Takashi Shibuya

Takashi Shibuya on Hugging Face Daily Papers: 6 papers, 0 in the top 3 of their day, 53 upvotes.

1. Spectral Prior for Reducing Exposure Bias in Diffusion Models 6 upvotes, #15 of 2026-07-27
2. Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models 1 upvotes, #25 of 2026-02-27
3. SoundReactor: Frame-level Online Video-to-Audio Generation 2 upvotes, #28 of 2025-10-06
4. Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis 16 upvotes, #5 of 2024-12-23
5. SoundCTM: Uniting Score-based and Consistency Models for Text-to-Sound Generation 7 upvotes, #11 of 2024-05-30
6. Visual Echoes: A Simple Unified Transformer for Audio-Visual Generation 10 upvotes, #8 of 2024-05-24

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.