5 papers
General and Efficient Steering of Diffusion Models
Qingsong Wang, Mikhail Belkin, Yusu Wang
Steering diffusion models toward conditions unseen during training typically requires either retraining with conditional inputs or per-step gradient computations, both of which inc…
MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning
Jesse He, Helen Jenne, Max Vargas +4
The recent field of neural algorithmic reasoning (NAR) studies the ability of graph neural networks (GNNs) to emulate classical algorithms like Bellman-Ford, a phenomenon known as…
Two Calm Ends and the Wild Middle: A Geometric Picture of Memorization in Diffusion Models
Nick Dodson, Xinyu Gao, Qingsong Wang +2
Diffusion models generate high-quality samples but can also memorize training data, raising serious privacy concerns. Understanding the mechanisms governing when memorization versu…
Explaining GNN Explanations with Edge Gradients
Jesse He, Akbar Rafiey, Gal Mishne +1
In recent years, the remarkable success of graph neural networks (GNNs) on graph-structured data has prompted a surge of methods for explaining GNN predictions. However, the state-…
Elucidating Flow Matching ODE Dynamics with Respect to Data Geometries and Denoisers
Zhengchao Wan, Qingsong Wang, Gal Mishne +1
Flow matching (FM) models extend ODE sampler based diffusion models into a general framework, significantly reducing sampling steps through learned vector fields. However, the theo…