Imagen de Portada

SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hinojosa, Carlos, Grange, Clemens, Ghanem, Bernard
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Learning Semantic Segmentation with Query Points Supervision on Aerial Images
por: Rivier, Santiago, et al.
Publicado: (2023)

CURE: Curriculum-guided Multi-task Training for Reliable Anatomy Grounded Report Generation
por: Messina, Pablo, et al.
Publicado: (2026)

ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders
por: Hinojosa, Carlos, et al.
Publicado: (2024)

Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection
por: Li, Bangzheng, et al.
Publicado: (2025)

Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models
por: Yang, Jiaxi, et al.
Publicado: (2026)

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
por: Yang, Senqiao, et al.
Publicado: (2025)

AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
por: Lin, Zichuan, et al.
Publicado: (2025)

Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust and Semantically-Rich Vision-Language Models
por: Hossain, Md Zarif, et al.
Publicado: (2024)

Unified Vision-Language Modeling via Concept Space Alignment
por: Qiu, Yifu, et al.
Publicado: (2026)

Vision-Language Models Can Self-Improve Reasoning via Reflection
por: Cheng, Kanzhi, et al.
Publicado: (2024)

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

Learning to Steer: Input-dependent Steering for Multimodal LLMs
por: Parekh, Jayneel, et al.
Publicado: (2025)

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement
por: Wang, Xiyao, et al.
Publicado: (2024)

JSTR: Judgment Improves Scene Text Recognition
por: Fujitake, Masato
Publicado: (2024)

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

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

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

VisionZip: Longer is Better but Not Necessary in Vision Language Models
por: Yang, Senqiao, et al.
Publicado: (2024)

Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance
por: Zhao, Linxi, et al.
Publicado: (2024)

Evaluating the Correctness of Inference Patterns Used by LLMs for Judgment
por: Chen, Lu, et al.
Publicado: (2024)

A Novel Framework for Automated Explain Vision Model Using Vision-Language Models
por: Nguyen, Phu-Vinh, et al.
Publicado: (2025)

Imperfect Vision Encoders: Efficient and Robust Tuning for Vision-Language Models
por: Panos, Aristeidis, et al.
Publicado: (2024)

Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback
por: Xiao, Wenyi, et al.
Publicado: (2024)

Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
por: Zhai, Yuexiang, et al.
Publicado: (2024)

Vision-Language Model Based Handwriting Verification
por: Chauhan, Mihir, et al.
Publicado: (2024)

Differentiable Prompt Learning for Vision Language Models
por: Huang, Zhenhan, et al.
Publicado: (2024)

How Culturally Aware are Vision-Language Models?
por: Burda-Lassen, Olena, et al.
Publicado: (2024)

Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence
por: Yang, Yibo, et al.
Publicado: (2025)

Mordal: Automated Pretrained Model Selection for Vision Language Models
por: He, Shiqi, et al.
Publicado: (2025)

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

MedCLM: Learning to Localize and Reason via a CoT-Curriculum in Medical Vision-Language Models
por: Kim, Soo Yong, et al.
Publicado: (2025)

Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks
por: Lian, Shijie, et al.
Publicado: (2025)

Modeling Caption Diversity in Contrastive Vision-Language Pretraining
por: Lavoie, Samuel, et al.
Publicado: (2024)

Efficient Architectures for High Resolution Vision-Language Models
por: Carvalho, Miguel, et al.
Publicado: (2025)

Understanding the Effects of Distractors on Reasoning Vision-Language Models
por: Bae, Jiyun, et al.
Publicado: (2025)

Coordinated Robustness Evaluation Framework for Vision-Language Models
por: Babu, Ashwin Ramesh, et al.
Publicado: (2025)

Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification
por: Huang, Wenxuan, et al.
Publicado: (2024)

C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
por: Yoon, Hee Suk, et al.
Publicado: (2024)

Steering the Verifiability of Multimodal AI Hallucinations
por: Pang, Jianhong, et al.
Publicado: (2026)

Linear Spaces of Meanings: Compositional Structures in Vision-Language Models
por: Trager, Matthew, et al.
Publicado: (2023)