Media Analytics | Yu-Kai Huang

Yu-Kai Huang is a Researcher in the Media Analytics group at NEC Laboratories America, where he works on prediction, planning, generative modeling, and embodied AI for autonomous systems. He earned his Ph.D. and M.S. in Electrical and Computer Engineering from Carnegie Mellon University and received his undergraduate degree in Computer Science and Information Engineering from National Central University.

His research focuses on building intelligent systems that can predict future behaviors, reason under uncertainty, and simulate complex multi-agent interactions for autonomous driving. His work spans motion prediction, trajectory planning, behavior simulation, and foundation models for autonomous systems. He emphasizes the development of scalable modeling frameworks capable of generating diverse, realistic, and physically plausible future scenarios to support robust decision-making in dynamic environments.

His work has been published at leading AI conferences, including the Conference on Computer Vision and Pattern Recognition (CVPR) and the Conference on Neural Information Processing Systems (NeurIPS). He has contributed to top-performing teams in major autonomous driving benchmarks, including a first-place result in the 2024 Waymo Open Dataset Sim Agents Challenge, a second-place result in the Motion Prediction Challenge, and multiple top rankings across the Argoverse 1 and Argoverse 2 Challenges from 2023 to 2024.