12 citations · 22 across the 10 of their papers we have counts for
5 papers · 1 filter
Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits
Neha Kalibhat, Zi Wang, Prasoon Bajpai +4
We introduce a black-box interpretability framework that learns a verifiable constitution: a natural language summary of how changes to a prompt affect a model's specific behavior,…
Augmentations vs Algorithms: What Works in Self-Supervised Learning
Warren Morningstar, Alex Bijamov, Chris Duvarney +8
We study the relative effects of data augmentations, pretraining algorithms, and model architectures in Self-Supervised Learning (SSL). While the recent literature in this space le…
Measuring Self-Supervised Representation Quality for Downstream Classification using Discriminative Features
Neha Kalibhat, Kanika Narang, Hamed Firooz +2
Self-supervised learning (SSL) has shown impressive results in downstream classification tasks. However, there is limited work in understanding their failure modes and interpreting…
Understanding Overparameterization in Generative Adversarial Networks
Yogesh Balaji, Mohammadmahdi Sajedi, Neha Mukund Kalibhat +4
A broad class of unsupervised deep learning methods such as Generative Adversarial Networks (GANs) involve training of overparameterized models where the number of parameters of th…
Winning Lottery Tickets in Deep Generative Models
Neha Mukund Kalibhat, Yogesh Balaji, Soheil Feizi
The lottery ticket hypothesis suggests that sparse, sub-networks of a given neural network, if initialized properly, can be trained to reach comparable or even better performance t…