1 citations · 4 across the 18 of their papers we have counts for
18 papers
Mirror Learning
Yunpeng Liu, Matthew Niedoba, Oluwanifemi A. Adekanye +4
We investigate imitation learning through the lens of third-person observation and propose a framework for mirror learning: acquiring actionable policies from passive observation.…
Integration Matters: Rollout-Based Training for Constrained Diffusion Models
Xiaoxuan Liang, Saeid Naderiparizi, Berend Zwartsenberg +1
Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution. Existing constrained generation…
Filtered Posterior Mean Collections: A Unified Framework for Analytical Models of Diffusion Generalization
Matthew Niedoba, Berend Zwartsenberg, Frank Wood
The neural-network denoising functions which form the backbone of image diffusion models are remarkably consistent in their generalization behaviour across a wide variety of networ…
Improved Constrained Generation by Bridging Pretrained Generative Models
Xiaoxuan Liang, Saeid Naderiparizi, Yunpeng Liu +2
Constrained generative modeling is fundamental to applications such as robotic control and autonomous driving, where models must respect physical laws and safety-critical constrain…
Constrained Generative Modeling with Manually Bridged Diffusion Models
Saeid Naderiparizi, Xiaoxuan Liang, Berend Zwartsenberg +1
In this paper we describe a novel framework for diffusion-based generative modeling on constrained spaces. In particular, we introduce manual bridges, a framework that expands the…
Rolling Ahead Diffusion for Traffic Scene Simulation
Yunpeng Liu, Matthew Niedoba, William Harvey +3
Realistic driving simulation requires that NPCs not only mimic natural driving behaviors but also react to the behavior of other simulated agents. Recent developments in diffusion-…
Control-ITRA: Controlling the Behavior of a Driving Model
Vasileios Lioutas, Adam Scibior, Matthew Niedoba +2
Simulating realistic driving behavior is crucial for developing and testing autonomous systems in complex traffic environments. Equally important is the ability to control the beha…
Towards a Mechanistic Explanation of Diffusion Model Generalization
Matthew Niedoba, Berend Zwartsenberg, Kevin Murphy +1
We propose a simple, training-free mechanism which explains the generalization behaviour of diffusion models. By comparing pre-trained diffusion models to their theoretically optim…
TorchDriveEnv: A Reinforcement Learning Benchmark for Autonomous Driving with Reactive, Realistic, and Diverse Non-Playable Characters
Jonathan Wilder Lavington, Ke Zhang, Vasileios Lioutas +9
The training, testing, and deployment, of autonomous vehicles requires realistic and efficient simulators. Moreover, because of the high variability between different problems pres…
Semantically Consistent Video Inpainting with Conditional Diffusion Models
Dylan Green, William Harvey, Saeid Naderiparizi +10
Current state-of-the-art methods for video inpainting typically rely on optical flow or attention-based approaches to inpaint masked regions by propagating visual information acros…
Nearest Neighbour Score Estimators for Diffusion Generative Models
Matthew Niedoba, Dylan Green, Saeid Naderiparizi +9
Score function estimation is the cornerstone of both training and sampling from diffusion generative models. Despite this fact, the most commonly used estimators are either biased…
A Diffusion-Model of Joint Interactive Navigation
Matthew Niedoba, Jonathan Wilder Lavington, Yunpeng Liu +8
Simulation of autonomous vehicle systems requires that simulated traffic participants exhibit diverse and realistic behaviors. The use of prerecorded real-world traffic scenarios i…
Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidance
Saeid Naderiparizi, Xiaoxuan Liang, Setareh Cohan +2
Score-based diffusion models are a powerful class of generative models, widely utilized across diverse domains. Despite significant advancements in large-scale tasks such as text-t…
Realistically distributing object placements in synthetic training data improves the performance of vision-based object detection models
Setareh Dabiri, Vasileios Lioutas, Berend Zwartsenberg +8
When training object detection models on synthetic data, it is important to make the distribution of synthetic data as close as possible to the distribution of real data. We invest…
Video Killed the HD-Map: Predicting Multi-Agent Behavior Directly From Aerial Images
Yunpeng Liu, Vasileios Lioutas, Jonathan Wilder Lavington +8
The development of algorithms that learn multi-agent behavioral models using human demonstrations has led to increasingly realistic simulations in the field of autonomous driving.…
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…
Probabilistic Surrogate Networks for Simulators with Unbounded Randomness
Andreas Munk, Berend Zwartsenberg, Adam Ścibior +5
We present a framework for automatically structuring and training fast, approximate, deep neural surrogates of stochastic simulators. Unlike traditional approaches to surrogate mod…