13 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…
Lifelong Learning of Video Diffusion Models From a Single Video Stream
Jason Yoo, Yingchen He, Saeid Naderiparizi +4
Video diffusion models can enable embodied agents to anticipate plausible futures from the recent past, but they are typically trained offline on curated datasets--a mismatch with…
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…
Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning
Jason Yoo, Yunpeng Liu, Frank Wood +1
In online continual learning, a neural network incrementally learns from a non-i.i.d. data stream. Nearly all online continual learning methods employ experience replay to simultan…
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…