Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning
Paper • 2608.27549 • Published • 50
Zhiyuan Shi
2304022380szy
·
AI & ML interests
World Models; AI Agent; Robotics
Recent Activity
upvoted a paper 18 days ago
HarnessEval-W: Agentifying the Evaluation of Visual Worlds updated a collection about 1 month ago
Video Understanding BenchmarksOrganizations
upvoted a paper 1 day ago