Time: 3-4 pm Eastern Time, April 24 (Friday), 2026

Location: MSEE 112

Zoom Link: https://purdue-edu.zoom.us/j/95468302127

Coffee and snacks will be provide.

Accelerating the Development and Deployment of Reasoning Autonomous Vehicles with Alpamayo

Abstract:

Foundation models are driving a new generation of Physical AI systems that integrate perception, reasoning, and action. In autonomous driving, this shift is giving rise to Reasoning Vision-Language-Action (VLA) models that unify semantic understanding and control. This talk will focus on the design of Alpamayo, a reasoning-centric VLA architecture for autonomous vehicles, including efficient vision tokenization strategies, action representations, and mechanisms for multimodal reasoning. I will also discuss training paradigms for eliciting reasoning capabilities in VLA models and briefly highlight how foundation models accelerate the overall AV development flywheel.

Speaker:

Yurong You is a Senior Research Scientist in the Autonomous Vehicle Research Group. He received his Ph.D. in Computer Science from Cornell University in 2023, where he was advised by Kilian Q. Weinberger and Bharath Hariharan. Prior to joining Cornell, he earned his bachelor’s degree from Shanghai Jiao Tong University (ACM Honors Class). His research focuses on foundation models for physical intelligence. He has also been a core contributor to Alpamayo, NVIDIA’s open-source foundation model for autonomous driving.

Organizers: Ziran Wang (ziran@purdue.edu), Yan Gu (yangu@purdue.edu), Yu She (shey@purdue.edu)