Cover Image

Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huo, Mingxiao, Zhang, Jiayi, Wang, Hewei, Xu, Jinfeng, Chen, Zheyu, Tai, Huilin, Chen, Yijun
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding
by: Kang, Jialiang, et al.
Published: (2025)

Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification
by: Huang, Wenxuan, et al.
Published: (2024)

SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant
by: Sun, Guohao, et al.
Published: (2024)

SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding
by: Lin, Yijun, et al.
Published: (2026)

X-LLaVA: Optimizing Bilingual Large Vision-Language Alignment
by: Shin, Dongjae, et al.
Published: (2024)

LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model
by: Hinck, Musashi, et al.
Published: (2024)

NanoSpec: Accelerating Speculative Decoding using Minimalist In-Context Vocabularies
by: Chen, Zhiyang, et al.
Published: (2026)

Why do LLaVA Vision-Language Models Reply to Images in English?
by: Hinck, Musashi, et al.
Published: (2024)

LLaVAC: Fine-tuning LLaVA as a Multimodal Sentiment Classifier
by: Chay-intr, T., et al.
Published: (2025)

SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
by: Shi, Weijie, et al.
Published: (2026)

Cosmos-LLaVA: Chatting with the Visual Cosmos-LLaVA: Görselle Sohbet Etmek
by: Zeer, Ahmed, et al.
Published: (2024)

Amharic LLaMA and LLaVA: Multimodal LLMs for Low Resource Languages
by: Andersland, Michael
Published: (2024)

Annotation-Efficient Vision-Language Model Adaptation to the Polish Language Using the LLaVA Framework
by: Statkiewicz, Grzegorz, et al.
Published: (2026)

LLaVA-CMoE: Towards Continual Mixture of Experts for Large Vision-Language Models
by: Zhao, Hengyuan, et al.
Published: (2025)

SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding
by: Sun, Ryan, et al.
Published: (2024)

LLaVA-OneVision: Easy Visual Task Transfer
by: Li, Bo, et al.
Published: (2024)

Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models
by: Shi, Wenhao, et al.
Published: (2024)

G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model
by: Gao, Jiahui, et al.
Published: (2023)

LLaVA-Critic: Learning to Evaluate Multimodal Models
by: Xiong, Tianyi, et al.
Published: (2024)

MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning
by: Zhang, Jianyi, et al.
Published: (2024)

WSI-LLaVA: A Multimodal Large Language Model for Whole Slide Image
by: Liang, Yuci, et al.
Published: (2024)

LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model
by: Zhu, Yichen, et al.
Published: (2024)

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

Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models
by: Mamou, Jonathan, et al.
Published: (2024)

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation
by: Liu, Tianyu, et al.
Published: (2025)

HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model
by: Guo, Haiyang, et al.
Published: (2025)

LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
by: Zhang, Shaolei, et al.
Published: (2025)

LLaVA-Chef: A Multi-modal Generative Model for Food Recipes
by: Mohbat, Fnu, et al.
Published: (2024)

LLaVA-Video: Video Instruction Tuning With Synthetic Data
by: Zhang, Yuanhan, et al.
Published: (2024)

TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings
by: Yan, Dawei, et al.
Published: (2024)

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

LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
by: Shang, Yuzhang, et al.
Published: (2024)

MC-LLaVA: Multi-Concept Personalized Vision-Language Model
by: An, Ruichuan, et al.
Published: (2025)

MC-LLaVA: Multi-Concept Personalized Vision-Language Model
by: An, Ruichuan, et al.
Published: (2024)

LLaVA-NeuMT: Selective Layer-Neuron Modulation for Efficient Multilingual Multimodal Translation
by: Wei, Jingxuan, et al.
Published: (2025)

AVG-LLaVA: An Efficient Large Multimodal Model with Adaptive Visual Granularity
by: Lan, Zhibin, et al.
Published: (2024)

Accelerating Mobile Language Model via Speculative Decoding and NPU-Coordinated Execution
by: Chen, Zhiyang, et al.
Published: (2025)

LLaVA-Docent: Instruction Tuning with Multimodal Large Language Model to Support Art Appreciation Education
by: Lee, Unggi, et al.
Published: (2024)

HiSpec: Hierarchical Speculative Decoding for LLMs
by: Kumar, Avinash, et al.
Published: (2025)

ToolSpec: Accelerating Tool Calling via Schema-Aware and Retrieval-Augmented Speculative Decoding
by: Xia, Heming, et al.
Published: (2026)