collaborators

5 papers

cs.CV2026

Twin Co-Adaptive Dialogue for Progressive Image Generation

Jianhui Wang, Yangfan He, Yan Zhong +12

Modern text-to-image generation systems have enabled the creation of remarkably realistic and high-quality visuals, yet they often falter when handling the inherent ambiguities in…

cs.CL2025

SCORE: Story Coherence and Retrieval Enhancement for AI Narratives

Qiang Yi, Yangfan He, Jianhui Wang +18

Large Language Models (LLMs) can generate creative and engaging narratives from user-specified input, but maintaining coherence and emotional depth throughout these AI-generated st…

cs.CV2025

ReGraP-LLaVA: Reasoning enabled Graph-based Personalized Large Language and Vision Assistant

Yifan Xiang, Zhenxi Zhang, Bin Li +4

Recent advances in personalized MLLMs enable effective capture of user-specific concepts, supporting both recognition of personalized concepts and contextual captioning. However, h…

cs.CV2025

Optimizing Multi-Round Enhanced Training in Diffusion Models for Improved Preference Understanding

Kun Li, Jianhui Wang, Yangfan He +10

Generative AI has significantly changed industries by enabling text-driven image generation, yet challenges remain in achieving high-resolution outputs that align with fine-grained…

cs.CV2025

Efficient Temporal Consistency in Diffusion-Based Video Editing with Adaptor Modules: A Theoretical Framework

Xinyuan Song, Yangfan He, Sida Li +10

Adapter-based methods are commonly used to enhance model performance with minimal additional complexity, especially in video editing tasks that require frame-to-frame consistency.…