3 papers
cs.AI2026
Containment Verification: AI Safety Guarantees Independent of Alignment
Royce Moon, Lav R. Varshney
Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable…
cs.AI2025
Measuring Combinatorial Creativity in Large Language Models and Humans
Samuel Schapiro, Sumuk Shashidhar, Akshay K. Jagadish +11
Combinatorial creativity, the process of combining familiar ideas in unfamiliar ways, is one of the foremost engines of scientific, technological, and artistic progress. This work…
cs.AI2025
Spark: A System for Scientifically Creative Idea Generation
Aishik Sanyal, Samuel Schapiro, Sumuk Shashidhar +3
Recently, large language models (LLMs) have shown promising abilities to generate novel research ideas in science, a direction which coincides with many foundational principles in…