Cover Image

DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Zining, Hu, Yunhai, Xia, Tianhua, Bao, Bo, Sather, Eric, Thangarasa, Vithursan, Zhang, Sai Qian
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding
by: Hu, Yunhai, et al.
Published: (2025)

DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution
by: Hu, Yunhai, et al.
Published: (2026)

CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts
by: Yin, Xiangyang, et al.
Published: (2026)

TapOut: A Bandit-Based Approach to Dynamic Speculative Decoding
by: Sridhar, Aditya, et al.
Published: (2025)

MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models
by: Ganesan, Mugilan, et al.
Published: (2025)

Speculative Decoding and Beyond: An In-Depth Survey of Techniques
by: Hu, Yunhai, et al.
Published: (2025)

Draft, Verify, and Improve: Toward Training-Aware Speculative Decoding
by: Bhansali, Shrenik, et al.
Published: (2025)

Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
by: Thangarasa, Vithursan, et al.
Published: (2023)

When Drafts Evolve: Speculative Decoding Meets Online Learning
by: Qian, Yu-Yang, et al.
Published: (2026)

PipeSpec: Breaking Stage Dependencies in Hierarchical LLM Decoding
by: McDanel, Bradley, et al.
Published: (2025)

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

Self-Data Distillation for Recovering Quality in Pruned Large Language Models
by: Thangarasa, Vithursan, et al.
Published: (2024)

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

FastEagle: Cascaded Drafting for Accelerating Speculative Decoding
by: Huang, Haiduo, et al.
Published: (2025)

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

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

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

MediSwift: Efficient Sparse Pre-trained Biomedical Language Models
by: Thangarasa, Vithursan, et al.
Published: (2024)

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression
by: Lasby, Mike, et al.
Published: (2025)

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

TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding
by: Wang, Zhuoyu, et al.
Published: (2026)

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

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

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

TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs
by: Lee, Minjae, et al.
Published: (2026)

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding
by: Plaksin, Anton, et al.
Published: (2026)

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

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

Reject Only Critical Tokens: Pivot-Aware Speculative Decoding
by: Ziashahabi, Amir, et al.
Published: (2025)

Cost-Aware Diffusion Draft Trees for Speculative Decoding
by: Zhang, Shuai, et al.
Published: (2026)

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

OmniDraft: A Cross-vocabulary, Online Adaptive Drafter for On-device Speculative Decoding
by: Ramakrishnan, Ramchalam Kinattinkara, et al.
Published: (2025)

DREAM: Visual Decoding from Reversing Human Visual System
by: Xia, Weihao, et al.
Published: (2023)

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

PEARL: Parallel Speculative Decoding with Adaptive Draft Length
by: Liu, Tianyu, et al.
Published: (2024)

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

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

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

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

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