Research Scientist · Vision-Language-Action Models
Can Cui 崔璨
Vision, language, and action models for autonomous systems that people can understand and trust.
citations · h-index
I am a Research Scientist in Vision-Language Action (VLA) Models at the
Bosch Center for Artificial Intelligence (BCAI), developing foundation models for personalized, interpretable, and safe autonomous driving. My prior industry experience includes serving as an AI Research Intern at
Toyota InfoTech Labs and as a Controls Research Intern at
Cummins Inc., developing control algorithms and digital twin validation for physical systems. I earned my Ph.D. from
Purdue University, advised by Dr. Ziran Wang, where my research focused on human–autonomy teaming, multimodal perception, and digital twin–based validation for autonomous vehicles. My work spans LLMs/VLMs, VLA, human-autonomy teaming, generative motion planning, control, and data-driven autonomy.
News
| Jan 5, 2026 |
I start working for Bosch Center for Artificial Intelligence (BCAI) as a Research Scientist in Vision-Language Action (VLA) Models!🎉
|
|---|---|
| Dec 1, 2025 | I successfully defend my Ph.D. dissertation on “Foundation Models for Human-Autonomy Teaming in Autonomous Vehicles”! 🎉 |
| Oct 8, 2025 | I will serve as the Guest Editor of the JCAV Focus Issue on Large Language and Vision Models for Connected and Automated Vehicles!🎉 |
| Sep 10, 2025 | One paper is accepted at EMNLP 2025 Industry Track! 🎉 |
| Jan 17, 2025 | I will serve as the General Chair of the CVPR 2025 Workshop on Distillation of Foundation Models for Autonomous Driving. See you in Nashville!🎉 |
Selected Publications
* indicates equal contribution. See my Google Scholar for the complete list of publications.
-
P-IEEE
LLM4AD: Large Language Models for Autonomous Driving – Concept, Review, Benchmark, Experiments, and Future Trends -
EMNLP
DASR: Distributed Adaptive Scene Recognition-A Multi-Agent Cloud-Edge Framework for Language-Guided Scene Detection -
ITSC
Personalized Autonomous Driving with Large Language Models: Field Experiments -
CVPR
LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs -
ITSM
Receive, Reason, and React: Drive as You Say with Large Language Models in Autonomous Vehicles -
WACV
Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehicles -
T-IV
REDFormer: Radar Enlightens the Darkness of Camera Perception with Transformers