It Is Not Seeing the Hazard: A Frozen Vision-Language Safety Score Measures Its Caption Bank
cs.CV, cs.LG
Submitted: 2026-10-07
Updated: 2026-10-07
Terminology
Sources
- Constrained Policy Optimization
- Vision-Language Models Do Not Understand Negation
- Vision-Language Models as a Source of Rewards
- Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions
- Vision-Language Models as Success Detectors
- Probing the 3D Awareness of Visual Foundation Models
- MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
- VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving
- Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
- MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning
- Delving into Out-of-Distribution Detection with Vision-Language Representations
- Learning Transferable Visual Models From Natural Language Supervision
- Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning
- RoboCLIP: One Demonstration is Enough to Learn Robot Policies
- Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
- A Theory of Usable Information Under Computational Constraints
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models