Visual Grounding Safety in Vision-Language Models
cs.AI, cs.CR, cs.CV, cs.CY, cs.LG
Submitted: 2026-10-05
Updated: 2026-10-05
Code: https://github.com/tatsu-lab/stanford_alpaca
Terminology
Sources
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agents
- Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic
- PointArena: Probing Multimodal Grounding Through Language-Guided Pointing
- MolmoPoint: Better Pointing for VLMs with Grounding Tokens
- Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
- GRIT: Teaching MLLMs to Think with Images
- FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts
- Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents
- Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
- Can AI Perceive Physical Danger and Intervene?
- Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents
- OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
- MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?
- MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models
- Visual-RFT: Visual Reinforcement Fine-Tuning
- BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models
- Kosmos-2: Grounding Multimodal Large Language Models to the World
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems