Cover Image

Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Pengxiang, Muhtar, Dilxat, Chen, Tianlong, Yin, Lu, Liu, Shiwei
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Diffusion Language Models Know the Answer Before Decoding
by: Li, Pengxiang, et al.
Published: (2025)

ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
by: Li, Jia-Nan, et al.
Published: (2025)

Outlier-weighed Layerwise Sampling for LLM Fine-tuning
by: Li, Pengxiang, et al.
Published: (2024)

CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit
by: Wang, Kangyu, et al.
Published: (2025)

The End of Manual Decoding: Towards Truly End-to-End Language Models
by: Wang, Zhichao, et al.
Published: (2025)

Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models
by: Cao, Mingyu, et al.
Published: (2026)

Locally Coherent Parallel Decoding in Diffusion Language Models
by: Hersche, Michael, et al.
Published: (2026)

Falcon: Faster and Parallel Inference of Large Language Models through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree
by: Gao, Xiangxiang, et al.
Published: (2024)

Reversible Diffusion Decoding for Diffusion Language Models
by: Wang, Xinyun, et al.
Published: (2026)

Differences in Text Generated by Diffusion and Autoregressive Language Models
by: Zhang, Zeyang, et al.
Published: (2026)

Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models
by: Li, Miao, et al.
Published: (2026)

PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition
by: Lu, Jinghui, et al.
Published: (2024)

LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model
by: Muhtar, Dilxat, et al.
Published: (2024)

Contextualization Distillation from Large Language Model for Knowledge Graph Completion
by: Li, Dawei, et al.
Published: (2024)

Breaking the Autoregressive Chain: Hyper-Parallel Decoding for Efficient LLM-Based Attribute Value Extraction
by: Glavas, Theodore, et al.
Published: (2026)

Deferred Commitment Decoding for Diffusion Language Models
by: Shu, Yingte, et al.
Published: (2026)

Are Large Language Models Truly Smarter Than Humans?
by: M, Eshwar Reddy, et al.
Published: (2026)

Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models
by: Kim, Jiyeon, et al.
Published: (2026)

StreamAdapter: Efficient Test Time Adaptation from Contextual Streams
by: Muhtar, Dilxat, et al.
Published: (2024)

How Well Do Large Language Models Truly Ground?
by: Lee, Hyunji, et al.
Published: (2023)

PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding
by: An, Zihao, et al.
Published: (2026)

Large Language Models Struggle in Token-Level Clinical Named Entity Recognition
by: Lu, Qiuhao, et al.
Published: (2024)

Cause and Effect: Can Large Language Models Truly Understand Causality?
by: Ashwani, Swagata, et al.
Published: (2024)

DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding
by: Li, Guanghao, et al.
Published: (2025)

Language Models Struggle to Use Representations Learned In-Context
by: Lepori, Michael A., et al.
Published: (2026)

Parallel Decoder Transformer: Planner-Seeded Latent Coordination for Synchronized Parallel Decoding
by: Robbins, Logan
Published: (2025)

Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding
by: Huang, Kung-Hsiang, et al.
Published: (2025)

Loop as a Bridge: Can Looped Transformers Truly Link Representation Space and Natural Language Outputs?
by: Chen, Guanxu, et al.
Published: (2026)

When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors
by: Emmons, Scott, et al.
Published: (2025)

Evaluating the Retrieval Robustness of Large Language Models
by: Cao, Shuyang, et al.
Published: (2025)

Empirical Analysis of Decoding Biases in Masked Diffusion Models
by: Huang, Pengcheng, et al.
Published: (2025)

A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models
by: Zhang, Lingzhe, et al.
Published: (2025)

Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving
by: Li, Pengxiang, et al.
Published: (2025)

AMO-Bench: Large Language Models Still Struggle in High School Math Competitions
by: An, Shengnan, et al.
Published: (2025)

Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs
by: Sun, Chenxi, et al.
Published: (2024)

Cerberus: Efficient Inference with Adaptive Parallel Decoding and Sequential Knowledge Enhancement
by: Liu, Yuxuan, et al.
Published: (2024)

MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning
by: Yang, Yaming, et al.
Published: (2024)

ASPD: Unlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMs
by: Chen, Keyu, et al.
Published: (2025)

Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM Editing
by: Liu, Ziyang
Published: (2026)

Automatically Planning Optimal Parallel Strategy for Large Language Models
by: Li, Zongbiao, et al.
Published: (2024)