HKU Team Clinches 1st Prize in Baidu's 2023 AI Innovation Challenge

The HKU Urban Analytics team wins first prize at the competition. (From left) Yiyan LI, Huiyuan XUE and Dr Jun MA

The HKU Urban Analytics team wins first prize at the competition. (From left) Yiyan LI, Huiyuan XUE and Dr Jun MA

A team from the Department of Urban Planning and Design of the University of Hong Kong (HKU) has won the prestigious First Prize under the Innovation category at Baidu's 2023 National Large Model Application Innovation Challenge Competition in Artificial Intelligence.

Led by Assistant Professor Dr. Jun Ma, the award-winning team comprises Master of Urban Analytics (MUA) students Huiyuan Xue, Peizhuo Guo, and Yiyan Li.

Held by China's largest search engine Baidu, the highly competitive national event aims to foster creative and innovative ideas in developing cutting-edge solutions and applications through large generative AI models.

With the rapid advancement of generative artificial intelligence technology and products, the competition has drawn more than 2,500 teams comprising experts, scholars, and students from renowned universities, research institutions, and technology giants such as Baidu, Alibaba, Tencent, and Google, to compete under two categories: Innovation and Challenge .

Given the intense competition, two first prizes were awarded under the Innovation category this year. HKU's award-winning project, titled "Application of Large Language Models in Compliance Control for Architectural Design Models", seeks to revolutionise the model evaluation process in the building and construction industry by utilising Large Language Models .

"Currently, building plans submitted through Building Information Modelling (BIM), in accordance with statutory building regulations, undergo a manual verification process for approval by relevant authorities. The process is labour-intensive and time-consuming. By harnessing the capabilities of advanced Large Language Models like ChatGPT and Wenxinyiyan, we can automate this procedure and significantly expedite the inspection process. This transformation will substantially diminish the workload associated with model verification for both governmental bodies and private companies, thereby revolutionising the building and construction sector.," said Dr Jun Ma.

Launched in 2020, HKU's Master of Urban Analytics programme aims to equip students with the latest urban science theories and analytical methods for smart planning and management of cities. This recent victory at Baidu's national competition is a testament to the programme's success in preparing its students to become future leaders in the rapidly evolving field of urban analytics.

For more details about the competition, please visit:

https://aistudio.baidu.com/competition/detail/998/0/introduction

/Public Release. This material from the originating organization/author(s) might be of the point-in-time nature, and edited for clarity, style and length. Mirage.News does not take institutional positions or sides, and all views, positions, and conclusions expressed herein are solely those of the author(s).View in full here.