37 citations · 94 across the 12 of their papers we have counts for
10 papers · 1 filter
Generative Classifiers Avoid Shortcut Solutions
Alexander C. Li, Ananya Kumar, Deepak Pathak
Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail even under minor distribution shift. This failure mode stems from an overrelian…
On the Surprising Effectiveness of Attention Transfer for Vision Transformers
Alexander C. Li, Yuandong Tian, Beidi Chen +2
Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate t…
An Introduction to Vision-Language Modeling
Florian Bordes, Richard Yuanzhe Pang, Anurag Ajay +38
Following the recent popularity of Large Language Models (LLMs), several attempts have been made to extend them to the visual domain. From having a visual assistant that could guid…
Your Diffusion Model is Secretly a Zero-Shot Classifier
Alexander C. Li, Mihir Prabhudesai, Shivam Duggal +2
The recent wave of large-scale text-to-image diffusion models has dramatically increased our text-based image generation abilities. These models can generate realistic images for a…
Internet Explorer: Targeted Representation Learning on the Open Web
Alexander C. Li, Ellis Brown, Alexei A. Efros +1
Modern vision models typically rely on fine-tuning general-purpose models pre-trained on large, static datasets. These general-purpose models only capture the knowledge within thei…
Understanding Collapse in Non-Contrastive Siamese Representation Learning
Alexander C. Li, Alexei A. Efros, Deepak Pathak
Contrastive methods have led a recent surge in the performance of self-supervised representation learning (SSL). Recent methods like BYOL or SimSiam purportedly distill these contr…
Functional Regularization for Reinforcement Learning via Learned Fourier Features
Alexander C. Li, Deepak Pathak
We propose a simple architecture for deep reinforcement learning by embedding inputs into a learned Fourier basis and show that it improves the sample efficiency of both state-base…
Generalized Hindsight for Reinforcement Learning
Alexander C. Li, Lerrel Pinto, Pieter Abbeel
One of the key reasons for the high sample complexity in reinforcement learning (RL) is the inability to transfer knowledge from one task to another. In standard multi-task RL sett…
Autoregressive Models: What Are They Good For?
Murtaza Dalal, Alexander C. Li, Rohan Taori
Autoregressive (AR) models have become a popular tool for unsupervised learning, achieving state-of-the-art log likelihood estimates. We investigate the use of AR models as density…
Sub-policy Adaptation for Hierarchical Reinforcement Learning
Alexander C. Li, Carlos Florensa, Ignasi Clavera +1
Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lowe…