Yuhta Takida

76 papers A* 13A 1B 2Misc 5Journal 49Unranked 6
YearRankTypeTitle / Venue / Authors
2026 J jnl
A Unified View of Drifting and Score-Based Models.
CoRR
Chieh-Hsin Lai, Bac Nguyen, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon, Molei Tao
2026 J jnl
Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion.
Trans. Mach. Learn. Res.
Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji
2026 J jnl
GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning.
CoRR
Naoki Murata, Yuhta Takida, Chieh-Hsin Lai, Toshimitsu Uesaka, Bac Nguyen, Stefano Ermon, Yuki Mitsufuji
2026 J jnl
Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment.
CoRR
Bac Nguyen, Yuhta Takida, Naoki Murata, Chieh-Hsin Lai, Toshimitsu Uesaka, Stefano Ermon, Yuki Mitsufuji
2026 J jnl
Information-Guided Noise Allocation for Efficient Diffusion Training.
CoRR
Gabriel Raya, Bac Nguyen, Georgios Batzolis, Yuhta Takida, Dejan Stancevic, Naoki Murata, Chieh-Hsin Lai, Yuki Mitsufuji, Luca Ambrogioni
2025 A* conf
Classifier-Free Guidance Inside the Attraction Basin May Cause Memorization.
CVPR
Anubhav Jain, Yuya Kobayashi, Takashi Shibuya, Yuhta Takida, Nasir D. Memon, Julian Togelius, Yuki Mitsufuji
2025 J jnl
Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution.
CoRR
Yong-Hyun Park, Chieh-Hsin Lai, Satoshi Hayakawa, Yuhta Takida, Naoki Murata, Wei-Hsiang Liao, Woosung Choi, Kin Wai Cheuk, Junghyun Koo, Yuki Mitsufuji
2025 J jnl
Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion.
CoRR
Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji
2025 J jnl
Denoising Multi-Beta VAE: Representation Learning for Disentanglement and Generation.
CoRR
Anshuk Uppal, Yuhta Takida, Chieh-Hsin Lai, Yuki Mitsufuji
2025 J jnl
Distill, Forget, Repeat: A Framework for Continual Unlearning in Text-to-Image Diffusion Models.
CoRR
Naveen George, Naoki Murata, Yuhta Takida, Konda Reddy Mopuri, Yuki Mitsufuji
2025 A* conf
Distillation of Discrete Diffusion through Dimensional Correlations.
ICML
Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji
2025 B conf
Efficiency without Compromise: CLIP-aided Text-to-Image GANs with Increased Diversity.
IJCNN
Yuya Kobayashi, Yuhta Takida, Takashi Shibuya, Yuki Mitsufuji
2025 J jnl
Efficiency without Compromise: CLIP-aided Text-to-Image GANs with Increased Diversity.
CoRR
Yuya Kobayashi, Yuhta Takida, Takashi Shibuya, Yuki Mitsufuji
2025 J jnl
Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image.
CoRR
Anubhav Jain, Yuya Kobayashi, Naoki Murata, Yuhta Takida, Takashi Shibuya, Yuki Mitsufuji, Niv Cohen, Nasir D. Memon, Julian Togelius
2025 J jnl
G2D2: Gradient-Guided Discrete Diffusion for Inverse Problem Solving.
Trans. Mach. Learn. Res.
Naoki Murata, Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Bac Nguyen, Stefano Ermon, Yuki Mitsufuji
2025 B conf
Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion.
IJCNN
Bac Nguyen, Chieh-Hsin Lai, Yuhta Takida, Naoki Murata, Toshimitsu Uesaka, Stefano Ermon, Yuki Mitsufuji
2025 A* conf
Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models.
ICLR
Yong-Hyun Park, Chieh-Hsin Lai, Satoshi Hayakawa, Yuhta Takida, Yuki Mitsufuji
2025 J jnl
Large-Scale Training Data Attribution for Music Generative Models via Unlearning.
CoRR
Woosung Choi, Junghyun Koo, Kin Wai Cheuk, Joan Serrà, Marco A. Martínez Ramírez, Yukara Ikemiya, Naoki Murata, Yuhta Takida, Wei-Hsiang Liao, Yuki Mitsufuji
2025 — conf
MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training.
CVPR Workshops
Kengo Uchida, Takashi Shibuya, Yuhta Takida, Naoki Murata, Julian Tanke, Shusuke Takahashi, Yuki Mitsufuji
2025 J jnl
Music Foundation Model as Generic Booster for Music Downstream Tasks.
Trans. Mach. Learn. Res.
