Imagen de Portada

MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	He, Haoyu, Renz, Katrin, Cao, Yong, Geiger, Andreas
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization and Distillation
por: von Rad, Jonathan, et al.
Publicado: (2026)

MDPO: Multi-Granularity Direct Preference Optimization for Mathematical Reasoning
por: Lin, Yunze
Publicado: (2025)

Optimal Inference Schedules for Masked Diffusion Models
por: Chen, Sitan, et al.
Publicado: (2025)

Backdooring Masked Diffusion Language Models
por: Cao, Daniel Yiming, et al.
Publicado: (2026)

HDT: Hierarchical Document Transformer
por: He, Haoyu, et al.
Publicado: (2024)

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

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

KLASS: KL-Guided Fast Inference in Masked Diffusion Models
por: Kim, Seo Hyun, et al.
Publicado: (2025)

ILRR: Inference-Time Steering Method for Masked Diffusion Language Models
por: Avrahami, Eden, et al.
Publicado: (2026)

Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion Models
por: Jia, Mengni, et al.
Publicado: (2025)

Training-Free Self-Correction for Multimodal Masked Diffusion Models
por: Ouyang, Yidong, et al.
Publicado: (2026)

Encoder-Decoder Diffusion Language Models for Efficient Training and Inference
por: Arriola, Marianne, et al.
Publicado: (2025)

Improving Text Style Transfer using Masked Diffusion Language Models with Inference-time Scaling
por: Padole, Tejomay Kishor, et al.
Publicado: (2025)

Learning Generation Orders for Masked Discrete Diffusion Models via Variational Inference
por: Fox, David, et al.
Publicado: (2026)

Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training
por: Kim, Jaeyeon, et al.
Publicado: (2026)

Diffusion Generative Modelling for Divide-and-Conquer MCMC
por: Trojan, C., et al.
Publicado: (2024)

Mask Is What DLLM Needs: A Masked Data Training Paradigm for Diffusion LLMs
por: Ma, Linrui, et al.
Publicado: (2026)

Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios?
por: Hallgarten, Marcel, et al.
Publicado: (2024)

Scaling Beyond Masked Diffusion Language Models
por: Sahoo, Subham Sekhar, et al.
Publicado: (2026)

Diffusion-State Policy Optimization for Masked Diffusion Language Models
por: Oba, Daisuke, et al.
Publicado: (2026)

Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models
por: Piskorz, Julianna, et al.
Publicado: (2025)

Faithfulness Measurable Masked Language Models
por: Madsen, Andreas, et al.
Publicado: (2023)

Soft-Masked Diffusion Language Models
por: Hersche, Michael, et al.
Publicado: (2025)

APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference
por: Zhao, Bowen, et al.
Publicado: (2024)

Fast Training of Diffusion Models with Masked Transformers
por: Zheng, Hongkai, et al.
Publicado: (2023)

Understanding Post-Training Structural Changes in Large Language Models
por: He, Xinyu, et al.
Publicado: (2025)

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

Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models
por: Luo, Ziwei, et al.
Publicado: (2026)

Overcoming Selection Bias in Statistical Studies With Amortized Bayesian Inference
por: Arruda, Jonas, et al.
Publicado: (2026)

On the Reasoning Abilities of Masked Diffusion Language Models
por: Svete, Anej, et al.
Publicado: (2025)

Simple and Effective Masked Diffusion Language Models
por: Sahoo, Subham Sekhar, et al.
Publicado: (2024)

PlanT 2.0: Exposing Biases and Structural Flaws in Closed-Loop Driving
por: Gerstenecker, Simon, et al.
Publicado: (2025)

Fail2Drive: Benchmarking Closed-Loop Driving Generalization
por: Gerstenecker, Simon, et al.
Publicado: (2026)

An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models
por: Zhang, Yizhou, et al.
Publicado: (2024)

Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
por: Kim, Jaeyeon, et al.
Publicado: (2025)

Auto-Regressive Masked Diffusion Models
por: Karami, Mahdi, et al.
Publicado: (2026)

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

Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEG
por: Wei, Xinxu, et al.
Publicado: (2024)

On the Trainability of Masked Diffusion Language Models via Blockwise Locality
por: Wang, Yuxiang, et al.
Publicado: (2026)

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