3 papers
cs.AI2026
LLM Jaggedness Unlocks Scientific Creativity
Shray Mathur, J. Anibal Boscoboinik, Esther H. R. Tsai +1
As artificial intelligence advances, models are not improving uniformly. Instead, progress unfolds in a jagged fashion, with capabilities growing unevenly across tasks, domains, an…
cs.SE2025
EnvTrace: Simulation-Based Semantic Evaluation of LLM Code via Execution Trace Alignment -- Demonstrated at Synchrotron Beamlines
Noah van der Vleuten, Anthony Flores, Shray Mathur +4
Evaluating large language models (LLMs) for instrument control requires methods that go beyond standard, stateless algorithmic benchmarks, since the behavior of physical systems ca…
cs.AI2024
VISION: A Modular AI Assistant for Natural Human-Instrument Interaction at Scientific User Facilities
Shray Mathur, Noah van der Vleuten, Kevin Yager +1
Scientific user facilities, such as synchrotron beamlines, are equipped with a wide array of hardware and software tools that require a codebase for human-computer-interaction. Thi…