Tian Lan

A new method enhances policy evaluation in offline RL.

Text2Data improves data generation using unlabeled and labeled sources effectively.

Introducing a framework for AI collaboration with agents whose goals are not clear.

Exploring unique properties and behaviors of topological orders in materials.

This paper presents Bayesian-CFR, enhancing decision-making in complex games with incomplete information.

A new method called ADEPT improves offline reinforcement learning through adaptive models.

APIGen generates diverse, high-quality datasets for function-calling agents.

A new framework enhances RL simulations for complex scientific data processing.

A framework to improve teamwork among diverse software engineering agents.

Y-Flash cells and Tsetlin Machine enhance machine learning efficiency.

SpecTool brings clarity to LLM errors in using tools.