From the 1 of 5 linked papers with an AI index.
5 papers
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…
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…
Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling
Hayeon Kim, Ji Ha Jang, Se Young Chun
Recent advances in 3D neural representations and instance-level editing models have enabled the efficient creation of high-quality 3D content. However, achieving precise local 3D e…
Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models
Hoigi Seo, Byung Hyun Lee, Jaehyun Cho +2
Large-scale text-to-image (T2I) diffusion models deliver remarkable visual fidelity but pose safety risks due to their capacity to reproduce undesirable content, such as copyrighte…
On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
Hoigi Seo, Dong Un Kang, Hyunjin Cho +2
Large vision-language models (LVLMs), which integrate a vision encoder (VE) with a large language model, have achieved remarkable success across various tasks. However, there are s…