79 citations · 264 across the 15 of their papers we have counts for
13 papers · 1 filter
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…
Position: Modular Memory is the Key to Continual Learning Agents
Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov +21
Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these…
Generative Modeling of Individual Behavior at Scale
Nabil Omi, Lucas Caccia, Anurag Sarkar +2
There has been a growing interest in using AI to model human behavior, particularly in domains where humans interact with this technology. While most existing work models human beh…
Guiding The Last Layer in Federated Learning with Pre-Trained Models
Gwen Legate, Nicolas Bernier, Lucas Caccia +2
Federated Learning (FL) is an emerging paradigm that allows a model to be trained across a number of participants without sharing data. Recent works have begun to consider the effe…
Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning
Gwen Legate, Lucas Caccia, Eugene Belilovsky
In Federated Learning, a global model is learned by aggregating model updates computed at a set of independent client nodes, to reduce communication costs multiple gradient steps a…
Building a Subspace of Policies for Scalable Continual Learning
Jean-Baptiste Gaya, Thang Doan, Lucas Caccia +3
The ability to continuously acquire new knowledge and skills is crucial for autonomous agents. Existing methods are typically based on either fixed-size models that struggle to lea…
New Insights on Reducing Abrupt Representation Change in Online Continual Learning
Lucas Caccia, Rahaf Aljundi, Nader Asadi +3
In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small sub…
Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning
Eugene Belilovsky, Louis Leconte, Lucas Caccia +2
A commonly cited inefficiency of neural network training using back-propagation is the update locking problem: each layer must wait for the signal to propagate through the full net…
On Anytime Learning at Macroscale
Lucas Caccia, Jing Xu, Myle Ott +2
In many practical applications of machine learning data arrives sequentially over time in large chunks. Practitioners have then to decide how to allocate their computational budget…
New Insights on Reducing Abrupt Representation Change in Online Continual Learning
Lucas Caccia, Rahaf Aljundi, Nader Asadi +3
In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small sub…
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…
Recurrent Value Functions
Pierre Thodoroff, Nishanth Anand, Lucas Caccia +2
Despite recent successes in Reinforcement Learning, value-based methods often suffer from high variance hindering performance. In this paper, we illustrate this in a continuous con…