activity
20182022
most citedPlug and Play Language Models: A Simple Approach to Controlled Text Generation

141 citations · 146 across the 4 of their papers we have counts for

collaborators

12 papers

cs.LG20222 cited

When less is more: Simplifying inputs aids neural network understanding

Robin Tibor Schirrmeister, Rosanne Liu, Sara Hooker +1

How do neural network image classifiers respond to simpler and simpler inputs? And what do such responses reveal about the learning process? To answer these questions, we need a cl…

cs.CL2021

Language Models are Few-shot Multilingual Learners

Genta Indra Winata, Andrea Madotto, Zhaojiang Lin +3

General-purpose language models have demonstrated impressive capabilities, performing on par with state-of-the-art approaches on a range of downstream natural language processing (…

cs.LG20212 cited

When does loss-based prioritization fail?

Niel Teng Hu, Xinyu Hu, Rosanne Liu +2

Not all examples are created equal, but standard deep neural network training protocols treat each training point uniformly. Each example is propagated forward and backward through…

cs.LG20211 cited

Why is Pruning at Initialization Immune to Reinitializing and Shuffling?

Sahib Singh, Rosanne Liu

Recent studies assessing the efficacy of pruning neural networks methods uncovered a surprising finding: when conducting ablation studies on existing pruning-at-initialization meth…

cs.LG2020

Supermasks in Superposition

Mitchell Wortsman, Vivek Ramanujan, Rosanne Liu +4

We present the Supermasks in Superposition (SupSup) model, capable of sequentially learning thousands of tasks without catastrophic forgetting. Our approach uses a randomly initial…

cs.LG2020

Estimating Q(s,s') with Deep Deterministic Dynamics Gradients

Ashley D. Edwards, Himanshu Sahni, Rosanne Liu +7

In this paper, we introduce a novel form of value function, , that expresses the utility of transitioning from a state to a neighboring state and then acting opt…