Buchumschlag

From Evaluation to Defense: Advancing Safety in Video Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Sun, Yiwei, Jiang, Peiqi, Liu, Chuanbin, Lin, Luohao, Lu, Zhiying, Xie, Hongtao
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computer Vision and Pattern Recognition Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document Understanding
von: Li, Yinglu, et al.
Veröffentlicht: (2025)

Decoupling Perception from Reasoning for Hallucination-Resistant Video Understanding
von: Pu, Bowei, et al.
Veröffentlicht: (2025)

Hallucination Mitigation Prompts Long-term Video Understanding
von: Sun, Yiwei, et al.
Veröffentlicht: (2024)

Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models
von: Liu, Zhihang, et al.
Veröffentlicht: (2025)

VERHallu: Evaluating and Mitigating Event Relation Hallucination in Video Large Language Models
von: Zhang, Zefan, et al.
Veröffentlicht: (2026)

Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding
von: Yuan, Liping, et al.
Veröffentlicht: (2025)

Towards Fine-Grained Recognition with Large Visual Language Models: Benchmark and Optimization Strategies
von: Pang, Cong, et al.
Veröffentlicht: (2025)

Advancing Content Moderation: Evaluating Large Language Models for Detecting Sensitive Content Across Text, Images, and Videos
von: AlDahoul, Nouar, et al.
Veröffentlicht: (2024)

LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models
von: Ge, Qihang, et al.
Veröffentlicht: (2024)

SafeVid: Toward Safety Aligned Video Large Multimodal Models
von: Wang, Yixu, et al.
Veröffentlicht: (2025)

INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model
von: Ma, Yiwei, et al.
Veröffentlicht: (2024)

From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding
von: Zou, Heqing, et al.
Veröffentlicht: (2024)

Med-GLIP: Advancing Medical Language-Image Pre-training with Large-scale Grounded Dataset
von: Deng, Ziye, et al.
Veröffentlicht: (2025)

CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models
von: Li, Jingyao, et al.
Veröffentlicht: (2025)

PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering
von: Gao, Yifan, et al.
Veröffentlicht: (2025)

From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models
von: Dai, Muzhi, et al.
Veröffentlicht: (2025)

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
von: Ye, Mang, et al.
Veröffentlicht: (2025)

T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model
von: Zhang, Chenyu, et al.
Veröffentlicht: (2025)

Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models
von: Chen, Shimin, et al.
Veröffentlicht: (2024)

Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models
von: Xu, Yifan, et al.
Veröffentlicht: (2025)

VideoPoet: A Large Language Model for Zero-Shot Video Generation
von: Kondratyuk, Dan, et al.
Veröffentlicht: (2023)

FCoT-VL:Advancing Text-oriented Large Vision-Language Models with Efficient Visual Token Compression
von: Li, Jianjian, et al.
Veröffentlicht: (2025)

Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient Adaptation
von: Xie, Jingjing, et al.
Veröffentlicht: (2024)

SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability
von: Wang, Jiankang, et al.
Veröffentlicht: (2025)

Enhancing Advanced Visual Reasoning Ability of Large Language Models
von: Li, Zhiyuan, et al.
Veröffentlicht: (2024)

Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models
von: Zhao, Yunhan, et al.
Veröffentlicht: (2025)

Adversarial Defense in Vision-Language Models: An Overview
von: Fu, Xiaowei, et al.
Veröffentlicht: (2026)

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models
von: Sun, Fengyuan, et al.
Veröffentlicht: (2025)

COLT: Enhancing Video Large Language Models with Continual Tool Usage
von: Liu, Yuyang, et al.
Veröffentlicht: (2025)

VideoPhy: Evaluating Physical Commonsense for Video Generation
von: Bansal, Hritik, et al.
Veröffentlicht: (2024)

Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning
von: Zeng, Xingchen, et al.
Veröffentlicht: (2024)

TEMPLE: Incentivizing Temporal Understanding of Video Large Language Models via Progressive Pre-SFT Alignment
von: Li, Shicheng, et al.
Veröffentlicht: (2025)

Navigating the Trade-off: A Synthesis of Defensive Strategies for Zero-Shot Adversarial Robustness in Vision-Language Models
von: Xu, Zane, et al.
Veröffentlicht: (2025)

CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
von: Wang, Jiyuan, et al.
Veröffentlicht: (2026)

Advancing Egocentric Video Question Answering with Multimodal Large Language Models
von: Patel, Alkesh, et al.
Veröffentlicht: (2025)

Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward
von: Zhang, Ruohong, et al.
Veröffentlicht: (2024)

Evaluation of Safety Cognition Capability in Vision-Language Models for Autonomous Driving
von: Zhang, Enming, et al.
Veröffentlicht: (2025)

RAU: Reference-based Anatomical Understanding with Vision Language Models
von: Li, Yiwei, et al.
Veröffentlicht: (2025)

TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
von: Ren, Shuhuai, et al.
Veröffentlicht: (2023)

VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
von: Shen, Yichao, et al.
Veröffentlicht: (2025)