From the 1 of 4 linked papers with an AI index.
2 citations · 2 across the 2 of their papers we have counts for
4 papers
Post-Disaster Affected Area Segmentation with a Vision Transformer (ViT)-based EVAP Model using Sentinel-2 and Formosat-5 Imagery
Yi-Shan Chu, Hsuan-Cheng Wei
The paper presents a vision‑transformer based framework that expands a small set of manually labeled disaster areas using PCA and a confidence index, then trains encoder‑decoder mo…
S-GAI: Spectral Geometry-Aware Initialization for Sigmoidal MLPs -- From Dataset Geometry to Network Weights
Yi-Shan Chu
Classical universal approximation theorems establish the expressive power of sigmoidal multilayer perceptrons, but they do not prescribe how initial weights should encode the geome…
Seeing Symbols, Missing Cultures: Probing Vision-Language Models' Reasoning on Fire Imagery and Cultural Meaning
Haorui Yu, Yang Zhao, Yijia Chu +1
Vision-Language Models (VLMs) often appear culturally competent but rely on superficial pattern matching rather than genuine cultural understanding. We introduce a diagnostic frame…
From Universal Approximation Theorem to Tropical Geometry of Multi-Layer Perceptrons
Yi-Shan Chu, Yueh-Cheng Kuo
We revisit the Universal Approximation Theorem(UAT) through the lens of the tropical geometry of neural networks and introduce a constructive, geometry-aware initialization for sig…