6 papers · 1 filter
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…