Toward Autonomous Laboratory Safety Monitoring with Vision Language Models: Learning to See Hazards Through Scene Structure
cs.CV, cs.LG
Submitted: 2026-01-31
Updated: 2026-10-28
Terminology
Sources
- Schema-Guided Scene-Graph Reasoning based on Multi-Agent Large Language Model System
- The Llama 3 Herd of Models
- SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
- The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
- A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges
- BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science
- Are large language models superhuman chemists?
- Chemist Eye: A Visual Language Model-Powered System for Safety Monitoring and Robot Decision-Making in Self-Driving Laboratories
- Agent Laboratory: Using LLM Agents as Research Assistants
- OpenAI GPT-5 System Card
- Gemini: A Family of Highly Capable Multimodal Models
- Effective Data Augmentation With Diffusion Models
- Qwen3 Technical Report
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