Wei-Hsiang Liao, Yuhta Takida, Yukara Ikemiya, Zhi Zhong, Chieh-Hsin Lai, Giorgio Fabbro, Kazuki Shimada, Keisuke Toyama, Kin Wai Cheuk, Marco A. Martínez Ramírez, Shusuke Takahashi, Stefan Uhlich, Taketo Akama, Woosung Choi, Yuichiro Koyama, Yuki Mitsufuji
2025 J jnl
PAVAS: Physics-Aware Video-to-Audio Synthesis.
CoRR
Oh Hyun-Bin, Yuhta Takida, Toshimitsu Uesaka, Tae-Hyun Oh, Yuki Mitsufuji
2025 J jnl
SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator.
CoRR
Yuhta Takida, Satoshi Hayakawa, Takashi Shibuya, Masaaki Imaizumi, Naoki Murata, Bac Nguyen, Toshimitsu Uesaka, Chieh-Hsin Lai, Yuki Mitsufuji
2025 A* conf
SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation.
ICLR
Koichi Saito, Dongjun Kim, Takashi Shibuya, Chieh-Hsin Lai, Zhi Zhong, Yuhta Takida, Yuki Mitsufuji
2025 J jnl
Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity.
CoRR
Naoki Yoshida, Satoshi Hayakawa, Yuhta Takida, Toshimitsu Uesaka, Hiromi Wakaki, Yuki Mitsufuji
2025 J jnl
Theory-Informed Improvements to Classifier-Free Guidance for Discrete Diffusion Models.
CoRR
Kevin Rojas, Ye He, Chieh-Hsin Lai, Yuhta Takida, Yuki Mitsufuji, Molei Tao
2025 J jnl
Training Consistency Models with Variational Noise Coupling.
CoRR
Gianluigi Silvestri, Luca Ambrogioni, Chieh-Hsin Lai, Yuhta Takida, Yuki Mitsufuji
2025 J jnl
Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models.
CoRR
Zerui Tao, Yuhta Takida, Naoki Murata, Qibin Zhao, Yuki Mitsufuji
2025 A* conf
VCT: Training Consistency Models with Variational Noise Coupling.
ICML
Gianluigi Silvestri, Luca Ambrogioni, Chieh-Hsin Lai, Yuhta Takida, Yuki Mitsufuji
2025 Misc conf
Variable Bitrate Residual Vector Quantization for Audio Coding.
ICASSP
Yunkee Chae, Woosung Choi, Yuhta Takida, Junghyun Koo, Yukara Ikemiya, Zhi Zhong, Kin Wai Cheuk, Marco A. Martínez Ramírez, Kyogu Lee, Wei-Hsiang Liao, Yuki Mitsufuji
2025 A* conf
Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric.
ICLR
Toshimitsu Uesaka, Taiji Suzuki, Yuhta Takida, Chieh-Hsin Lai, Naoki Murata, Yuki Mitsufuji
2024 Misc conf
BIGVSAN: Enhancing Gan-Based Neural Vocoders with Slicing Adversarial Network.
ICASSP
Takashi Shibuya, Yuhta Takida, Yuki Mitsufuji
2024 J jnl
Classifier-Free Guidance inside the Attraction Basin May Cause Memorization.
CoRR
Anubhav Jain, Yuya Kobayashi, Takashi Shibuya, Yuhta Takida, Nasir D. Memon, Julian Togelius, Yuki Mitsufuji
2024 A* conf
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion.
ICLR
Dongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yutong He, Yuki Mitsufuji, Stefano Ermon
2024 J jnl
DisMix: Disentangling Mixtures of Musical Instruments for Source-level Pitch and Timbre Manipulation.
CoRR
Yin-Jyun Luo, Kin Wai Cheuk, Woosung Choi, Toshimitsu Uesaka, Keisuke Toyama, Koichi Saito, Chieh-Hsin Lai, Yuhta Takida, Wei-Hsiang Liao, Simon Dixon, Yuki Mitsufuji
2024 J jnl
Distillation of Discrete Diffusion through Dimensional Correlations.
CoRR
Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, Yuki Mitsufuji
2024 J jnl
G2D2: Gradient-guided Discrete Diffusion for image inverse problem solving.
CoRR
Naoki Murata, Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Bac Nguyen, Stefano Ermon, Yuki Mitsufuji
2024 J jnl
HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes.
CoRR
Yuhta Takida, Yukara Ikemiya, Takashi Shibuya, Kazuki Shimada, Woosung Choi, Chieh-Hsin Lai, Naoki Murata, Toshimitsu Uesaka, Kengo Uchida, Wei-Hsiang Liao, Yuki Mitsufuji
2024 J jnl
HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes.
