Copertina

Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic Perspective

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Shaorong, Yu, Longxuan, Brekelmans, Rob, Tang, Luhan, Asif, Salman, Steeg, Greg Ver
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Is Your Diffusion Sampler Actually Correct? A Sampler-Centric Evaluation of Discrete Diffusion Language Models
di: Tang, Luhan, et al.
Pubblicazione: (2026)

Measurement-Aligned Sampling for Inverse Problem
di: Zhang, Shaorong, et al.
Pubblicazione: (2025)

Local MAP Sampling for Diffusion Models
di: Zhang, Shaorong, et al.
Pubblicazione: (2025)

Exploring the Design Space of Diffusion Bridge Models
di: Zhang, Shaorong, et al.
Pubblicazione: (2024)

Discrete Stochastic Localization for Non-autoregressive Generation
di: Wu, Yunshu, et al.
Pubblicazione: (2026)

Discrete Stochastic Localization for Non-autoregressive Generation
di: Wu, Yunshu, et al.
Pubblicazione: (2026)

MMG: Mutual Information Estimation via the MMSE Gap in Diffusion
di: Yu, Longxuan, et al.
Pubblicazione: (2025)

Improving Mutual Information Estimation with Annealed and Energy-Based Bounds
di: Brekelmans, Rob, et al.
Pubblicazione: (2023)

Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models
di: Yu, Longxuan, et al.
Pubblicazione: (2026)

Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language Models
di: Yu, Longxuan, et al.
Pubblicazione: (2026)

DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs
di: Yu, Longxuan, et al.
Pubblicazione: (2026)

Annealed Importance Sampling with q-Paths
di: Brekelmans, Rob, et al.
Pubblicazione: (2020)

Interpretable Diffusion via Information Decomposition
di: Kong, Xianghao, et al.
Pubblicazione: (2023)

Spectral Regularization for Diffusion Models
di: Chandran, Satish, et al.
Pubblicazione: (2026)

Your Diffusion Model is Secretly a Noise Classifier and Benefits from Contrastive Training
di: Wu, Yunshu, et al.
Pubblicazione: (2024)

Making Sense Of Distributed Representations With Activation Spectroscopy
di: Reing, Kyle, et al.
Pubblicazione: (2025)

Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks
di: Shahgir, Haz Sameen, et al.
Pubblicazione: (2023)

Variational Representations of Annealing Paths: Bregman Information under Monotonic Embedding
di: Brekelmans, Rob, et al.
Pubblicazione: (2022)

Learning Morphisms with Gauss-Newton Approximation for Growing Networks
di: Lawton, Neal, et al.
Pubblicazione: (2024)

FedDAPL: Toward Client-Private Generalization in Federated Learning
di: Loaliyan, Soroosh Safari, et al.
Pubblicazione: (2025)

Generating Synthetic Net Load Data with Physics-informed Diffusion Model
di: Zhang, Shaorong, et al.
Pubblicazione: (2024)

Prompt Perturbation Consistency Learning for Robust Language Models
di: Qiang, Yao, et al.
Pubblicazione: (2024)

Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding
di: Achille, Alessandro, et al.
Pubblicazione: (2024)

Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow
di: Zhong, Yangyang, et al.
Pubblicazione: (2026)

AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion
di: Abir, Abrar Rahman, et al.
Pubblicazione: (2025)

Knowledge Enhanced Multi-Domain Recommendations in an AI Assistant Application
di: Markowitz, Elan, et al.
Pubblicazione: (2023)

Generalized Flow Matching for Transition Dynamics Modeling
di: Wang, Haibo, et al.
Pubblicazione: (2024)

Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo
di: Zhao, Stephen, et al.
Pubblicazione: (2024)

Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference
di: Zhao, Stephen, et al.
Pubblicazione: (2025)

Diffusion Bridge Models for 3D Medical Image Translation
di: Zhang, Shaorong, et al.
Pubblicazione: (2025)

QuAILoRA: Quantization-Aware Initialization for LoRA
di: Lawton, Neal, et al.
Pubblicazione: (2024)

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

Masked Diffusion Models are Secretly Learned-Order Autoregressive Models
di: Garg, Prateek, et al.
Pubblicazione: (2025)

ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
di: Kang, Wonjun, et al.
Pubblicazione: (2025)

DualDiffusion: A Speculative Decoding Strategy for Masked Diffusion Models
di: Goyal, Satyam, et al.
Pubblicazione: (2026)

Accelerating Parallel Sampling of Diffusion Models
di: Tang, Zhiwei, et al.
Pubblicazione: (2024)

Regressor-guided Diffusion Model for De Novo Peptide Sequencing with Explicit Mass Control
di: Chen, Shaorong, et al.
Pubblicazione: (2026)

Any-Order Flexible Length Masked Diffusion
di: Kim, Jaeyeon, et al.
Pubblicazione: (2025)

Scalable Spatio-Temporal SE(3) Diffusion for Long-Horizon Protein Dynamics
di: Shoghi, Nima, et al.
Pubblicazione: (2026)

Polybasic Speculative Decoding Through a Theoretical Perspective
di: Wang, Ruilin, et al.
Pubblicazione: (2025)