3 citations · 7 across the 13 of their papers we have counts for
15 papers
Studying Generalization on Memory-Based Methods in Continual Learning
Felipe del Rio, Julio Hurtado, Cristian Buc +2
One of the objectives of Continual Learning is to learn new concepts continually over a stream of experiences and at the same time avoid catastrophic forgetting. To mitigate comple…
A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference Information
Vladimir Araujo, Alvaro Soto, Marie-Francine Moens
Existing question answering methods often assume that the input content (e.g., documents or videos) is always accessible to solve the task. Alternatively, memory networks were intr…
PIVOT: Prompting for Video Continual Learning
Andrés Villa, Juan León Alcázar, Motasem Alfarra +5
Modern machine learning pipelines are limited due to data availability, storage quotas, privacy regulations, and expensive annotation processes. These constraints make it difficult…
Bridging the visual gap in VLN via semantically richer instructions
Joaquin Ossandón, Benjamin Earle, Álvaro Soto
The Visual-and-Language Navigation (VLN) task requires understanding a textual instruction to navigate a natural indoor environment using only visual information. While this is a t…
How Relevant is Selective Memory Population in Lifelong Language Learning?
Vladimir Araujo, Helena Balabin, Julio Hurtado +2
Lifelong language learning seeks to have models continuously learn multiple tasks in a sequential order without suffering from catastrophic forgetting. State-of-the-art approaches…
A Study on the Predictability of Sample Learning Consistency
Alain Raymond-Saez, Julio Hurtado, Alvaro Soto
Curriculum Learning is a powerful training method that allows for faster and better training in some settings. This method, however, requires having a notion of which examples are…
Memory Population in Continual Learning via Outlier Elimination
Julio Hurtado, Alain Raymond-Saez, Vladimir Araujo +3
Catastrophic forgetting, the phenomenon of forgetting previously learned tasks when learning a new one, is a major hurdle in developing continual learning algorithms. A popular met…
Entropy-based Stability-Plasticity for Lifelong Learning
Vladimir Araujo, Julio Hurtado, Alvaro Soto +1
The ability to continuously learn remains elusive for deep learning models. Unlike humans, models cannot accumulate knowledge in their weights when learning new tasks, mainly due t…
Evaluation Benchmarks for Spanish Sentence Representations
Vladimir Araujo, Andrés Carvallo, Souvik Kundu +6
Due to the success of pre-trained language models, versions of languages other than English have been released in recent years. This fact implies the need for resources to evaluate…
Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations
Vladimir Araujo, Andrés Villa, Marcelo Mendoza +2
Current language models are usually trained using a self-supervised scheme, where the main focus is learning representations at the word or sentence level. However, there has been…
DeepSocNav: Social Navigation by Imitating Human Behaviors
Juan Pablo de Vicente, Alvaro Soto
Current datasets to train social behaviors are usually borrowed from surveillance applications that capture visual data from a bird's-eye perspective. This leaves aside precious re…
Inspecting the concept knowledge graph encoded by modern language models
Carlos Aspillaga, Marcelo Mendoza, Alvaro Soto
The field of natural language understanding has experienced exponential progress in the last few years, with impressive results in several tasks. This success has motivated researc…
TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification
Andrés Villa, Juan-Manuel Perez-Rua, Victor Escorcia +3
Recently, few-shot video classification has received an increasing interest. Current approaches mostly focus on effectively exploiting the temporal dimension in videos to improve l…
Optimizing Reusable Knowledge for Continual Learning via Metalearning
Julio Hurtado, Alain Raymond-Saez, Alvaro Soto
When learning tasks over time, artificial neural networks suffer from a problem known as Catastrophic Forgetting (CF). This happens when the weights of a network are overwritten du…
Translating Natural Language Instructions for Behavioral Robot Navigation with a Multi-Head Attention Mechanism
Patricio Cerda-Mardini, Vladimir Araujo, Alvaro Soto
We propose a multi-head attention mechanism as a blending layer in a neural network model that translates natural language to a high level behavioral language for indoor robot navi…