Cover Image

Polybasic Speculative Decoding Through a Theoretical Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Ruilin, Li, Huixia, Ma, Yuexiao, Zheng, Xiawu, Chao, Fei, Xiao, Xuefeng, Ji, Rongrong
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AffineQuant: Affine Transformation Quantization for Large Language Models
by: Ma, Yuexiao, et al.
Published: (2024)

Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective
by: Huang, Weizhong, et al.
Published: (2025)

OMPQ: Orthogonal Mixed Precision Quantization
by: Ma, Yuexiao, et al.
Published: (2021)

A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation
by: Ma, Qingchuan, et al.
Published: (2026)

Towards Efficient Automatic Self-Pruning of Large Language Models
by: Huang, Weizhong, et al.
Published: (2025)

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

Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective
by: Ma, Qingchuan, et al.
Published: (2025)

HASTE: Training-Free Video Diffusion Acceleration via Head-Wise Adaptive Sparse Attention
by: Zheng, Xuzhe, et al.
Published: (2026)

Flow caching for autoregressive video generation
by: Ma, Yuexiao, et al.
Published: (2026)

Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference
by: Zhou, Xuwen, et al.
Published: (2026)

A Graph Sufficiency Perspective for Neural Networks
by: Shen, Cencheng, et al.
Published: (2025)

Speculative Speculative Decoding
by: Kumar, Tanishq, et al.
Published: (2026)

EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs
by: Guo, Song, et al.
Published: (2024)

Dynamic Low-Rank Sparse Adaptation for Large Language Models
by: Huang, Weizhong, et al.
Published: (2025)

Decoding Speculative Decoding
by: Yan, Minghao, et al.
Published: (2024)

Boosting the Cross-Architecture Generalization of Dataset Distillation through an Empirical Study
by: Zhao, Lirui, et al.
Published: (2023)

SpecPipe: Accelerating Pipeline Parallelism-based LLM Inference with Speculative Decoding
by: Yin, Haofei, et al.
Published: (2025)

Speculative Safety-Aware Decoding
by: Wang, Xuekang, et al.
Published: (2025)

Accelerating Time Series Foundation Models with Speculative Decoding
by: Subbaraman, Pranav, et al.
Published: (2025)

ALGOGEN: Tool-Generated Verifiable Traces for Reliable Algorithm Visualization
by: Liao, Kunpeng, et al.
Published: (2026)

MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification
by: Song, Jingwei, et al.
Published: (2026)

KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
by: Zheng, Zihao, et al.
Published: (2026)

Speculative Decoding Across Languages
by: Paudel, Nirajan, et al.
Published: (2026)

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

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

TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification
by: Jiang, Haoyun, et al.
Published: (2026)

Online Speculative Decoding
by: Liu, Xiaoxuan, et al.
Published: (2023)

Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance
by: Wang, Songsheng, et al.
Published: (2025)

Linear Discriminant Analysis with Gradient Optimization
by: Shen, Cencheng, et al.
Published: (2025)

High-Dimensional Independence Testing via Maximum and Average Distance Correlations
by: Shen, Cencheng, et al.
Published: (2020)

TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration
by: Li, Ye, et al.
Published: (2025)

Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation
by: Li, Xingyao, et al.
Published: (2026)

Fast Inference via Hierarchical Speculative Decoding
by: Mohri, Clara, et al.
Published: (2025)

Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs
by: Liu, Hongyi, et al.
Published: (2025)

QSpec: Speculative Decoding with Complementary Quantization Schemes
by: Zhao, Juntao, et al.
Published: (2024)

MoE-Spec: Expert Budgeting for Efficient Speculative Decoding
by: McDanel, Bradley, et al.
Published: (2026)

UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding
by: Weng, Yepeng, et al.
Published: (2026)

BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
by: Hou, Yunlong, et al.
Published: (2025)

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

Steering Pretrained Drafters during Speculative Decoding
by: Berdoz, Frédéric, et al.
Published: (2025)