Yuhta Takida

Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment

SONA: Learning Conditional, Unconditional, and Matching-Aware Discriminator

Concept-TRAK: Understanding how diffusion models learn concepts through concept attribution

Theoretical refinement of CLIP by utilizing linear structure of optimal similarity

Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact

TraSCE: Trajectory Steering for Concept Erasure

Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion

Exposing Vulnerabilities in Latent-Noise Diffusion Watermarks

Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric

SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation

Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models

Distillation of Discrete Diffusion through Dimensional Correlations

G2D2: Gradient-guided Discrete Diffusion for image inverse problem solving

VCT: Training Consistency Models with Variational Noise Coupling

Mitigating Embedding Collapse in Diffusion Models for Categorical Data