works on

From the 1 of 10 linked papers with an AI index.

activity
20242026
collaborators

10 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

Integration Matters: Rollout-Based Training for Constrained Diffusion Models

Xiaoxuan Liang, Saeid Naderiparizi, Berend Zwartsenberg +1

The paper introduces a fine‑tuning method that uses online rollout to guide constraint enforcement during training of diffusion models, aligning training with the sampling process…

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.LG2026

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…

cs.LG2025

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…

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…