GitHub

Bayesian Curriculum Learning over the Latent

This repository contains the official implementation for Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models. The paper introduces two main components: ...
GitHub

A Bayesian Approach to Segmentation with Noisy Labels via Spatially Correlated Distributions

Our approach models label noise in semantic segmentation with a probabilistic framework that incorporates spatial correlations. By introducing a continuous latent ...
IEEE

Bayesian Spatio-Temporal Graph Convolutional Network for Railway Train Delay Prediction

Abstract: This study introduces a novel approach that integrates dynamic Bayesian network with attention based spatio-temporal graph convolutional network to forecast railway train delays, capturing ...
IEEE

Prototype Bayesian Meta-Learning for Few-Shot Image Classification

Abstract: Meta-learning aims to leverage prior knowledge from related tasks to enable a base learner to quickly adapt to new tasks with limited labeled samples. However, traditional meta-learning ...