Thomas Hannagan — accepted AI-conference papers

2024

Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation

Yixiao Wang*, Chen Tang, Lingfeng Sun, Simone Rossi, Yichen Xie, Chensheng Peng +5

ECCV 2024poster

"Diffusion models are promising for joint trajectory prediction and controllable generation in autonomous driving, but they face challenges of inefficient inference steps and high computational demands. To tackle these challenges, we introduce Optimal Gaussian Diffusion (OGD) and Estimated Clean Man…

Cited by 29 Source ↗PDF ↗code ↗Scholar ↗

2023

On permutation symmetries in Bayesian neural network posteriors: a variational perspective

Simone Rossi, Ankit Singh, Thomas Hannagan

NeurIPS 2023poster

The elusive nature of gradient-based optimization in neural networks is tied to their loss landscape geometry, which is poorly understood. However recent work has brought solid evidence that there is essentially no loss barrier between the local solutions of gradient descent, once accounting for wei…

Cited by 5 Source ↗PDF ↗Scholar ↗