| Consistency trajectory models: Learning probability flow ode trajectory of diffusion D Kim, CH Lai, WH Liao, N Murata, Y Takida, T Uesaka, Y He, Y Mitsufuji, ... ICLR 2024, 2023 | 120 | 2023 |
| Robust subspace recovery layer for unsupervised anomaly detection CH Lai, D Zou, G Lerman ICLR 2020, 2019 | 82 | 2019 |
| Sq-vae: Variational bayes on discrete representation with self-annealed stochastic quantization Y Takida, T Shibuya, WH Liao, CH Lai, J Ohmura, T Uesaka, N Murata, ... ICML 2022, 2022 | 67 | 2022 |
| Gibbsddrm: A partially collapsed gibbs sampler for solving blind inverse problems with denoising diffusion restoration N Murata, K Saito, CH Lai, Y Takida, T Uesaka, Y Mitsufuji, S Ermon ICML 2023, 25501-25522, 2023 | 44 | 2023 |
| FP-Diffusion: Improving score-based diffusion models by enforcing the underlying score fokker-planck equation CH Lai, Y Takida, N Murata, T Uesaka, Y Mitsufuji, S Ermon ICML 2023, 18365-18398, 2023 | 41* | 2023 |
| Manifold preserving guided diffusion Y He, N Murata, CH Lai, Y Takida, T Uesaka, D Kim, WH Liao, Y Mitsufuji, ... ICLR 2024, 2023 | 35 | 2023 |
| Unsupervised vocal dereverberation with diffusion-based generative models K Saito, N Murata, T Uesaka, CH Lai, Y Takida, T Fukui, Y Mitsufuji ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 24 | 2023 |
| Inverse problems, deep learning, and symmetry breaking K Tayal, CH Lai, V Kumar, J Sun ICLR 2021, 2020 | 22 | 2020 |
| The Sound Demixing Challenge 2023$\unicode {x2013} $ Music Demixing Track G Fabbro, S Uhlich, CH Lai, W Choi, M Martínez-Ramírez, W Liao, ... Transactions of the International Society for Music Information Retrieval 2024, 2023 | 21 | 2023 |
| Robust variational autoencoding with wasserstein penalty for novelty detection CH Lai, D Zou, G Lerman International Conference on Artificial Intelligence and Statistics, 2023 | 15* | 2023 |
| Preventing oversmoothing in VAE via generalized variance parameterization Y Takida, WH Liao, CH Lai, T Uesaka, S Takahashi, Y Mitsufuji Neurocomputing 509, 137-156, 2022 | 11 | 2022 |
| SAN: Inducing metrizability of GAN with discriminative normalized linear layer Y Takida, M Imaizumi, T Shibuya, CH Lai, T Uesaka, N Murata, Y Mitsufuji ICML 2023, 2023 | 10 | 2023 |
| GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping J Seo, K Fukuda, T Shibuya, T Narihira, N Murata, S Hu, CH Lai, S Kim, ... NeurIPS 2024, 2024 | 9 | 2024 |
| Vrdmg: Vocal restoration via diffusion posterior sampling with multiple guidance C Hernandez-Olivan, K Saito, N Murata, CH Lai, MA Martínez-Ramirez, ... ICASSP 2024, 596-600, 2024 | 9 | 2024 |
| Unlocking inverse problems using deep learning: Breaking symmetries in phase retrieval K Tayal, CH Lai, R Manekar, Z Zhuang, V Kumar, J Sun NeurIPS 2020 Workshop on Deep Learning and Inverse Problems, 2020 | 9 | 2020 |
| A survey on diffusion models for inverse problems G Daras, H Chung, CH Lai, Y Mitsufuji, JC Ye, P Milanfar, AG Dimakis, ... arXiv preprint arXiv:2410.00083, 2024 | 8 | 2024 |
| HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes Y Takida, Y Ikemiya, T Shibuya, K Shimada, W Choi, CH Lai, N Murata, ... TMLR 2024, 2023 | 8 | 2023 |
| On the equivalence of consistency-type models: Consistency models, consistent diffusion models, and fokker-planck regularization CH Lai, Y Takida, T Uesaka, N Murata, Y Mitsufuji, S Ermon ICML 2023 Workshop, 2023 | 8 | 2023 |
| PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher D Kim, CH Lai, WH Liao, Y Takida, N Murata, T Uesaka, Y Mitsufuji, ... NeurIPS 2024, 2024 | 7 | 2024 |
| SoundCTM: Uniting Score-based and Consistency Models for Text-to-Sound Generation K Saito, D Kim, T Shibuya, CH Lai, Z Zhong, Y Takida, Y Mitsufuji ICLR 2025, 2024 | 4 | 2024 |
Yuki MitsufujiDistinguished Engineer, Sony; Specially Appointed Associate Professor, Tokyo Institute of TechnologyVerified email at sony.com