Trans. Mach. Learn. Res.
Yuhta Takida, Yukara Ikemiya, Takashi Shibuya, Kazuki Shimada, Woosung Choi, Chieh-Hsin Lai, Naoki Murata, Toshimitsu Uesaka, Kengo Uchida, Wei-Hsiang Liao, Yuki Mitsufuji
2024 A* conf
Manifold Preserving Guided Diffusion.
ICLR
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
2024 J jnl
Mitigating Embedding Collapse in Diffusion Models for Categorical Data.
CoRR
Bac Nguyen, Chieh-Hsin Lai, Yuhta Takida, Naoki Murata, Toshimitsu Uesaka, Stefano Ermon, Yuki Mitsufuji
2024 J jnl
MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training.
CoRR
Kengo Uchida, Takashi Shibuya, Yuhta Takida, Naoki Murata, Shusuke Takahashi, Yuki Mitsufuji
2024 J jnl
Music Foundation Model as Generic Booster for Music Downstream Tasks.
CoRR
Wei-Hsiang Liao, Yuhta Takida, Yukara Ikemiya, Zhi Zhong, Chieh-Hsin Lai, Giorgio Fabbro, Kazuki Shimada, Keisuke Toyama, Kin Wai Cheuk, Marco A. Martínez Ramírez, Shusuke Takahashi, Stefan Uhlich, Taketo Akama, Woosung Choi, Yuichiro Koyama, Yuki Mitsufuji
2024 — conf
On the Language Encoder of Contrastive Cross-modal Models.
ACL (Findings)
Mengjie Zhao, Junya Ono, Zhi Zhong, Chieh-Hsin Lai, Yuhta Takida, Naoki Murata, Wei-Hsiang Liao, Takashi Shibuya, Hiromi Wakaki, Yuki Mitsufuji
2024 A* conf
PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher.
NeurIPS
Dongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Yuhta Takida, Naoki Murata, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon
2024 J jnl
PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher.
CoRR
Dongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Yuhta Takida, Naoki Murata, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon
2024 A* conf
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer.
ICLR
Yuhta Takida, Masaaki Imaizumi, Takashi Shibuya, Chieh-Hsin Lai, Toshimitsu Uesaka, Naoki Murata, Yuki Mitsufuji
2024 J jnl
SoundCTM: Uniting Score-based and Consistency Models for Text-to-Sound Generation.
CoRR
Koichi Saito, Dongjun Kim, Takashi Shibuya, Chieh-Hsin Lai, Zhi Zhong, Yuhta Takida, Yuki Mitsufuji
2024 J jnl
TraSCE: Trajectory Steering for Concept Erasure.
CoRR
Anubhav Jain, Yuya Kobayashi, Takashi Shibuya, Yuhta Takida, Nasir D. Memon, Julian Togelius, Yuki Mitsufuji
2024 J jnl
Understanding Multimodal Contrastive Learning Through Pointwise Mutual Information.
CoRR
Toshimitsu Uesaka, Taiji Suzuki, Yuhta Takida, Chieh-Hsin Lai, Naoki Murata, Yuki Mitsufuji
2024 J jnl
VRVQ: Variable Bitrate Residual Vector Quantization for Audio Compression.
CoRR
Yunkee Chae, Woosung Choi, Yuhta Takida, Junghyun Koo, Yukara Ikemiya, Zhi Zhong, Kin Wai Cheuk, Marco A. Martínez Ramírez, Kyogu Lee, Wei-Hsiang Liao, Yuki Mitsufuji
2023 J jnl
Adversarially Slicing Generative Networks: Discriminator Slices Feature for One-Dimensional Optimal Transport.
CoRR
Yuhta Takida, Masaaki Imaizumi, Chieh-Hsin Lai, Toshimitsu Uesaka, Naoki Murata, Yuki Mitsufuji
2023 — conf
Automatic Piano Transcription With Hierarchical Frequency-Time Transformer.
ISMIR
Keisuke Toyama, Taketo Akama, Yukara Ikemiya, Yuhta Takida, Wei-Hsiang Liao, Yuki Mitsufuji
2023 J jnl
Automatic Piano Transcription with Hierarchical Frequency-Time Transformer.
CoRR
Keisuke Toyama, Taketo Akama, Yukara Ikemiya, Yuhta Takida, Wei-Hsiang Liao, Yuki Mitsufuji
2023 J jnl
BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network.
CoRR
Takashi Shibuya, Yuhta Takida, Yuki Mitsufuji
2023 J jnl
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion.
CoRR
Dongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yutong He, Yuki Mitsufuji, Stefano Ermon
2023 A conf
Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancement.
