Yuki Mitsufuji

CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow-Map Models

Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment

LLM2Fx-Tools: Tool Calling for Music Post-Production

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

VIRTUE: Visual-Interactive Text-Image Universal Embedder

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

3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation

Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance

TraSCE: Trajectory Steering for Concept Erasure

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

Exposing Vulnerabilities in Latent-Noise Diffusion Watermarks

SoundReactor: Frame-level Online Video-to-Audio Generation

MLLMCLIP: Feature-Level Distillation of MLLM for Robust Vision-Language Representations

Unified Pose Embeddings: Utilizing Euclidean Space for Simplified Topology Alignment

MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval

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

Supervised Contrastive Learning from Weakly-Labeled Audio Segments for Musical Version Matching

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

Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models

Enhancing 3D Reconstruction for Dynamic Scenes

Distillation of Discrete Diffusion through Dimensional Correlations

MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation

HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning

Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models

GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models

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

Orator: LLM-Guided Multi-Shot Speech Video Generation

Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation

A Simple but Strong Baseline for Sounding Video Generation: Effective Adaptation of Audio and Video Diffusion Models for Joint Generation

Bellman Diffusion: Generative Modeling as Learning a Linear Operator in the Distribution Space

VCT: Training Consistency Models with Variational Noise Coupling

FLEXOUNDIT: VARIABLE-LENGTH DIFFUSION TRANSFORMER FOR TEXT-TO-AUDIO GENERATION

Mitigating Embedding Collapse in Diffusion Models for Categorical Data

OpenMU: Your Swiss Army Knife for Music Understanding