2 papers
cs.LG2026
Marginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Models
Duong Bach, Hai Nguyen Hong, Cuong Do
Factorized generative models commonly regularize a latent style variable z_s by matching its marginal distribution to a fixed Gaussian prior and interpret this as evidence that the…
cs.CV2025
Investigating Market Strength Prediction with CNNs on Candlestick Chart Images
Thanh Nam Duong, Trung Kien Hoang, Quoc Khanh Duong +5
This paper investigates predicting market strength solely from candlestick chart images to assist investment decisions. The core research problem is developing an effective compute…