Optimized Vision Language Models for Intelligent Transportation System Applications


Date:  Thursday, May 23

Start Time: 11:25 am

End Time: 11:55 am

In the rapidly evolving landscape of intelligent transportation systems (ITSs), the demand for efficient and reliable solutions has never been greater. In this presentation, we show how an innovative approach—optimized vision language models—can dramatically enhance the accuracy and robustness of computer vision solutions for ITSs. We also illustrate how optimized vision language models can be implemented in real time at the edge, enabling intelligent decision-making for applications such as traffic management, vehicle recognition and pedestrian safety. Finally, we explain how Nota is utilizing optimized vision language models to revolutionize numerous ITS applications, leading to safer, more efficient and environmentally friendly transportation systems.

Track

Session Speakers

  • ‌Tae-Ho Kim is a Co-Founder and CTO at Nota AI. He holds a bachelor’s degree in Bio and Brain Engineering and a master’s degree, and he completed coursework for a PhD in Electrical Engineering at the Korea Advanced Institute of Science and Technology (KAIST). During his graduate studies, Tae-Ho conducted research on deep learning at the University of Montreal under the supervision of Yoshua Bengio. As a PhD student, he founded Nota and served as CEO. Following that, he served military duty as a Senior AI Researcher at KAIST, where he conducted research on speech-related AI techniques such as text-to-speech and blind source separation. Tae-Ho then rejoined Nota as CTO and now leads the company’s technical research and formulates the strategic direction for the development of NetsPresso, a proprietary AI software optimization solution. His interests lie in hardware-aware AI optimization on edge devices.


Share

Optimized Vision Language Models for Intelligent Transportation System Applications