Yuki Mitsufuji

Affiliations

Sony Group Corporation

papers

690

total citations

papers (16)

Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion

ICLR 2024arXiv

333

citations

Manifold Preserving Guided Diffusion

ICLR 2024arXiv

129

citations

STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events

NEURIPS 2023arXiv

citations

MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

CVPR 2025arXiv

citations

MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation

ICLR 2025arXiv

citations

SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation

ICLR 2025arXiv

citations

Enhancing 3D Reconstruction for Dynamic Scenes

NEURIPS 2025arXiv

citations

Classifier-Free Guidance Inside the Attraction Basin May Cause Memorization

CVPR 2025arXiv

citations

HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning

ICLR 2025arXiv

citations

Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric

ICLR 2025arXiv

citations

Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models

ICCV 2025arXiv

citations

TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation

NEURIPS 2025arXiv

citations

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

ICLR 2025arXiv

citations

VinaBench: Benchmark for Faithful and Consistent Visual Narratives

CVPR 2025arXiv

citations

TITAN-Guide: Taming Inference-Time Alignment for Guided Text-to-Video Diffusion Models

ICCV 2025arXiv

citations

Densely Connected Multi-Dilated Convolutional Networks for Dense Prediction Tasks

CVPR 2021

citations