Announcements:
-Purdue DT Lab always looks for self-motivated talents to join as PhD/MS students or onsite/remote interns,
and please refer to this page for more information.
Check out the first-of-its-kind field test of large language model-enabled autonomous driving! More details can be found on the
website.
An invited talk in Oct. 2022 that summarized Dr. Wang's research activities during 2017-2022. More details can be found in the
paper.
An invited talk and a panel discussion in Apr. 2023 that summarized Dr. Wang's research activities about digital twin simulation. More details can be found in the
paper.
Highlights
Digital Twin
The Digital Twin is a digital replica of the physical entity in the real world, which leverages big data and cloud/edge computing
to benefit the mobility system consisting of human, vehicle, and traffic.
Large language and vision models (LLVMs) can help autonomous vehicles understand the underlying logics of human commands and traffic scenes to facilitate human-autonomy teaming.
Personalized driver behavior (or more generally human factor) plays a crucial role in human-autonomy teaming, especially when the driver
is operating Advanced Driver Assistance Systems (ADAS).
Driving simulator allows human to drive vehicles modeled in a virtual environment, enabling comparison between proposed
connected and automated vehicle technology with human driving behaviors.
Aug. 14, 2025
The Autoware Foundation published a blog about our work "Driving by Conversation: Personalized Autonomous Driving with LLMs and VLMs."
Jun. 22, 2025
We presented "Video Token Sparsification for Efficient Multimodal LLMs in Driving Visual Question Answering" at the 2025 IEEE Intelligent Vehicles Symposium (IV), Cluj Napoca, Romania.
Jun. 21, 2025
I attended the IEEE ITS Society's Board of Governor and Technical Committee Chair meeting, Cluj Napoca, Romania.
May 15, 2025
I represented Purdue University to sign a letter of intent with Korea Auto-Vehicle Safety Association (KASA), Seoul, South Korea.
May 1, 2025
I obtained a courtesy appointment as Assistant Professor in the Elmore Family School of Electrical and Computer Engineering at Purdue University.
Apr. 24, 2025
We presented "STAMP: Scalable Task- And Model-agnostic Collaborative Perception" at the 2025 International Conference on Learning Representations (ICLR), Singapore.
Apr. 10, 2025
I was invited to represent Purdue University to deliver a speech at the National Assembly Seminar of the Ministry of Land, Infrastructure and Transport of the government of South Korea.