Cover Image

Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yue, Yi, Xin, Shi, Dongsheng, de Melo, Gerard, Wang, Xiaoling, Wang, Linlin
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning
by: Yi, Xin, et al.
Published: (2024)

AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models
by: Li, Yue, et al.
Published: (2026)

Think-Reflect-Revise: A Policy-Guided Reflective Framework for Safety Alignment in Large Vision Language Models
by: Weng, Fenghua, et al.
Published: (2025)

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

MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models
by: Xia, Yinan, et al.
Published: (2025)

Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
by: Ding, Yi, et al.
Published: (2025)

HieraVid: Hierarchical Token Pruning for Fast Video Large Language Models
by: Guo, Yansong, et al.
Published: (2026)

ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time
by: Ding, Yi, et al.
Published: (2024)

Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models
by: Xu, Shicheng, et al.
Published: (2024)

Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking
by: Li, Jingru, et al.
Published: (2026)

Can Large Vision-Language Models Understand Multimodal Sarcasm?
by: Wang, Xinyu, et al.
Published: (2025)

Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
by: Bachu, Saketh, et al.
Published: (2024)

Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models
by: Son, Jaemin, et al.
Published: (2025)

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models
by: Liu, Jianyu, et al.
Published: (2025)

Hyperbolic Safety-Aware Vision-Language Models
by: Poppi, Tobia, et al.
Published: (2025)

A Unified Hallucination Mitigation Framework for Large Vision-Language Models
by: Chang, Yue, et al.
Published: (2024)

CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
by: Tang, Zicong, et al.
Published: (2025)

Multimodal Large Language Models for Enhanced Traffic Safety: A Comprehensive Review and Future Trends
by: Tami, Mohammad Abu, et al.
Published: (2025)

Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification
by: Weng, Charles, et al.
Published: (2026)

A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models
by: Jing, Liqiang, et al.
Published: (2025)

HomeSafeBench: A Benchmark for Embodied Vision-Language Models in Free-Exploration Home Safety Inspection
by: Gao, Siyuan, et al.
Published: (2025)

Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language Models
by: Liu, Shaonan, et al.
Published: (2026)

VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service
by: Wang, Xiasi, et al.
Published: (2025)

Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding
by: Zeng, Tong, et al.
Published: (2025)

Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts
by: Wu, Xuyang, et al.
Published: (2024)

GeoAlign: Geometric Feature Realignment for MLLM Spatial Reasoning
by: Liu, Zhaochen, et al.
Published: (2026)

Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving
by: Li, Yue, et al.
Published: (2025)

A Spectrum Evaluation Benchmark for Medical Multi-Modal Large Language Models
by: Liu, Jie, et al.
Published: (2024)

HazardNet: A Small-Scale Vision Language Model for Real-Time Traffic Safety Detection at Edge Devices
by: Tami, Mohammad Abu, et al.
Published: (2025)

Visual In-Context Learning for Large Vision-Language Models
by: Zhou, Yucheng, et al.
Published: (2024)

The Safety Reminder: A Soft Prompt to Reactivate Delayed Safety Awareness in Vision-Language Models
by: Tang, Peiyuan, et al.
Published: (2025)

NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision
by: Li, Xiang, et al.
Published: (2024)

Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models
by: Wang, Weihang, et al.
Published: (2025)

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
by: Ma, Xingjun, et al.
Published: (2025)

Vision-centric Token Compression in Large Language Model
by: Xing, Ling, et al.
Published: (2025)

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models
by: Liu, Jizhihui, et al.
Published: (2025)

SurvAgent: Hierarchical CoT-Enhanced Case Banking and Dichotomy-Based Multi-Agent System for Multimodal Survival Prediction
by: Huang, Guolin, et al.
Published: (2025)

SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model
by: Zhang, Yongting, et al.
Published: (2024)

Cerberus: Real-Time Video Anomaly Detection via Cascaded Vision-Language Models
by: Zheng, Yue, et al.
Published: (2025)

Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
by: Wen, Zichen, et al.
Published: (2025)