2 papers
cs.CV2024
Evaluating Hallucination in Text-to-Image Diffusion Models with Scene-Graph based Question-Answering Agent
Ziyuan Qin, Dongjie Cheng, Haoyu Wang +5
Contemporary Text-to-Image (T2I) models frequently depend on qualitative human evaluations to assess the consistency between synthesized images and the text prompts. There is a dem…
cs.LG2024
Calibrated Self-Rewarding Vision Language Models
Yiyang Zhou, Zhiyuan Fan, Dongjie Cheng +7
Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. Despite th…