GitHub

Neural Importance Sampling of Many Lights

This is the official implementation of the paper, titled "Neural Importance Sampling of Many Lights", to be presented at ACM SIGGRAPH 2025 (conference track). We propose a hybrid neural approach for ...
IEEE

Accelerating Convergence of Stein Variational Gradient Descent via Deep Unfolding

Abstract: Stein variational gradient descent (SVGD) is a prominent particle-based variational inference method used for sampling a target distribution. In this paper, we propose two novel trainable ...
IEEE

Distributed Variational Inference for Online Supervised Learning

Abstract: This article introduces a scalable distributed probabilistic inference algorithm for intelligent sensor networks, tackling challenges of continuous variables, intractable posteriors, and ...
GitHub

Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score-Based Generative Models

We propose Ψ-Sampler, an SMC-based framework that improves inference-time reward alignment in score-based generative models via efficient posterior initialization using the pCNL algorithm. We ...