IEEE

Fast Weighted Transforms for Linear Convolution

Abstract: Convolution is fundamental in digital signal processing across many applications. Existing works enable N-point linear convolution via N-point right-angle circular convolution (RCC) based on ...
IEEE

Benchmarking Diffusion Annealing-Based Bayesian Inverse Problem Solvers

Abstract: In recent years, the ascendance of diffusion modeling as a state-of-the-art generative modeling approach has spurred significant interest in their use as priors in Bayesian inverse problems.
GitHub

BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding

This is the official implementation of the paper BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding, which is accepted by CVPR2025. Large video-language models ...
GitHub

Blaze3DM: Integrating Triplane Representation with Diffusion for Solving 3D Inverse Problems in Medical Imaging

This repository Blaze3DM is the official implementation of the paper [Blaze3DM: Integrating Triplane Representation with Diffusion for Solving 3D Inverse Problems in Medical Imaging]. The paper has ...