79 citations · 113 across the 6 of their papers we have counts for
6 papers
Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?
C. Daniel Freeman, Laura Culp, Aaron Parisi +27
We introduce and study the problem of adversarial arithmetic, which provides a simple yet challenging testbed for language model alignment. This problem is comprised of arithmetic…
Probing clustering in neural network representations
Thao Nguyen, Simon Kornblith
Neural network representations contain structure beyond what was present in the training labels. For instance, representations of images that are visually or semantically similar t…
Synthetic Data from Diffusion Models Improves ImageNet Classification
Shekoofeh Azizi, Simon Kornblith, Chitwan Saharia +2
Deep generative models are becoming increasingly powerful, now generating diverse high fidelity photo-realistic samples given text prompts. Have they reached the point where models…
Does progress on ImageNet transfer to real-world datasets?
Alex Fang, Simon Kornblith, Ludwig Schmidt
Does progress on ImageNet transfer to real-world datasets? We investigate this question by evaluating ImageNet pre-trained models with varying accuracy (57% - 83%) on six practical…
A Study on Self-Supervised Object Detection Pretraining
Trung Dang, Simon Kornblith, Huy Thong Nguyen +2
In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense rep…
Patching open-vocabulary models by interpolating weights
Gabriel Ilharco, Mitchell Wortsman, Samir Yitzhak Gadre +5
Open-vocabulary models like CLIP achieve high accuracy across many image classification tasks. However, there are still settings where their zero-shot performance is far from optim…