79 citations · 255 across the 15 of their papers we have counts for
17 papers
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
Emiliano Penaloza, Dane Malenfant, Dheeraj Vattikonda +15
Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been the most popular mechanism to alleviate…
WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
Alexandre Drouin, Maxime Gasse, Massimo Caccia +9
We study the use of large language model-based agents for interacting with software via web browsers. Unlike prior work, we focus on measuring the agents' ability to perform tasks…
Towards Compute-Optimal Transfer Learning
Massimo Caccia, Alexandre Galashov, Arthur Douillard +6
The field of transfer learning is undergoing a significant shift with the introduction of large pretrained models which have demonstrated strong adaptability to a variety of downst…
NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research
Jorg Bornschein, Alexandre Galashov, Ross Hemsley +17
A shared goal of several machine learning communities like continual learning, meta-learning and transfer learning, is to design algorithms and models that efficiently and robustly…
Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges
Massimo Caccia, Jonas Mueller, Taesup Kim +2
Continual learning (CL) enables the development of models and agents that learn from a sequence of tasks while addressing the limitations of standard deep learning approaches, such…
Continual Learning via Local Module Composition
Oleksiy Ostapenko, Pau Rodriguez, Massimo Caccia +1
Modularity is a compelling solution to continual learning (CL), the problem of modeling sequences of related tasks. Learning and then composing modules to solve different tasks pro…
Learning where to learn: Gradient sparsity in meta and continual learning
Johannes von Oswald, Dominic Zhao, Seijin Kobayashi +4
Finding neural network weights that generalize well from small datasets is difficult. A promising approach is to learn a weight initialization such that a small number of weight ch…
Sequoia: A Software Framework to Unify Continual Learning Research
Fabrice Normandin, Florian Golemo, Oleksiy Ostapenko +10
The field of Continual Learning (CL) seeks to develop algorithms that accumulate knowledge and skills over time through interaction with non-stationary environments. In practice, a…
Understanding Continual Learning Settings with Data Distribution Drift Analysis
Timothée Lesort, Massimo Caccia, Irina Rish
Classical machine learning algorithms often assume that the data are drawn i.i.d. from a stationary probability distribution. Recently, continual learning emerged as a rapidly grow…
Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations
Pau Rodriguez, Massimo Caccia, Alexandre Lacoste +4
Explainability for machine learning models has gained considerable attention within the research community given the importance of deploying more reliable machine-learning systems.…
CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions
Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodriguez +12
In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems…
Synbols: Probing Learning Algorithms with Synthetic Datasets
Alexandre Lacoste, Pau Rodríguez, Frédéric Branchaud-Charron +7
Progress in the field of machine learning has been fueled by the introduction of benchmark datasets pushing the limits of existing algorithms. Enabling the design of datasets to te…
Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko +8
Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent continual-learning scenarios have opened…
Online Learned Continual Compression with Adaptive Quantization Modules
Lucas Caccia, Eugene Belilovsky, Massimo Caccia +1
We introduce and study the problem of Online Continual Compression, where one attempts to simultaneously learn to compress and store a representative dataset from a non i.i.d data…
Online Continual Learning with Maximally Interfered Retrieval
Rahaf Aljundi, Lucas Caccia, Eugene Belilovsky +4
Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In partic…
Language GANs Falling Short
Massimo Caccia, Lucas Caccia, William Fedus +3
Generating high-quality text with sufficient diversity is essential for a wide range of Natural Language Generation (NLG) tasks. Maximum-Likelihood (MLE) models trained with teache…
Option Pricing and Hedging for Discrete Time Autoregressive Hidden Markov Model
Massimo Caccia, Bruno Rémillard
In this paper we solve the discrete time mean-variance hedging problem when asset returns follow a multivariate autoregressive hidden Markov model. Time dependent volatility and se…