Cover Image

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Shen, Yao, Liuyi, Niu, Wujia, Zhang, Lan, Li, Yaliang
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Safety Layers in Aligned Large Language Models: The Key to LLM Security
by: Li, Shen, et al.
Published: (2024)

Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
by: Li, Jiaming, et al.
Published: (2025)

The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective
by: Qin, Zhen, et al.
Published: (2024)

Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model
by: Feng, Qianhan, et al.
Published: (2024)

Gestura: A LVLM-Powered System Bridging Motion and Semantics for Real-Time Free-Form Gesture Understanding
by: Li, Zhuoming, et al.
Published: (2025)

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

LVLM-Aided Alignment of Task-Specific Vision Models
by: Koebler, Alexander, et al.
Published: (2025)

GLIMPSE: Holistic Cross-Modal Explainability for Large Vision-Language Models
by: Shen, Guanxi
Published: (2025)

DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?
by: Jiao, Qirui, et al.
Published: (2025)

TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models
by: Shao, Wenqi, et al.
Published: (2023)

VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation
by: Park, Seongheon, et al.
Published: (2026)

LVLM-COUNT: Enhancing the Counting Ability of Large Vision-Language Models
by: Qharabagh, Muhammad Fetrat, et al.
Published: (2024)

Kestrel: Grounding Self-Refinement for LVLM Hallucination Mitigation
by: Mao, Jiawei, et al.
Published: (2026)

AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal Alignment
by: Li, Yan, et al.
Published: (2024)

Vision-and-Language Navigation via Causal Learning
by: Wang, Liuyi, et al.
Published: (2024)

SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model and Cross-Modal Interpretability
by: Nasiri-Sarvi, Ali, et al.
Published: (2025)

Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question Answering
by: Shen, Zhixuan, et al.
Published: (2024)

MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for Effective-and-Efficient Vision-and-Language Navigation
by: Wang, Liuyi, et al.
Published: (2024)

Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation
by: Cheng, Ruoxi, et al.
Published: (2026)

Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models
by: Yamabe, Shojiro, et al.
Published: (2025)

From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information
by: Jiao, Qirui, et al.
Published: (2024)

Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models
by: Kim, Mingyeong, et al.
Published: (2026)

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction
by: Man, Yuanbin, et al.
Published: (2024)

Multi-Modal Character Localization and Extraction for Chinese Text Recognition
by: Li, Qilong, et al.
Published: (2026)

OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis
by: Lin, Tianwei, et al.
Published: (2026)

Bridging Modality Gap for Visual Grounding with Effecitve Cross-modal Distillation
by: Wang, Jiaxi, et al.
Published: (2023)

Seeing is Believing: Robust Vision-Guided Cross-Modal Prompt Learning under Label Noise
by: Geng, Zibin, et al.
Published: (2026)

ArtAug: Enhancing Text-to-Image Generation through Synthesis-Understanding Interaction
by: Duan, Zhongjie, et al.
Published: (2024)

GeoVLMath: Enhancing Geometry Reasoning in Vision-Language Models via Cross-Modal Reward for Auxiliary Line Creation
by: Guo, Shasha, et al.
Published: (2025)

AnalogRetriever: Learning Cross-Modal Representations for Analog Circuit Retrieval
by: Wang, Yihan, et al.
Published: (2026)

AlignGuard: Scalable Safety Alignment for Text-to-Image Generation
by: Liu, Runtao, et al.
Published: (2024)

Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models
by: Yan, Hanqi, et al.
Published: (2025)

REALM: An RGB and Event Aligned Latent Manifold for Cross-Modal Perception
by: Polizzi, Vincenzo, et al.
Published: (2026)

SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense
by: Huang, Yiyang, et al.
Published: (2025)

Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning
by: Li, Jiazheng, et al.
Published: (2026)

Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models
by: Jiao, Qirui, et al.
Published: (2024)

HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks
by: Zhou, Ting, et al.
Published: (2024)

OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language Models
by: Miyamoto, Ryoto, et al.
Published: (2025)

DriveCritic: Towards Context-Aware, Human-Aligned Evaluation for Autonomous Driving with Vision-Language Models
by: Song, Jingyu, et al.
Published: (2025)

Cross-Modal Adapter for Vision-Language Retrieval
by: Jiang, Haojun, et al.
Published: (2022)