Imagen de Portada

Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Qishun, Yang, Shu, Hu, Lijie, Wang, Di
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap
por: Liu, Qin, et al.
Publicado: (2025)

Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images
por: You, Liangliang, et al.
Publicado: (2025)

SHAPE : Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner
por: Chen, Kejia, et al.
Publicado: (2025)

Textual and Visual Prompt Fusion for Image Editing via Step-Wise Alignment
por: Feng, Zhanbo, et al.
Publicado: (2023)

PersonaTalk: Bring Attention to Your Persona in Visual Dubbing
por: Zhang, Longhao, et al.
Publicado: (2024)

From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment
por: Suo, Yucheng, et al.
Publicado: (2025)

Benchmarking and Mitigating Sycophancy in Medical Vision Language Models
por: Xu, Juangui, et al.
Publicado: (2025)

Text Guided Image Editing with Automatic Concept Locating and Forgetting
por: Li, Jia, et al.
Publicado: (2024)

Evaluating Data Influence in Meta Learning
por: Ren, Chenyang, et al.
Publicado: (2025)

Dual Relation Alignment for Composed Image Retrieval
por: Jiang, Xintong, et al.
Publicado: (2023)

Cross-Modal Attention Analysis and Optimization in Vision-Language Models: A Study on Visual Reliability
por: Zhou, Lijie
Publicado: (2026)

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
por: Zhou, Wenrui, et al.
Publicado: (2025)

Dissecting Representation Misalignment in Contrastive Learning via Influence Function
por: Hu, Lijie, et al.
Publicado: (2024)

Online Iterative Self-Alignment for Radiology Report Generation
por: Xiao, Ting, et al.
Publicado: (2025)

Personalized Safety Alignment for Text-to-Image Diffusion Models
por: Lei, Yu, et al.
Publicado: (2025)

Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment
por: Song, Zhixue, et al.
Publicado: (2026)

Fair Text-to-Image Diffusion via Fair Mapping
por: Li, Jia, et al.
Publicado: (2023)

VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation
por: Li, Bo, et al.
Publicado: (2026)

Instant Preference Alignment for Text-to-Image Diffusion Models
por: Li, Yang, et al.
Publicado: (2025)

Advancing Brain Imaging Analysis Step-by-step via Progressive Self-paced Learning
por: Yang, Yanwu, et al.
Publicado: (2024)

SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
por: Dai, Josef, et al.
Publicado: (2024)

Unsupervised Audio-Visual Segmentation with Modality Alignment
por: Bhosale, Swapnil, et al.
Publicado: (2024)

FOCA: Frequency-Oriented Cross-Domain Forgery Detection, Localization and Explanation via Multi-Modal Large Language Model
por: Liu, Zhou, et al.
Publicado: (2026)

Towards Multi-dimensional Explanation Alignment for Medical Classification
por: Hu, Lijie, et al.
Publicado: (2024)

Passive Construction Site Safety Monitoring via Persona-Scaffolded Adversarial Chain-of-Thought VLM Verification
por: Sriram, Ananth, et al.
Publicado: (2026)

Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models
por: Zeng, Zhen, et al.
Publicado: (2024)

Safety Alignment for Vision Language Models
por: Liu, Zhendong, et al.
Publicado: (2024)

EVE: Verifiable Self-Evolution of MLLMs via Executable Visual Transformations
por: Heng, Yongrui, et al.
Publicado: (2026)

Beyond Visual Safety: Jailbreaking Multimodal Large Language Models for Harmful Image Generation via Semantic-Agnostic Inputs
por: Yu, Mingyu, et al.
Publicado: (2026)

AMLRIS: Alignment-aware Masked Learning for Referring Image Segmentation
por: Chen, Tongfei, et al.
Publicado: (2026)

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

RIHA: Report-Image Hierarchical Alignment for Radiology Report Generation
por: Chen, Yucheng, et al.
Publicado: (2026)

Poivre: Self-Refining Visual Pointing with Reinforcement Learning
por: Yang, Wenjie, et al.
Publicado: (2025)

NeuroBridge: Bio-Inspired Self-Supervised EEG-to-Image Decoding via Cognitive Priors and Bidirectional Semantic Alignment
por: Zhang, Wenjiang, et al.
Publicado: (2025)

RAAP: Retrieval-Augmented Affordance Prediction with Cross-Image Action Alignment
por: Zhuang, Qiyuan, et al.
Publicado: (2026)

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

Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval
por: Ma, Qing, et al.
Publicado: (2023)

DualCap: Enhancing Lightweight Image Captioning via Dual Retrieval with Similar Scenes Visual Prompts
por: Li, Binbin, et al.
Publicado: (2025)

Informative Text-Image Alignment for Visual Affordance Learning with Foundation Models
por: Zhang, Qian, et al.
Publicado: (2025)

Theoretically Achieving Continuous Representation of Oriented Bounding Boxes
por: Xiao, Zi-Kai, et al.
Publicado: (2024)