3 papers
cs.CV2025
DeCoT: Decomposing Complex Instructions for Enhanced Text-to-Image Generation with Large Language Models
Xiaochuan Lin, Xiangyong Chen, Xuan Li +1
Despite remarkable advancements, current Text-to-Image (T2I) models struggle with complex, long-form textual instructions, frequently failing to accurately render intricate details…
cs.CL2025
Generating Medically-Informed Explanations for Depression Detection using LLMs
Xiangyong Chen, Xiaochuan Lin
Early detection of depression from social media data offers a valuable opportunity for timely intervention. However, this task poses significant challenges, requiring both professi…
cs.CL2024
Reasoning-Aware Query-Focused Summarization over Multi-Table Data
Xiaochuan Lin, Xiangyong Chen
Query-focused summarization over multi-table data is a challenging yet critical task for extracting precise and relevant information from structured data. Existing methods often re…