IEEE

Cable Fault Double-Ended Ranging Algorithm Based on Improved Wavelet Threshold Denoising and TT Transform

Abstract: To address the problem of large errors in single-end fault ranging for distribution cables, this paper proposes an offline double-end ranging method based on improved wavelet threshold ...
IEEE

Antinoise Bearing Fault Diagnosis Using Time-Reassigned Multisynchrosqueezing Transform and Complex Sparse Learning Dictionary

Abstract: Bearings are core components of rotating machinery, and their operating status monitoring and fault diagnosis are crucial for equipment health management. Accurately identifying fault ...
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. Code will be released soon.
GitHub

A tiny LM that does inference at compile time

This project pushes the boundaries of C++ template metaprogramming by implementing a Language Model that performs inference entirely at compile-time. Instead of calculating text during runtime, the ...