Cover Image

MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ganesan, Mugilan, Segal, Shane, Aggarwal, Ankur, Sinnadurai, Nish, Lie, Sean, Thangarasa, Vithursan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

SD$^2$: Self-Distilled Sparse Drafters
by: Lasby, Mike, et al.
Published: (2025)

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

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

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

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

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

Anthropogenic Regional Adaptation in Multimodal Vision-Language Model
by: Cahyawijaya, Samuel, et al.
Published: (2026)

Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
by: Zhang, Ce, et al.
Published: (2025)

Self Speculative Decoding for Diffusion Large Language Models
by: Gao, Yifeng, et al.
Published: (2025)

Conflict Adaptation in Vision-Language Models
by: Hu, Xiaoyang
Published: (2025)

Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models
by: Hu, Yushi, et al.
Published: (2023)

How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
by: Lee, Seongyun, et al.
Published: (2024)

Temperature-Centric Investigation of Speculative Decoding with Knowledge Distillation
by: Ouyang, Siru, et al.
Published: (2024)

Modality-Agnostic fMRI Decoding of Vision and Language
by: Nikolaus, Mitja, et al.
Published: (2024)

MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation
by: Koleilat, Taha, et al.
Published: (2026)

LLAVADI: What Matters For Multimodal Large Language Models Distillation
by: Xu, Shilin, et al.
Published: (2024)

A Multi-Model Adaptation of Speculative Decoding for Classification
by: Roy, Somnath, et al.
Published: (2025)

Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties
by: Yu, Keunwoo Peter, et al.
Published: (2023)

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding
by: Hoshino, Yuichiro, et al.
Published: (2025)

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
by: Kim, Sanghwan, et al.
Published: (2024)

Pre-Training Multimodal Hallucination Detectors with Corrupted Grounding Data
by: Whitehead, Spencer, et al.
Published: (2024)

On Speculative Decoding for Multimodal Large Language Models
by: Gagrani, Mukul, et al.
Published: (2024)

LinguDistill: Recovering Linguistic Ability in Vision-Language Models via Selective Cross-Modal Distillation
by: Irawan, Patrick Amadeus, et al.
Published: (2026)

Rethinking the Mixture of Vision Encoders Paradigm for Enhanced Visual Understanding in Multimodal LLMs
by: Azadani, Mozhgan Nasr, et al.
Published: (2025)

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
by: Yuan, Qianhao, et al.
Published: (2026)

Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation
by: Wang, Xintong, et al.
Published: (2025)

Enhancing Vision-Language Few-Shot Adaptation with Negative Learning
by: Zhang, Ce, et al.
Published: (2024)

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

VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering
by: Lim, Qi Zhi, et al.
Published: (2025)

Evaluating Vision Language Model Adaptations for Radiology Report Generation in Low-Resource Languages
by: Salmè, Marco, et al.
Published: (2025)

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

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
by: Yoon, Hee Suk, et al.
Published: (2026)

HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation
by: Liang, Yihao, et al.
Published: (2026)

General Scene Adaptation for Vision-and-Language Navigation
by: Hong, Haodong, et al.
Published: (2025)

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

Mitigating Hallucinations in Large Vision-Language Models with Internal Fact-based Contrastive Decoding
by: Wang, Chao, et al.
Published: (2025)

Watch Closely: Mitigating Object Hallucinations in Large Vision-Language Models with Disentangled Decoding
by: Ma, Ruiqi, et al.
Published: (2025)

CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts
by: Nikandrou, Malvina, et al.
Published: (2024)