3 papers
cs.CV2026
Progressive Decision-Making for Localizing Open-Ended AI-Generated Image Forgeries
Jingyi Hou, Xiaoxia Chen, Leyu Zhou +2
AI-generated image forgeries are becoming increasingly realistic and difficult to characterize with fixed manipulation patterns. As generative models continue to evolve, it is impr…
cs.CL2025
Unveiling the Impact of Multimodal Features on Chinese Spelling Correction: From Analysis to Design
Xiaowu Zhang, Hongfei Zhao, Jingyi Hou +1
The Chinese Spelling Correction (CSC) task focuses on detecting and correcting spelling errors in sentences. Current research primarily explores two approaches: traditional multimo…
cs.LG2023
Discovering Predictable Latent Factors for Time Series Forecasting
Jingyi Hou, Zhen Dong, Jiayu Zhou +1
Modern time series forecasting methods, such as Transformer and its variants, have shown strong ability in sequential data modeling. To achieve high performance, they usually rely…