What Does a Safety Label Measure? Auditing Situational-Safety Benchmarks for Multimodal LLMs
cs.CV, cs.AI, cs.LG, cs.MA
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
- Seeing is not Enough: Vision-Language Models Perceive Evidence but Fail to Act
- SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Language Models (Mostly) Know What They Know
- SmolVLM: Redefining small and efficient multimodal models
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs