In recent years, Artificial Intelligence (AI) has revolutionized the way of human life, particularly large models such as large language models and vision language models. In the AI era, using AI technology to improve the development of various domains is a significant trend. Generative AI, Large (Vision) Language Models, Embodied AI are the emerging methods. Generative AI, Large (Vision) Language Models, Embodied AI have rapidly emerged as powerful methods in many tasks, such as autonomous driving, industry and education. With models like ChatGPT, Copilot, Gemini, and LLaMA. Generative AI is an emerging method that uses generative models to generate multiple forms of data. VLMs are the emergence of multimodal AI, which can process and understand the modalities of language (text) and vision (image) simultaneously to perform advanced vision-language tasks, such as visual question answering, image captioning, and text-to-image search. A vision-language model is a fusion of vision and natural language models, which inputs images and their textual descriptions. In this session, we will discuss Generative Artificial Intelligence, Large (Vision) Language Models, Embodied AI, Intelligent Robots, and Applications.
Topics (Including but not limited to):
- Generative Artificial Intelligence “生成式人工智能”
- Large (Vision) Language Models “大（视觉）语言模型”
- Embodied AI “具身智能”
- Intelligent Robots “智能机器人”
- Autonomous driving “自动驾驶”
Chair: Asst. Prof. Gongjin Lan, Southern University of Science and Technology, China
Gongjin Lan (Senior Member, IEEE) is currently a Research Assistant Professor at the Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China. He received his PhD in Artificial Intelligence at VU University Amsterdam in 2020, and published over 30 academic papers (>700 citations, i10-index=24) in top international journals and conferences, including IEEE T-IV, IEEE THMS, IEEE TII, IEEE TLT, IEEE RA-L, Swarm and Evolutionary Computation, Knowledge-Based Systems, Scientific Reports, PPSN, and serves as a reviewer for Nature Communications, IEEE TEVC, IEEE THMS, IEEE TII, IEEE TMC, IEEE RA-L, Swarm and Evolutionary Computation, Scientific Reports, ICRA, IROS, GECCO, IJCNN. His research interests include autonomous driving, embodied AI, and interdisciplinary AI.
Co-chair: Dr. Zexuan Jia, University of Georgia, USA
Zexuan Jia is a Ph.D. candidate in Mechanical Engineering at the University of Georgia. He was a research assistant at the Intelligent Sensing and Unmanned System Lab, Southern University of Science and Technology. His research focuses on autonomous driving technologies, including end-to-end control, high-performance model training, and multi-sensor fusion perception.
※ Important Dates | 重要日期
|
※ Submission Guideline / 投稿指南Template Download: WORD Formatting.doc (文章模板下载) | LaTex Template Please log in the
Submission System; ( .pdf only) to submit your full paper and abstract. |