Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributions
Yongju Jia, Jiarui Ma, Xiangxian Li +4
Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive capability in visual tasks, but their fine-tuning often suffers from bias in class-imbalanced…
cs.CV2024
LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations
Zejian Li, Chenye Meng, Yize Li +9
Recent advances in text-to-image (T2I) generation have shown remarkable success in producing high-quality images from text. However, existing T2I models show decayed performance in…