papers

Publications (8)

cs.SI2022

Patterns of Patterns

Joseph Corneli, Alex Murphy, Raymond S. Puzio +5

This paper shows how we combine and adapt methods from elite training, future studies, and collaborative design, and apply them to address significant problems in social networks.…

physics.ins-det2014

Background Assay and Rejection in DRIFT

Jeff Brack, Ed Daw, Alexei Dorofeev +22

The DRIFT-IId dark matter detector is a m-scale low-pressure TPC with directional sensitivity to WIMP-induced nuclear recoils. Its primary backgrounds were due to alpha decays…

cs.LG2024

Finding Shared Decodable Concepts and their Negations in the Brain

Cory Efird, Alex Murphy, Joel Zylberberg +1

Prior work has offered evidence for functional localization in the brain; different anatomical regions preferentially activate for certain types of visual input. For example, the f…

cs.LG2024

Exploring Curriculum Learning for Vision-Language Tasks: A Study on Small-Scale Multimodal Training

Rohan Saha, Abrar Fahim, Alona Fyshe +1

For specialized domains, there is often not a wealth of data with which to train large machine learning models. In such limited data / compute settings, various methods exist aimin…

cs.AI2023

Identifying Shared Decodable Concepts in the Human Brain Using Image-Language Foundation Models

Cory Efird, Alex Murphy, Joel Zylberberg +1

We introduce a method that takes advantage of high-quality pretrained multimodal representations to explore fine-grained semantic networks in the human brain. Previous studies have…

q-bio.NC2024

Correcting Biased Centered Kernel Alignment Measures in Biological and Artificial Neural Networks

Alex Murphy, Joel Zylberberg, Alona Fyshe

Centred Kernel Alignment (CKA) has recently emerged as a popular metric to compare activations from biological and artificial neural networks (ANNs) in order to quantify the alignm…

cs.CV2024

It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap

Abrar Fahim, Alex Murphy, Alona Fyshe

Multi-modal contrastive models such as CLIP achieve state-of-the-art performance in zero-shot classification by embedding input images and texts on a joint representational space.…

cs.SI2024

Patterns of Patterns II

Joseph Corneli, Noorah Alhasan, Leo Vivier +9

Our earlier paper "Patterns of Patterns" combined three techniques from training, futures studies, and design in a design pattern called PLACARD that helps groups of people work to…