Amin Ullah — accepted AI-conference papers

2025

Convex Potential Mirror Langevin Algorithm for Efficient Sampling of Energy-Based Models

Yang Zitao, Amin Ullah, Shuai Li, Li Fuxin, Jun Li

NeurIPS 2025poster

This paper introduces the Convex Potential Mirror Langevin Algorithm (CPMLA), a novel method to improve sampling efficiency for Energy-Based Models (EBMs). CPMLA uses mirror Langevin dynamics with a convex potential flow as a dynamic mirror map for EBM sampling. This dynamic mirror map enables targe…

Cited by 0 Source ↗Scholar ↗

2024

CVAE-SM: A Conditional Variational Autoencoder with Style Modulation for Efficient Uncertainty Quantification

Amin Ullah, Taiqing Yan, Li Fuxin

ICRA 2024poster

Deep learning has brought transformative advancements to object segmentation, especially in marine robotics contexts such as waste management and subaquatic infrastructure oversight. However, a central challenge persists: calibrating the prediction confidence of the model to ensure robust and reliab…

Cited by 0 Source ↗Scholar ↗