Dream to Chat - Model-based Reinforcement Learning on Dialogues with User Belief Modeling and LSD-3D - Large-Scale 3D Driving Scene Generation with Geometry Grounding

Explore cutting-edge AI research in this 35-minute conference talk featuring two groundbreaking papers from Geely AI Lab and Princeton University in collaboration with Mercedes-Benz. Discover the first paper "Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling" by researchers from Geely AI Lab, Beijing Institute of Technology, and Beihang University, which presents innovative approaches to dialogue systems using reinforcement learning techniques that incorporate user belief modeling. Learn about the second paper "LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding" from Princeton University, Mercedes-Benz, and Torc Robotics, which introduces novel methods for generating large-scale 3D driving environments with geometric constraints for autonomous driving applications. Gain insights into how these research advances are pushing the boundaries of conversational AI and autonomous vehicle technology, with practical implications for the automotive industry's AI development.