INTERSPEECH
Ryosuke Sawata, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Takashi Shibuya, Shusuke Takahashi, Yuki Mitsufuji
2023 A* conf
FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation.
ICML
Chieh-Hsin Lai, Yuhta Takida, Naoki Murata, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon
2023 A* conf
GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration.
ICML
Naoki Murata, Koichi Saito, Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon
2023 J jnl
GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration.
CoRR
Naoki Murata, Koichi Saito, Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon
2023 J jnl
Manifold Preserving Guided Diffusion.
CoRR
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
2023 J jnl
On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularization.
CoRR
Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Naoki Murata, Yuki Mitsufuji, Stefano Ermon
2023 J jnl
On the Language Encoder of Contrastive Cross-modal Models.
CoRR
Mengjie Zhao, Junya Ono, Zhi Zhong, Chieh-Hsin Lai, Yuhta Takida, Naoki Murata, Wei-Hsiang Liao, Takashi Shibuya, Hiromi Wakaki, Yuki Mitsufuji
2023 Misc conf
Unsupervised Vocal Dereverberation with Diffusion-Based Generative Models.
ICASSP
Koichi Saito, Naoki Murata, Toshimitsu Uesaka, Chieh-Hsin Lai, Yuhta Takida, Takao Fukui, Yuki Mitsufuji
2022 J jnl
A Versatile Diffusion-based Generative Refiner for Speech Enhancement.
CoRR
Ryosuke Sawata, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Takashi Shibuya, Shusuke Takahashi, Yuki Mitsufuji
2022 J jnl
Preventing oversmoothing in VAE via generalized variance parameterization.
Neurocomputing
Yuhta Takida, Wei-Hsiang Liao, Chieh-Hsin Lai, Toshimitsu Uesaka, Shusuke Takahashi, Yuki Mitsufuji
2022 J jnl
Regularizing Score-based Models with Score Fokker-Planck Equations.
CoRR
Chieh-Hsin Lai, Yuhta Takida, Naoki Murata, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon
2022 A* conf
SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization.
ICML
Yuhta Takida, Takashi Shibuya, Wei-Hsiang Liao, Chieh-Hsin Lai, Junki Ohmura, Toshimitsu Uesaka, Naoki Murata, Shusuke Takahashi, Toshiyuki Kumakura, Yuki Mitsufuji
2022 J jnl
SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization.
CoRR
Yuhta Takida, Takashi Shibuya, Wei-Hsiang Liao, Chieh-Hsin Lai, Junki Ohmura, Toshimitsu Uesaka, Naoki Murata, Shusuke Takahashi, Toshiyuki Kumakura, Yuki Mitsufuji
2022 J jnl
Unsupervised vocal dereverberation with diffusion-based generative models.
CoRR
Koichi Saito, Naoki Murata, Toshimitsu Uesaka, Chieh-Hsin Lai, Yuhta Takida, Takao Fukui, Yuki Mitsufuji
2021 — conf
Fast Convergent Method for Active Noise Control Over Spatial Region with Causal Constraint.
WASPAA
Naoki Murata, Yuhta Takida, Tetsu Magariyachi
2021 J jnl
Preventing Posterior Collapse Induced by Oversmoothing in Gaussian VAE.
CoRR
Yuhta Takida, Wei-Hsiang Liao, Toshimitsu Uesaka, Shusuke Takahashi, Yuki Mitsufuji
2020 Misc conf
Array-Geometry-Aware Spatial Active Noise Control Based on Direction-of-Arrival Weighting.
ICASSP
Yu Maeno, Yuhta Takida, Naoki Murata, Yuki Mitsufuji
2020 J jnl
Reciprocity gap functional in spherical harmonic domain for gridless sound field decomposition.
Signal Process.
Yuhta Takida, Shoichi Koyama, Natsuki Ueno, Hiroshi Saruwatari
2019 Misc conf
Robust Gridless Sound Field Decomposition Based on Structured Reciprocity Gap Functional in Spherical Harmonic Domain.
ICASSP
Yuhta Takida, Shoichi Koyama, Natsuki Ueno, Hiroshi Saruwatari
2018 — conf
Exterior and Interior Sound Field Separation Using Convex Optimization: Comparison of Signal Models.
EUSIPCO
Yuhta Takida, Shoichi Koyama, Hiroshi Saruwatari
2018 — conf
Gridless Sound Field Decomposition Based on Reciprocity Gap Functional in Spherical Harmonic Domain.
SAM
Yuhta Takida, Shoichi Koyama, Natsuki Ueno, Hiroshi Saruwatari