128 citations · 351 across the 8 of their papers we have counts for
9 papers
Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining
Nicholas Monath, Manzil Zaheer, Kelsey Allen +1
Dual encoder models are ubiquitous in modern classification and retrieval. Crucial for training such dual encoders is an accurate estimation of gradients from the partition functio…
Learning rigid dynamics with face interaction graph networks
Kelsey R. Allen, Yulia Rubanova, Tatiana Lopez-Guevara +4
Simulating rigid collisions among arbitrary shapes is notoriously difficult due to complex geometry and the strong non-linearity of the interactions. While graph neural network (GN…
Physical Design using Differentiable Learned Simulators
Kelsey R. Allen, Tatiana Lopez-Guevara, Kimberly Stachenfeld +4
Designing physical artifacts that serve a purpose - such as tools and other functional structures - is central to engineering as well as everyday human behavior. Though automating…
Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning
Kelsey R. Allen, Kevin A. Smith, Joshua B. Tenenbaum
Many animals, and an increasing number of artificial agents, display sophisticated capabilities to perceive and manipulate objects. But human beings remain distinctive in their cap…
Few-Shot Bayesian Imitation Learning with Logical Program Policies
Tom Silver, Kelsey R. Allen, Alex K. Lew +2
Humans can learn many novel tasks from a very small number (1--5) of demonstrations, in stark contrast to the data requirements of nearly tabula rasa deep learning methods. We prop…
Infinite Mixture Prototypes for Few-Shot Learning
Kelsey R. Allen, Evan Shelhamer, Hanul Shin +1
We propose infinite mixture prototypes to adaptively represent both simple and complex data distributions for few-shot learning. Our infinite mixture prototypes represent each clas…
Residual Policy Learning
Tom Silver, Kelsey Allen, Josh Tenenbaum +1
We present Residual Policy Learning (RPL): a simple method for improving nondifferentiable policies using model-free deep reinforcement learning. RPL thrives in complex robotic man…
Relational inductive bias for physical construction in humans and machines
Jessica B. Hamrick, Kelsey R. Allen, Victor Bapst +4
While current deep learning systems excel at tasks such as object classification, language processing, and gameplay, few can construct or modify a complex system such as a tower of…
Relational inductive biases, deep learning, and graph networks
Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst +24
Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, i…