3 papers
cs.CV2025
Positional Bias in Multimodal Embedding Models: Do They Favor the Beginning, the Middle, or the End?
Kebin Wu, Fatima Albreiki
Positional bias - where models overemphasize certain positions regardless of content - has been shown to negatively impact model performance across various tasks. While recent rese…
cs.CV2025
FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs
Mothilal Asokan, Kebin Wu, Fatima Albreiki
As a pioneering vision-language model, CLIP (Contrastive Language-Image Pre-training) has achieved significant success across various domains and a wide range of downstream vision-…
cs.CL2025
VisCon-100K: Leveraging Contextual Web Data for Fine-tuning Vision Language Models
Gokul Karthik Kumar, Iheb Chaabane, Kebin Wu
Vision-language models (VLMs) excel in various visual benchmarks but are often constrained by the lack of high-quality visual fine-tuning data. To address this challenge, we introd…