activity
20242026
collaborators

6 papers

cs.LG2026

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.…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

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-…

cs.AI2025

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…

cs.CV2024

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…