Asia
On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions
Kullback-Leibler (KL) divergence is one of the most important measures to calculate the difference between probability distributions. In this paper, we theoretically study several properties of KL divergence between multivariate Gaussian distributions.
Joint Prompt Optimization of Stacked LLMs using Variational Inference
Large language models (LLMs) can be seen as atomic units of computation mapping sequences to a distribution over sequences.
Dynamic 3D Gaussian Fields for Urban Areas T obias Fischer
We present an efficient neural 3D scene representation for novel-view synthesis (NVS) in large-scale, dynamic urban areas.
Understanding and Improving Ensemble Adversarial Defense
Guided by this theory, we propose an effective approach to improve ensemble adversarial defense, named interactive global adversarial training (iGA T).
FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
We qualitatively and quantitatively analyze FFAM with multiple detectors on several datasets. Experimental results validate the high-quality visual explanations produced by FFAM.
