Cover Image

Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Wei, Li, Zhe, Li, Yige, Sun, Jun
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence 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

GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity
by: Park, Seongheon, et al.
Published: (2025)

When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs
by: Zhao, Beidi, et al.
Published: (2026)

ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation
by: Yang, Bang, et al.
Published: (2023)

Robust Multimodal Large Language Models Against Modality Conflict
by: Zhang, Zongmeng, et al.
Published: (2025)

Medical Image Synthesis via Fine-Grained Image-Text Alignment and Anatomy-Pathology Prompting
by: Chen, Wenting, et al.
Published: (2024)

Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion
by: Allgeuer, Philipp, et al.
Published: (2024)

Multimodal LLMs Can Reason about Aesthetics in Zero-Shot
by: Jiang, Ruixiang, et al.
Published: (2025)

Robust Vision-Language Models via Tensor Decomposition: A Defense Against Adversarial Attacks
by: Patel, Het, et al.
Published: (2025)

E$^2$AT: Multimodal Jailbreak Defense via Dynamic Joint Optimization for Multimodal Large Language Models
by: Lu, Liming, et al.
Published: (2025)

Inquire, Interact, and Integrate: A Proactive Agent Collaborative Framework for Zero-Shot Multimodal Medical Reasoning
by: Gu, Zishan, et al.
Published: (2024)

Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation
by: Liang, Yupu, et al.
Published: (2025)

Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)
by: Manevich, Avshalom, et al.
Published: (2024)

SpatialPrompting: Keyframe-driven Zero-Shot Spatial Reasoning with Off-the-Shelf Multimodal Large Language Models
by: Taguchi, Shun, et al.
Published: (2025)

Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?
by: Li, Xiujun, et al.
Published: (2023)

Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs
by: Ghosh, Sreyan, et al.
Published: (2024)

Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark
by: Guo, Ziyu, et al.
Published: (2025)

Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation
by: Hua, Zhenglin, et al.
Published: (2025)

Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context
by: Zheng, Ge, et al.
Published: (2025)

From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks
by: Zhang, Xiaofeng, et al.
Published: (2024)

CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook
by: Chen, Zeyu, et al.
Published: (2026)

Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
by: Patil, Vaidehi, et al.
Published: (2025)

IE-Critic-R1: Advancing the Explanatory Measurement of Text-Driven Image Editing for Human Perception Alignment
by: Qu, Bowen, et al.
Published: (2025)

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

MULTI: Multimodal Understanding Leaderboard with Text and Images
by: Zhu, Zichen, et al.
Published: (2024)

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification
by: Sun, Han, et al.
Published: (2026)

Zero-Shot Vehicle Model Recognition via Text-Based Retrieval-Augmented Generation
by: Chang, Wei-Chia, et al.
Published: (2025)

Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study
by: Wang, Chenguang, et al.
Published: (2024)

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation
by: Leng, Jixuan, et al.
Published: (2025)

Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
by: Xiao, Xin, et al.
Published: (2024)

Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification
by: Xu, Wenjia, et al.
Published: (2024)

TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment
by: Li, Wei, et al.
Published: (2024)

Fine-Grained Image-Text Alignment in Medical Imaging Enables Explainable Cyclic Image-Report Generation
by: Chen, Wenting, et al.
Published: (2023)

ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos
by: Maity, Krishanu, et al.
Published: (2024)

Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models
by: Li, You, et al.
Published: (2025)

Improving Alignment in LVLMs with Debiased Self-Judgment
by: Yang, Sihan, et al.
Published: (2025)

RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models
by: Chen, Haoyu, et al.
Published: (2024)

LFTR: Learning-Free Token Reduction for Multimodal Large Language Models
by: Zhao, Zihui, et al.
Published: (2025)

MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs
by: Ding, Wei, et al.
Published: (2026)

Toward Robust Multimodal Learning using Multimodal Foundational Models
by: Zhao, Xianbing, et al.
Published: (2024)

VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models
by: Jiang, Lingjie, et al.
Published: (2025)