Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Rojas, Kevin, He, Ye, Lai, Chieh-Hsin, Takida, Yuhta, Mitsufuji, Yuki, Tao, Molei
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Denoising Multi-Beta VAE: Representation Learning for Disentanglement and Generation
por: Uppal, Anshuk, et al.
Publicado: (2025)

$\textit{Jump Your Steps}$: Optimizing Sampling Schedule of Discrete Diffusion Models
por: Park, Yong-Hyun, et al.
Publicado: (2024)

Understanding and Accelerating the Training of Masked Diffusion Language Models
por: Hong, Chunsan, et al.
Publicado: (2026)

VCT: Training Consistency Models with Variational Noise Coupling
por: Silvestri, Gianluigi, et al.
Publicado: (2025)

Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment
por: Nguyen, Bac, et al.
Publicado: (2026)

Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion
por: Nguyen, Bac, et al.
Publicado: (2024)

A Unified View of Score-Based and Drifting Models
por: Lai, Chieh-Hsin, et al.
Publicado: (2026)

Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion
por: Hayakawa, Satoshi, et al.
Publicado: (2025)

Classifier-Free Guidance inside the Attraction Basin May Cause Memorization
por: Jain, Anubhav, et al.
Publicado: (2024)

What Exactly Does Guidance Do in Masked Discrete Diffusion Models
por: Ye, He, et al.
Publicado: (2025)

Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric
por: Uesaka, Toshimitsu, et al.
Publicado: (2024)

BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network
por: Shibuya, Takashi, et al.
Publicado: (2023)

G2D2: Gradient-Guided Discrete Diffusion for Inverse Problem Solving
por: Murata, Naoki, et al.
Publicado: (2024)

GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning
por: Murata, Naoki, et al.
Publicado: (2026)

PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
por: Kim, Dongjun, et al.
Publicado: (2024)

Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models
por: Tao, Zerui, et al.
Publicado: (2025)

SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer
por: Takida, Yuhta, et al.
Publicado: (2023)

SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation
por: Saito, Koichi, et al.
Publicado: (2024)

Distillation of Discrete Diffusion through Dimensional Correlations
por: Hayakawa, Satoshi, et al.
Publicado: (2024)

Efficiency without Compromise: CLIP-aided Text-to-Image GANs with Increased Diversity
por: Kobayashi, Yuya, et al.
Publicado: (2025)

Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
por: Kim, Dongjun, et al.
Publicado: (2023)

Noise Scheduling as Information-Guided Allocation in Diffusion Training
por: Raya, Gabriel, et al.
Publicado: (2026)

Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity
por: Yoshida, Naoki, et al.
Publicado: (2025)

Distill, Forget, Repeat: A Framework for Continual Unlearning in Text-to-Image Diffusion Models
por: George, Naveen, et al.
Publicado: (2025)

SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator
por: Takida, Yuhta, et al.
Publicado: (2025)

MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training
por: Uchida, Kengo, et al.
Publicado: (2024)

Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion
por: He, Ye, et al.
Publicado: (2024)

PAVAS: Physics-Aware Video-to-Audio Synthesis
por: Hyun-Bin, Oh, et al.
Publicado: (2025)

The Principles of Diffusion Models
por: Lai, Chieh-Hsin, et al.
Publicado: (2025)

Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution
por: Park, Yonghyun, et al.
Publicado: (2025)

HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes
por: Takida, Yuhta, et al.
Publicado: (2023)

CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow Map Models
por: Hu, Zheyuan, et al.
Publicado: (2025)

TraSCE: Trajectory Steering for Concept Erasure
por: Jain, Anubhav, et al.
Publicado: (2024)

Dimming GRS 1915+105 observed with NICER and Insight--HXMT
por: Zhou, M., et al.
Publicado: (2025)

Bellman Diffusion: Generative Modeling as Learning a Linear Operator in the Distribution Space
por: Li, Yangming, et al.
Publicado: (2024)

Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image
por: Jain, Anubhav, et al.
Publicado: (2025)

Dimming Starlight with Dark Compact Objects
por: Bramante, Joseph, et al.
Publicado: (2024)

Through a Crystal Ball -- Dimly
Publicado: (1972)

DisMix: Disentangling Mixtures of Musical Instruments for Source-level Pitch and Timbre Manipulation
por: Luo, Yin-Jyun, et al.
Publicado: (2024)

Doppler Dimming and Brightening Effects in Solar Prominences
por: Peat, Aaron W., et al.
Publicado: (2024)