Takashi Shibuya

5

Papers

1

Total Citations

2

Affiliations

Affiliations

SonyUniversity of Tsukuba

Papers (5)

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

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

Classifier-Free Guidance Inside the Attraction Basin May Cause Memorization

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

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