11 papers
Strong Helps Weak: Directional Cross-Modal Alignment Transfer in Multi-modal LLMs
Hoigi Seo, Byung Hyun Lee, Minjun Kim +3
Multi-modal large language models (MLLMs) achieve strong modality understanding by pairing a large language model (LLM) with an encoder for a target modality such as vision, video,…
Benchmarking Vision-Language Models for Automated Pathology Diagnosis and Report Generation
Yumi Lee, Harim Oh, Hyoryung Kim +52
The rapid advancement of vision-language models (VLMs) has accelerated progress in computational pathology; however, whole-slide image (WSI)-based pathology report generation remai…
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…
Unlearning the Unpromptable: Prompt-free Instance Unlearning in Diffusion Models
Kyungryeol Lee, Kyeonghyun Lee, Seongmin Hong +2
Machine unlearning aims to remove specific outputs from trained models, often at the concept level, such as forgetting all occurrences of a particular celebrity or filtering conten…
Continual Multiple Instance Learning with Enhanced Localization for Histopathological Whole Slide Image Analysis
Byung Hyun Lee, Wongi Jeong, Woojae Han +2
Multiple instance learning (MIL) significantly reduced annotation costs via bag-level weak labels for large-scale images, such as histopathological whole slide images (WSIs). Howev…
Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate
Byung Hyun Lee, Sungjin Lim, Seunggyu Lee +2
Remarkable progress in text-to-image diffusion models has brought a major concern about potentially generating images on inappropriate or trademarked concepts. Concept erasing has…
Geometrical Properties of Text Token Embeddings for Strong Semantic Binding in Text-to-Image Generation
Hoigi Seo, Junseo Bang, Haechang Lee +3
Text-to-image (T2I) models often suffer from text-image misalignment in complex scenes involving multiple objects and attributes. Semantic binding has attempted to associate the ge…
Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation
Byung Hyun Lee, Sungjin Lim, Se Young Chun
Fine-tuning based concept erasing has demonstrated promising results in preventing generation of harmful contents from text-to-image diffusion models by removing target concepts wh…
Doubly Perturbed Task Free Continual Learning
Byung Hyun Lee, Min-hwan Oh, Se Young Chun
Task Free online continual learning (TF-CL) is a challenging problem where the model incrementally learns tasks without explicit task information. Although training with entire dat…
Online Continual Learning on Hierarchical Label Expansion
Byung Hyun Lee, Okchul Jung, Jonghyun Choi +1
Continual learning (CL) enables models to adapt to new tasks and environments without forgetting previously learned knowledge. While current CL setups have ignored the relationship…
Empirically Accelerating Scaled Gradient Projection Using Deep Neural Network For Inverse Problems In Image Processing
Byung Hyun Lee, Se Young Chun
Recently, deep neural networks (DNNs) have shown advantages in accelerating optimization algorithms. One approach is to unfold finite number of iterations of conventional optimizat…