5 papers
Multi-Granularity Reasoning for Image Quality Assessment via Attribute-Aware Reinforcement Learning to Rank
Xiangyong Chen, Xiaochuan Lin, Haoran Liu +3
Recent advances in reasoning-induced image quality assessment (IQA) have demonstrated the power of reinforcement learning to rank (RL2R) for training vision-language models (VLMs)…
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…
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…
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…
Improving Visual Storytelling with Multimodal Large Language Models
Xiaochuan Lin, Xiangyong Chen
Visual storytelling is an emerging field that combines images and narratives to create engaging and contextually rich stories. Despite its potential, generating coherent and emotio…