Image de couverture de livre

Divide and Conquer: Accelerating Diffusion-Based Large Language Models via Adaptive Parallel Decoding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Luo, Xiangzhong, An, Yilin, Yu, Zhicheng, Liu, Weichen, Yang, Xu
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Learning to Parallel: Accelerating Diffusion Large Language Models via Learnable Parallel Decoding
par: Bao, Wenrui, et autres
Publié: (2025)

Control Large Language Models via Divide and Conquer
par: Li, Bingxuan, et autres
Publié: (2024)

d$^2$Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching
par: Jiang, Yuchu, et autres
Publié: (2025)

Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models
par: Mao, Yanxu, et autres
Publié: (2024)

CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit
par: Wang, Kangyu, et autres
Publié: (2025)

An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models
par: Zhang, Yizhou, et autres
Publié: (2024)

Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding
par: Ou, Jie, et autres
Publié: (2024)

Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration
par: Wu, Pengfei, et autres
Publié: (2024)

Accelerating Diffusion LLMs via Adaptive Parallel Decoding
par: Israel, Daniel, et autres
Publié: (2025)

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism
par: Wei, Zhepei, et autres
Publié: (2025)

DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models
par: Cui, Wendi, et autres
Publié: (2024)

DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor Search
par: Yang, Lei, et autres
Publié: (2024)

ICU: Conquering Language Barriers in Vision-and-Language Modeling by Dividing the Tasks into Image Captioning and Language Understanding
par: Wu, Guojun
Publié: (2023)

Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence
par: Yu, Yijiong
Publié: (2025)

Enhancing LLM Character-Level Manipulation via Divide and Conquer
par: Xiong, Zhen, et autres
Publié: (2025)

Hierarchical Divide-and-Conquer for Fine-Grained Alignment in LLM-Based Medical Evaluation
par: Zheng, Shunfan, et autres
Publié: (2025)

DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs
par: Meng, Zijie, et autres
Publié: (2024)

Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
par: Ringel, Liran, et autres
Publié: (2026)

Exploring Deep-to-Shallow Transformable Neural Networks for Intelligent Embedded Systems
par: Luo, Xiangzhong, et autres
Publié: (2025)

Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
par: Wu, Chengyue, et autres
Publié: (2025)

Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models
par: Chen, Kecheng, et autres
Publié: (2025)

Divide, Cache, Conquer: Dichotomic Prompting for Efficient Multi-Label LLM-Based Classification
par: Langner, Mikołaj, et autres
Publié: (2025)

Fine-grained Verbal Attack Detection via a Hierarchical Divide-and-Conquer Framework
par: Zheng, Quan, et autres
Publié: (2026)

Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration
par: Xiao, Sibo, et autres
Publié: (2025)

Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding
par: Yi, Hanling, et autres
Publié: (2024)

Adaptive Draft-Verification for Efficient Large Language Model Decoding
par: Liu, Xukun, et autres
Publié: (2024)

Self Speculative Decoding for Diffusion Large Language Models
par: Gao, Yifeng, et autres
Publié: (2025)

ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
par: Li, Jia-Nan, et autres
Publié: (2025)

HADES: Hardware Accelerated Decoding for Efficient Speculation in Large Language Models
par: Yang, Ze, et autres
Publié: (2024)

Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability
par: Liang, Xiao, et autres
Publié: (2026)

Efficient Adaptive Rejection Sampling for Accelerating Speculative Decoding in Large Language Models
par: Sun, Chendong, et autres
Publié: (2025)

Locally Coherent Parallel Decoding in Diffusion Language Models
par: Hersche, Michael, et autres
Publié: (2026)

Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation
par: Chen, Jingchang, et autres
Publié: (2024)

Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?
par: Li, Pengxiang, et autres
Publié: (2026)

PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
par: Sun, Shengyin, et autres
Publié: (2026)

dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
par: Liu, Zhiyuan, et autres
Publié: (2025)

Coherence-Aware Task Graph Modeling for Realistic Application
par: Xiong, Guochu, et autres
Publié: (2025)

Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding
par: Zhang, Jun, et autres
Publié: (2023)

PEARL: Parallel Speculative Decoding with Adaptive Draft Length
par: Liu, Tianyu, et autres
Publié: (2024)

Accelerating Mobile Language Model via Speculative Decoding and NPU-Coordinated Execution
par: Chen, Zhiyang, et autres
Publié: (2025)