4 papers
Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient Experts
Sanae Lotfi, Lucas Caccia, Alessandro Sordoni +2
While large language models (LLMs) fine-tuned with lightweight adapters achieve strong performance across diverse tasks, their performance on individual tasks depends on the fine-t…
Towards Active Synthetic Data Generation for Finetuning Language Models
Samuel Kessler, Menglin Xia, Daniel Madrigal Diaz +5
A common and effective means for improving language model capabilities involves finetuning a ``student'' language model's parameters on generations from a more proficient ``teacher…
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…
A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
Arthur Juliani, Jordan T. Ash
Continual learning with deep neural networks presents challenges distinct from both the fixed-dataset and convex continual learning regimes. One such challenge is plasticity loss,…