Cover Image

When Drafts Evolve: Speculative Decoding Meets Online Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qian, Yu-Yang, Wu, Hao-Cong, Fu, Yichao, Zhang, Hao, Zhao, Peng
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
by: Shen, Yuhao, et al.
Published: (2026)

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

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration
by: Wen, Zhuofan, et al.
Published: (2024)

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
by: Yang, Penghui, et al.
Published: (2025)

POSS: Position Specialist Generates Better Draft for Speculative Decoding
by: Huang, Langlin, et al.
Published: (2025)

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning
by: Xu, Yuhang, et al.
Published: (2026)

BudgetDraft: Acceptance-Aware Multi-View Training for Sparse-KV Speculative Decoding
by: He, Liang, et al.
Published: (2026)

FastGRPO: Accelerating Policy Optimization via Concurrency-aware Speculative Decoding and Online Draft Learning
by: Zhang, Yizhou, et al.
Published: (2025)

Balancing Coverage and Draft Latency in Vocabulary Trimming for Faster Speculative Decoding
by: Shoham, Ofir Ben
Published: (2026)

ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts
by: Georganas, Evangelos, et al.
Published: (2025)

Training Domain Draft Models for Speculative Decoding: Best Practices and Insights
by: Hong, Fenglu, et al.
Published: (2025)

When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
by: You, Haoran, et al.
Published: (2024)

Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design
by: Zhang, Yudi, et al.
Published: (2025)

Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs
by: Goel, Raghavv, et al.
Published: (2024)

MineDraft: A Framework for Batch Parallel Speculative Decoding
by: Tang, Zhenwei, et al.
Published: (2026)

Make Every Draft Count: Hidden State based Speculative Decoding
by: Chen, Yuetao, et al.
Published: (2026)

D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
by: Wu, Tianyu, et al.
Published: (2026)

When Continue Learning Meets Multimodal Large Language Model: A Survey
by: Huo, Yukang, et al.
Published: (2025)

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

Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
by: Hao, Yongchang, et al.
Published: (2026)

Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language Models
by: Wu, Shutong, et al.
Published: (2025)

Agentic Unlearning: When LLM Agent Meets Machine Unlearning
by: Wang, Bin, et al.
Published: (2026)

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

Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs
by: Pan, Rui, et al.
Published: (2025)

PRISM: Parametrically Refactoring Inference for Speculative Sampling Draft Models
by: Wang, Xuliang, et al.
Published: (2026)

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

STree: Speculative Tree Decoding for Hybrid State-Space Models
by: Wu, Yangchao, et al.
Published: (2025)

Fast Large Language Model Collaborative Decoding via Speculation
by: Fu, Jiale, et al.
Published: (2025)

DEER: Draft with Diffusion, Verify with Autoregressive Models
by: Cheng, Zicong, et al.
Published: (2025)

When Graph Neural Network Meets Causality: Opportunities, Methodologies and An Outlook
by: Jiang, Wenzhao, et al.
Published: (2023)

$\texttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts
by: Cemri, Mert, et al.
Published: (2025)

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

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

When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning
by: Qiu, Chenghao, et al.
Published: (2026)

MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
by: Huang, Zongle, et al.
Published: (2025)

When Speculation Spills Secrets: Side Channels via Speculative Decoding In LLMs
by: Wei, Jiankun, et al.
Published: (2024)

Exploring and Improving Drafts in Blockwise Parallel Decoding
by: Kim, Taehyeon, et al.
Published: (2024)

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

Draft-Conditioned Constrained Decoding for Structured Generation in LLMs
by: Reddy, Avinash, et al.
Published: (2026)

Attention Drift: What Autoregressive Speculative Decoding Models Learn
by: Eldenk, Doğaç, et al.
Published: (2026)