Cover Image

Understanding and Accelerating the Training of Masked Diffusion Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hong, Chunsan, Lee, Sanghyun, Lai, Chieh-Hsin, Hayakawa, Satoshi, Takida, Yuhta, Mitsufuji, Yuki, Kim, Seungryong, Ye, Jong Chul
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

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

Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies
by: Hong, Chunsan, et al.
Published: (2025)

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

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

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

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

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

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

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

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

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

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

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

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

Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models
by: Kim, Jaemin, et al.
Published: (2026)

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

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

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

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

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

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

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

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

A Survey on Diffusion Models for Inverse Problems
by: Daras, Giannis, et al.
Published: (2024)

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

MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval
by: Wu, Qiyu, et al.
Published: (2025)

Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
by: Lee, Sanghyun, et al.
Published: (2025)

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

LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation
by: Lee, Suhyeon, et al.
Published: (2023)

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

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

Reconsidering Positional Supervision in Masked Diffusion Language Model Training
by: Ye, Mengyu, et al.
Published: (2026)

Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models
by: Gröpl, Marcel, et al.
Published: (2026)

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