9 citations · 15 across the 8 of their papers we have counts for
8 papers
Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language Models
Sameera Horawalavithana, Lauren Phillips, Ian Stewart +2
Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new and more capable LLMs emerge…
Recursive Decoding: A Situated Cognition Approach to Compositional Generation in Grounded Language Understanding
Matthew Setzler, Scott Howland, Lauren Phillips
Compositional generalization is a troubling blind spot for neural language models. Recent efforts have presented techniques for improving a model's ability to encode novel combinat…
Adaptive Transfer Learning: a simple but effective transfer learning
Jung H Lee, Henry J Kvinge, Scott Howland +7
Transfer learning (TL) leverages previously obtained knowledge to learn new tasks efficiently and has been used to train deep learning (DL) models with limited amount of data. When…
Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with Perceivers
Piper Wolters, Logan Sizemore, Chris Daw +2
Many applications involve detecting and localizing specific sound events within long, untrimmed documents, including keyword spotting, medical observation, and bioacoustic monitori…
One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representations
Henry Kvinge, Scott Howland, Nico Courts +9
The field of few-shot learning has made remarkable strides in developing powerful models that can operate in the small data regime. Nearly all of these methods assume every unlabel…
Prototypical Region Proposal Networks for Few-Shot Localization and Classification
Elliott Skomski, Aaron Tuor, Andrew Avila +5
Recently proposed few-shot image classification methods have generally focused on use cases where the objects to be classified are the central subject of images. Despite success on…
A Study of Few-Shot Audio Classification
Piper Wolters, Chris Careaga, Brian Hutchinson +1
Advances in deep learning have resulted in state-of-the-art performance for many audio classification tasks but, unlike humans, these systems traditionally require large amounts of…
Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning
Henry Kvinge, Zachary New, Nico Courts +6
Deep learning has shown great success in settings with massive amounts of data but has struggled when data is limited. Few-shot learning algorithms, which seek to address this limi…