Alert button
Picture for Yuki Mitsufuji

Yuki Mitsufuji

Alert button

MR-MT3: Memory Retaining Multi-Track Music Transcription to Mitigate Instrument Leakage

Mar 15, 2024
Hao Hao Tan, Kin Wai Cheuk, Taemin Cho, Wei-Hsiang Liao, Yuki Mitsufuji

Viaarxiv icon

DiffuCOMET: Contextual Commonsense Knowledge Diffusion

Feb 26, 2024
Silin Gao, Mete Ismayilzada, Mengjie Zhao, Hiromi Wakaki, Yuki Mitsufuji, Antoine Bosselut

Viaarxiv icon

MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models

Feb 09, 2024
Yixiao Zhang, Yukara Ikemiya, Gus Xia, Naoki Murata, Marco Martínez, Wei-Hsiang Liao, Yuki Mitsufuji, Simon Dixon

Viaarxiv icon

HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes

Dec 31, 2023
Yuhta Takida, Yukara Ikemiya, Takashi Shibuya, Kazuki Shimada, Woosung Choi, Chieh-Hsin Lai, Naoki Murata, Toshimitsu Uesaka, Kengo Uchida, Wei-Hsiang Liao, Yuki Mitsufuji

Viaarxiv icon

Manifold Preserving Guided Diffusion

Nov 28, 2023
Yutong He, Naoki Murata, Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Dongjun Kim, Wei-Hsiang Liao, Yuki Mitsufuji, J. Zico Kolter, Ruslan Salakhutdinov, Stefano Ermon

Viaarxiv icon

On the Language Encoder of Contrastive Cross-modal Models

Oct 20, 2023
Mengjie Zhao, Junya Ono, Zhi Zhong, Chieh-Hsin Lai, Yuhta Takida, Naoki Murata, Wei-Hsiang Liao, Takashi Shibuya, Hiromi Wakaki, Yuki Mitsufuji

Viaarxiv icon

Towards reporting bias in visual-language datasets: bimodal augmentation by decoupling object-attribute association

Oct 02, 2023
Qiyu Wu, Mengjie Zhao, Yutong He, Lang Huang, Junya Ono, Hiromi Wakaki, Yuki Mitsufuji

Figure 1 for Towards reporting bias in visual-language datasets: bimodal augmentation by decoupling object-attribute association
Figure 2 for Towards reporting bias in visual-language datasets: bimodal augmentation by decoupling object-attribute association
Figure 3 for Towards reporting bias in visual-language datasets: bimodal augmentation by decoupling object-attribute association
Figure 4 for Towards reporting bias in visual-language datasets: bimodal augmentation by decoupling object-attribute association
Viaarxiv icon

Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion

Oct 01, 2023
Dongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yutong He, Yuki Mitsufuji, Stefano Ermon

Figure 1 for Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
Figure 2 for Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
Figure 3 for Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
Figure 4 for Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
Viaarxiv icon

Timbre-Trap: A Low-Resource Framework for Instrument-Agnostic Music Transcription

Sep 27, 2023
Frank Cwitkowitz, Kin Wai Cheuk, Woosung Choi, Marco A. Martínez-Ramírez, Keisuke Toyama, Wei-Hsiang Liao, Yuki Mitsufuji

Viaarxiv icon

Zero- and Few-shot Sound Event Localization and Detection

Sep 17, 2023
Kazuki Shimada, Kengo Uchida, Yuichiro Koyama, Takashi Shibuya, Shusuke Takahashi, Yuki Mitsufuji, Tatsuya Kawahara

Figure 1 for Zero- and Few-shot Sound Event Localization and Detection
Figure 2 for Zero- and Few-shot Sound Event Localization and Detection
Figure 3 for Zero- and Few-shot Sound Event Localization and Detection
Figure 4 for Zero- and Few-shot Sound Event Localization and Detection
Viaarxiv icon