Shusuke Takahashi

VIRTUE: Visual-Interactive Text-Image Universal Embedder

Unified Pose Embeddings: Utilizing Euclidean Space for Simplified Topology Alignment

Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models

FLEXOUNDIT: VARIABLE-LENGTH DIFFUSION TRANSFORMER FOR TEXT-TO-AUDIO GENERATION

OpenMU: Your Swiss Army Knife for Music Understanding