Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hayakawa, Satoshi, Takida, Yuhta, Imaizumi, Masaaki, Wakaki, Hiromi, Mitsufuji, Yuki
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Probability
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact
di: Rojas, Kevin, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

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

Convex-Geometric Error Bounds for Positive-Weight Kernel Quadrature
di: Hayakawa, Satoshi
Pubblicazione: (2026)

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

Minimax Optimal Estimation of Transport-Growth Pairs in Unbalanced Optimal Transport
di: Ponnoprat, Donlapark, et al.
Pubblicazione: (2026)

Dichotomy of Feature Learning and Unlearning: Fast-Slow Analysis on Neural Networks with Stochastic Gradient Descent
di: Imai, Shota, et al.
Pubblicazione: (2026)

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

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

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

The Within-Orbit Adaptive Leapfrog No-U-Turn Sampler
di: Bou-Rabee, Nawaf, et al.
Pubblicazione: (2025)

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

On The Hidden Biases of Flow Matching Samplers
di: Lim, Soon Hoe
Pubblicazione: (2025)

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

Liouville Flow Importance Sampler
di: Tian, Yifeng, et al.
Pubblicazione: (2024)

Mixing of the No-U-Turn Sampler and the Geometry of Gaussian Concentration
di: Bou-Rabee, Nawaf, et al.
Pubblicazione: (2024)

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

Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers
di: Sakai, Mana, et al.
Pubblicazione: (2026)

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

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

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

On Accelerated Mixing of the No-U-turn Sampler
di: Oberdörster, Stefan
Pubblicazione: (2025)

DOS: Dependency-Oriented Sampler for Masked Diffusion Language Models
di: Zhou, Xueyu, et al.
Pubblicazione: (2026)

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

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

TED: Turn Emphasis with Dialogue Feature Attention for Emotion Recognition in Conversation
di: Ono, Junya, et al.
Pubblicazione: (2025)

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

Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking
di: Chao, Chen-Hao, et al.
Pubblicazione: (2025)

MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control
di: Zhu, Yuchen, et al.
Pubblicazione: (2025)

SpecMaskGIT: Masked Generative Modeling of Audio Spectrograms for Efficient Audio Synthesis and Beyond
di: Comunità, Marco, et al.
Pubblicazione: (2024)

Explicit Density Approximation for Neural Implicit Samplers Using a Bernstein-Based Convex Divergence
di: de Frutos, José Manuel, et al.
Pubblicazione: (2025)

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