Yuhta Takida
16 papers · 2022–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Cross-Pollinator (12) πΊοΈ Taxonomy Completionist (30) π Interdisciplinary Bridge π§ Keyword Pioneer π Renaissance Researcher (6)
π
Conference Polyglot
(7)
π€
Dynamic Duo
(16)
π
Century Club
(16)
β‘
Prolific Year
(7)
ποΈ
Keyword Collector
(53)
Conferences
ICLR (6)
ICML (5)
ACL (1)
CVPR (1)
ICCV (1)
INTERSPEECH (1)
NIPS (1)
Top co-authors
Research topics
Keywords
diffusion model
(5)
generative model
(3)
image generation
(2)
variational inference
(1)
model merging
(1)
model adaptation
(1)
knowledge distillation
(1)
speech enhancement
(1)
tensor decomposition
(1)
vector quantization
(1)
likelihood estimation
(1)
score matching
(1)
gibbs sampler
(1)
inverse problem
(1)
posterior sampling
(1)
image restoration
(1)
variational autoencoder
(1)
cross-modal alignment
(1)
parameter-efficient fine-tuning
(1)
contrastive learning
(1)
Papers
Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric
ICLR 2025
SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation
ICLR 2025
Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models
ICLR 2025
VCT: Training Consistency Models with Variational Noise Coupling
ICML 2025
Distillation of Discrete Diffusion through Dimensional Correlations
ICML 2025
Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models
ICCV 2025
Classifier-Free Guidance Inside the Attraction Basin May Cause Memorization
CVPR 2025
PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
NIPS 2024
On the Language Encoder of Contrastive Cross-modal Models
ACL 2024
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
ICLR 2024
Manifold Preserving Guided Diffusion
ICLR 2024
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer
ICLR 2024
GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration
ICML 2023
FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation
ICML 2023
Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancement
INTERSPEECH 2023
SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization
ICML 2022