InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation Paper • 2510.09724 • Published Oct 10, 2025 • 10
JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence Paper • 2510.23538 • Published Oct 27, 2025 • 96
ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows Paper • 2505.19897 • Published May 26, 2025 • 104