102 citations · 315 across the 32 of their papers we have counts for
8 papers · 1 filter
Graphically Structured Diffusion Models
Christian Weilbach, William Harvey, Frank Wood
We introduce a framework for automatically defining and learning deep generative models with problem-specific structure. We tackle problem domains that are more traditionally solve…
Vehicle Type Specific Waypoint Generation
Yunpeng Liu, Jonathan Wilder Lavington, Adam Scibior +1
We develop a generic mechanism for generating vehicle-type specific sequences of waypoints from a probabilistic foundation model of driving behavior. Many foundation behavior model…
Conditional Permutation Invariant Flows
Berend Zwartsenberg, Adam Ścibior, Matthew Niedoba +7
We present a novel, conditional generative probabilistic model of set-valued data with a tractable log density. This model is a continuous normalizing flow governed by permutation…
Critic Sequential Monte Carlo
Vasileios Lioutas, Jonathan Wilder Lavington, Justice Sefas +6
We introduce CriticSMC, a new algorithm for planning as inference built from a composition of sequential Monte Carlo with learned Soft-Q function heuristic factors. These heuristic…
Flexible Diffusion Modeling of Long Videos
William Harvey, Saeid Naderiparizi, Vaden Masrani +2
We present a framework for video modeling based on denoising diffusion probabilistic models that produces long-duration video completions in a variety of realistic environments. We…
Gradients without Backpropagation
Atılım Güneş Baydin, Barak A. Pearlmutter, Don Syme +2
Using backpropagation to compute gradients of objective functions for optimization has remained a mainstay of machine learning. Backpropagation, or reverse-mode differentiation, is…
Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning
Michael Teng, Michiel van de Panne, Frank Wood
Distributional reinforcement learning (RL) aims to learn a value-network that predicts the full distribution of the returns for a given state, often modeled via a quantile-based cr…
Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning
Peyman Bateni, Jarred Barber, Raghav Goyal +4
Modern deep learning requires large-scale extensively labelled datasets for training. Few-shot learning aims to alleviate this issue by learning effectively from few labelled examp…