Imagen de Portada

SAGE: Accelerating Vision-Language Models via Entropy-Guided Adaptive Speculative Decoding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tong, Yujia, Zhang, Tian, Wan, Yunyang, Lin, Kaiwei, Yuan, Jingling, Hu, Chuang
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Enhancing Quantization-Aware Training on Edge Devices via Relative Entropy Coreset Selection and Cascaded Layer Correction
por: Tong, Yujia, et al.
Publicado: (2025)

LetheViT: Selective Machine Unlearning for Vision Transformers via Attention-Guided Contrastive Learning
por: Tong, Yujia, et al.
Publicado: (2025)

DFQ-ViT: Data-Free Quantization for Vision Transformers without Fine-tuning
por: Tong, Yujia, et al.
Publicado: (2025)

Visual Attention Drifts,but Anchors Hold:Mitigating Hallucination in Multimodal Large Language Models via Cross-Layer Visual Anchors
por: Yang, Chengxu, et al.
Publicado: (2026)

MMSpec: Benchmarking Speculative Decoding for Vision-Language Models
por: Shen, Hui, et al.
Publicado: (2026)

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

HSD: Training-Free Acceleration for Document Parsing Vision-Language Model with Hierarchical Speculative Decoding
por: Liao, Wenhui, et al.
Publicado: (2026)

SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation
por: Kang, Jialiang, et al.
Publicado: (2026)

SpecVLM: Fast Speculative Decoding in Vision-Language Models
por: Huang, Haiduo, et al.
Publicado: (2025)

Speculative Decoding Reimagined for Multimodal Large Language Models
por: Lin, Luxi, et al.
Publicado: (2025)

Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models
por: Im, Eun Woo, et al.
Publicado: (2025)

HIPPO: Accelerating Video Large Language Models Inference via Holistic-aware Parallel Speculative Decoding
por: Lv, Qitan, et al.
Publicado: (2026)

LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
por: Jang, Doohyuk, et al.
Publicado: (2024)

Poisoning Prompt-Guided Sampling in Video Large Language Models
por: Cao, Yuxin, et al.
Publicado: (2025)

Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
por: Teng, Yao, et al.
Publicado: (2025)

Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping
por: Zeng, Weili, et al.
Publicado: (2025)

SAGE: Saliency-Guided Contrastive Embeddings
por: Crum, Colton R., et al.
Publicado: (2025)

Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
por: So, Junhyuk, et al.
Publicado: (2025)

Speculative Decoding for Autoregressive Video Generation
por: Hu, Yuezhou, et al.
Publicado: (2026)

VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping
por: Dong, Haotian, et al.
Publicado: (2025)

SAGE: Sink-Aware Grounded Decoding for Multimodal Hallucination Mitigation
por: Shukla, Tripti, et al.
Publicado: (2026)

Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
por: Teng, Yao, et al.
Publicado: (2024)

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

SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
por: Wang, Hanzhen, et al.
Publicado: (2025)

PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding
por: Song, Wenxuan, et al.
Publicado: (2025)

ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding
por: Kong, Quan, et al.
Publicado: (2026)

Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy Analysis
por: Zhang, Yu, et al.
Publicado: (2026)

SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
por: Huang, Haoyu, et al.
Publicado: (2026)

Tag2Text: Guiding Vision-Language Model via Image Tagging
por: Huang, Xinyu, et al.
Publicado: (2023)

$Δ$VLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variation
por: Zhu, Yijie, et al.
Publicado: (2026)

VLA-InfoEntropy: A Training-Free Vision-Attention Information Entropy Approach for Vision-Language-Action Models Inference Acceleration and Success
por: Liu, Chuhang, et al.
Publicado: (2026)

SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition
por: Chen, Shunpeng, et al.
Publicado: (2025)

Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding
por: Min, Kyungmin, et al.
Publicado: (2024)

Grouped Speculative Decoding for Autoregressive Image Generation
por: So, Junhyuk, et al.
Publicado: (2025)

Continuous Speculative Decoding for Autoregressive Image Generation
por: Wang, Zili, et al.
Publicado: (2024)

SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation
por: Teng, Yao, et al.
Publicado: (2025)

Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding
por: Back, Kyungryul, et al.
Publicado: (2025)

ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models
por: Tian, Xinyu, et al.
Publicado: (2023)

Rethinking Overlooked Aspects in Vision-Language Models
por: Liu, Yuan, et al.
Publicado: (2024)

Multi-Scale Local Speculative Decoding for Image Generation
por: Peruzzo, Elia, et al.
Publicado: (2026)