hyperbolic embeddings 1part-whole relationships 1uncertainty modeling 1vision-language models 1zero-shot learning 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CV2026
Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models
Hayeon Kim, Ji Ha Jang, Junghun James Kim +1
The paper introduces UNCHA, a method that uses hyperbolic uncertainty to weight the importance of image parts when aligning vision and language embeddings, improving the modeling o…
cs.CV2026
HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding
Ji Ha Jang, Hayeon Kim, Chulwon Lee +2
CLIP (Contrastive Language-Image Pre-training) has become a de facto paradigm for image-text alignment, but it struggles with long-context descriptions (>77 tokens) due to absolute…
cs.AI2024
Accurate Link Prediction for Edge-Incomplete Graphs via PU Learning
Junghun Kim, Ka Hyun Park, Hoyoung Yoon +1
Given an edge-incomplete graph, how can we accurately find the missing links? The link prediction in edge-incomplete graphs aims to discover the missing relations between entities…