1 citations · 2 across the 8 of their papers we have counts for
8 papers
Just-In-Time Piecewise-Linear Semantics for ReLU-type Networks
Hongyi Duan, Haoyang Liu, Jian'an Zhang +2
We present a JIT PL semantics for ReLU-type networks that compiles models into a guarded CPWL transducer with shared guards. The system adds hyperplanes only when operands are affi…
Triangle Detection in Worst-Case Sparse Graphs via Local Sketching
Hongyi Duan, Jian'an Zhang
We present a non-algebraic, locality-preserving framework for triangle detection in worst-case sparse graphs. Our algorithm processes the graph in independent layers an…
Rethinking Selectivity in State Space Models: A Minimal Predictive Sufficiency Approach
Yiyi Wang, Jian'an Zhang, Hongyi Duan +2
State Space Models (SSMs), particularly recent selective variants like Mamba, have emerged as a leading architecture for sequence modeling, challenging the dominance of Transformer…
A case study of the Lunger phenomenon based on multiple algorithms
Zhang Jianan, Wang Yiyi, Duan Hongyi +1
In this study, we conduct a thorough and meticulous examination of the Runge phenomenon. Initially, we engage in an extensive review of relevant literature, which aids in delineati…
Analyzing Bridge Resonance and Lateral Vibrations Using String Vibration Principles
Zhang Jianan, Wang yiyi, Duan Hongyi +1
This article investigates the lateral vibration and resonance of bridges, crucial for transportation network integrity and traffic safety. It aims to understand the underlying prin…
Improvement and Enhancement of YOLOv5 Small Target Recognition Based on Multi-module Optimization
Qingyang Li, Yuchen Li, Hongyi Duan +4
In this paper, the limitations of YOLOv5s model on small target detection task are deeply studied and improved. The performance of the model is successfully enhanced by introducing…
Comparative study of microgrid optimal scheduling under multi-optimization algorithm fusion
Hongyi Duan, Qingyang Li, Yuchen Li +2
As global attention on renewable and clean energy grows, the research and implementation of microgrids become paramount. This paper delves into the methodology of exploring the rel…
Enhanced LFTSformer: A Novel Long-Term Financial Time Series Prediction Model Using Advanced Feature Engineering and the DS Encoder Informer Architecture
Jianan Zhang, Hongyi Duan
This study presents a groundbreaking model for forecasting long-term financial time series, termed the Enhanced LFTSformer. The model distinguishes itself through several significa…