We use an efficient data curation process to ensure our data is high-quality and license-permissive.
RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
We run a large-scale benchmark comprising several state-of-the-art LLMs to uncover differences in performance across models of various types and sizes in a context-conditional language modeling setting.
Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection
Our findings reveal that while these methods excel in detecting unknown classes, their performance is inconsistent when encountering other types of distribution shifts.
CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning
This work explores the use of self-supervised contrastive learning to the simultaneous detection of two types of OOD samples: unseen classes and adversarial perturbations.
Constraining Representations Yields Models That Know What They Don't Know
In the add-on case, the original neural network's inference head is completely unaffected (so its accuracy remains the same) but we now have the option to use TAC's own confidence and prediction when determining which course of action to take in an hypothetical production workflow.
Monotonicity Regularization: Improved Penalties and Novel Applications to Disentangled Representation Learning and Robust Classification
We study settings where gradient penalties are used alongside risk minimization with the goal of obtaining predictors satisfying different notions of monotonicity.
Monotonicity as a requirement and as a regularizer: efficient methods and applications
We study the setting where risk minimization is performed over general classes of models and consider two cases where monotonicity is treated as either a requirement to be satisfied everywhere or a useful property.
Domain Conditional Predictors for Domain Adaptation
Domain adaptation approaches thus appeared as a useful framework yielding extra flexibility in that distinct train and test data distributions are supported, provided that other assumptions are satisfied such as covariate shift, which expects the conditional distributions over labels to be independent of the underlying data distribution.
Learning Semantic Similarities for Prototypical Classifiers
Recent metric learning approaches parametrize semantic similarity measures through the use of an encoder trained along with a similarity model, which operates over pairs of representations.
On The Performance of Time-Pooling Strategies for End-to-End Spoken Language Identification
Automatic speech processing applications often have to deal with the problem of aggregating local descriptors (i. e., representations of input speech data corresponding to specific portions across the time dimension) and turning them into a single fixed-dimension representation, known as global descriptor, on top of which downstream classification tasks can be performed.
An end-to-end approach for the verification problem: learning the right distance
In this contribution, we augment the metric learning setting by introducing a parametric pseudo-distance, trained jointly with the encoder.
Multi-task self-supervised learning for Robust Speech Recognition
We then propose a revised encoder that better learns short- and long-term speech dynamics with an efficient combination of recurrent and convolutional networks.
A Simplified Fully Quantized Transformer for End-to-end Speech Recognition
While significant improvements have been made in recent years in terms of end-to-end automatic speech recognition (ASR) performance, such improvements were obtained through the use of very large neural networks, unfit for embedded use on edge devices.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Generative Adversarial Speaker Embedding Networks for Domain Robust End-to-End Speaker Verification
Furthermore, we are able to significantly boost verification performance by averaging our different GAN models at the score level, achieving a relative improvement of 7. 2% over the baseline.
On-line Adaptative Curriculum Learning for GANs
We argue that less expressive discriminators are smoother and have a general coarse grained view of the modes map, which enforces the generator to cover a wide portion of the data distribution support.
