Imagen de Portada

DualDiffusion: A Speculative Decoding Strategy for Masked Diffusion Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Goyal, Satyam, Patel, Kushal, Mittal, Tanush, Laxman, Arjun
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion
por: Christopher, Jacob K, et al.
Publicado: (2024)

Stopping Computation for Converged Tokens in Masked Diffusion-LM Decoding
por: Oba, Daisuke, et al.
Publicado: (2026)

Decoding Speculative Decoding
por: Yan, Minghao, et al.
Publicado: (2024)

Optimizing Decoding Paths in Masked Diffusion Models by Quantifying Uncertainty
por: Chen, Ziyu, et al.
Publicado: (2025)

Spiffy: Multiplying Diffusion LLM Acceleration via Lossless Speculative Decoding
por: Agrawal, Sudhanshu, et al.
Publicado: (2025)

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

Enhancing Authorship Attribution through Embedding Fusion: A Novel Approach with Masked and Encoder-Decoder Language Models
por: Kaushik, Arjun Ramesh, et al.
Publicado: (2024)

Benchmarking the Energy Savings with Speculative Decoding Strategies
por: Dutta, Rohit, et al.
Publicado: (2026)

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

Speculative Decoding Across Languages
por: Paudel, Nirajan, et al.
Publicado: (2026)

Variational Masked Diffusion Models
por: Zhang, Yichi, et al.
Publicado: (2025)

Stability-Weighted Decoding for Diffusion Language Models
por: Wu, Yue, et al.
Publicado: (2026)

Improving Sparse Memory Finetuning
por: Goyal, Satyam, et al.
Publicado: (2026)

Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning
por: Gupta, Prakhar, et al.
Publicado: (2026)

Scaling Speculative Decoding with Lookahead Reasoning
por: Fu, Yichao, et al.
Publicado: (2025)

View From Above: A Framework for Evaluating Distribution Shifts in Model Behavior
por: Chopra, Tanush, et al.
Publicado: (2024)

Recurrent Drafter for Fast Speculative Decoding in Large Language Models
por: Cheng, Yunfei, et al.
Publicado: (2024)

Online Speculative Decoding
por: Liu, Xiaoxuan, et al.
Publicado: (2023)

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

Masked Diffusion Models as Energy Minimization
por: Chen, Sitong, et al.
Publicado: (2025)

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

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

Out-of-Vocabulary Sampling Boosts Speculative Decoding
por: Timor, Nadav, et al.
Publicado: (2025)

On Speculative Decoding for Multimodal Large Language Models
por: Gagrani, Mukul, et al.
Publicado: (2024)

Scaling up Masked Diffusion Models on Text
por: Nie, Shen, et al.
Publicado: (2024)

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

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

Mixture of Attentions For Speculative Decoding
por: Zimmer, Matthieu, et al.
Publicado: (2024)

Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding
por: Sun, Shuoyang, et al.
Publicado: (2026)

ParallelSpec: Parallel Drafter for Efficient Speculative Decoding
por: Xiao, Zilin, et al.
Publicado: (2024)

VOCABTRIM: Vocabulary Pruning for Efficient Speculative Decoding in LLMs
por: Goel, Raghavv, et al.
Publicado: (2025)

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
por: Bachmann, Gregor, et al.
Publicado: (2025)

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding
por: Hoshino, Yuichiro, et al.
Publicado: (2025)

Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding
por: Guo, Gabe, et al.
Publicado: (2025)

Confidence-Modulated Speculative Decoding for Large Language Models
por: Sen, Jaydip, et al.
Publicado: (2025)

Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
por: Sedykh, Ivan, et al.
Publicado: (2026)

Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing
por: Azangulov, Iskander, et al.
Publicado: (2025)

Tree Reward-Aligned Search for TReASURe in Masked Diffusion Language Models
por: Yu, Zichao, et al.
Publicado: (2025)

TapOut: A Bandit-Based Approach to Dynamic Speculative Decoding
por: Sridhar, Aditya, et al.
Publicado: (2025)

A Theoretical Perspective for Speculative Decoding Algorithm
por: Yin, Ming, et al.
Publicado: (2024)