8 papers
Decoupled Guidance: Disentangling Subject and Context Pathways in Text-to-Image Personalization
Seongmin Kim, Kyucheol Shin, Heesun Jung +2
Text-to-image personalization aims to generate a user-provided subject in novel scenes described by text. However, most existing methods encode subject identity (fidelity) and cont…
Learning to Recover Task Experts from a Multi-Task Merged Model
Jinwook Jung, Taegyu Kim, Kumju Jo +1
Multi-task model merging aims to consolidate several task-specific experts into a unified model, yet static merging consistently suffers from parameter interference. While dynamic…
Training-free Task Classification for Multi-Task Model Merging
Jungyong Son, Jinwook Jung, Sungyong Baik
Ever since the advent of foundation models and the pre-training-finetuning paradigm, there have been numerous efforts to merge multiple task-specific experts into a single multi-ta…
Bilinear Coordinate Alignment for Training-Free Task-Vector Transfer
Jungyong Son, Jinwook Jung, Minhee Park +1
Fine-tuning large-scale pre-trained models is a recent prevalent paradigm for adapting general representations to specialized tasks. However, when a new version of a pre-trained mo…
Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization
Jungwook Seo, Minjeong Kim, Younkwan Lee +2
Detecting subtle visual anomalies in images remains challenging, particularly when only normal samples are available a priori. Such unsupervised anomaly detection is typically solv…
SeeDiff: Off-the-Shelf Seeded Mask Generation from Diffusion Models
Joon Hyun Park, Kumju Jo, Sungyong Baik
Entrusted with the goal of pixel-level object classification, the semantic segmentation networks entail the laborious preparation of pixel-level annotation masks. To obtain pixel-l…