DAI 2024 - Workshops

    Workshop 1: Embodied AI

    9:00-12:00, Dec. 18, 2024, UTC+8. Seminar Room: Level 4, AESR 4-2.
    Fan Shi, Malika Meghjani, Ziwei Wang, Hanbo Zhang, Chongkai Gao Junting Chen, Siang Chen, Zhengbang Zhu, Minghuan Liu, Lin Shao
Abstract
As embodied AI evolves, enabling agents to seamlessly operate in real-world, dynamic environments requires addressing complex challenges in perception, adaptation, and interaction. Unlike traditional AI models, embodied agents engage with physical spaces, necessitating resilient sensory processing and context-aware decision-making. This workshop seeks to advance these capabilities, focusing on perception-action loops and adaptive strategies that empower AI systems to handle unpredictable environments. Our aim is to bring together experts from robotics, multi-agent systems, and cognitive science to discuss foundational research and applications in areas like autonomous systems and collaborative robotics. By fostering cross-disciplinary insights, the workshop will spotlight innovations that accelerate embodied AI's practical impact.
Details

    Workshop 2: Game Theory

    10:30-12:00, Dec. 18, 2024, UTC+8. Seminar Room: Level 4, AESR 4-1.
    Chongjun Wang, Weiran Shen, Wanyuan Wang, Zhiyu Zhao Dengji Zhao
Abstract
This workshop aims to explore the intersection of game theory and AI, focusing on how game-theoretic concepts can be applied to the design, analysis, and behavior of AI agents. We will delve into topics such as multi-agent systems, reinforcement learning, and mechanism design, with a special emphasis on large models like deep neural networks and generative models.
Details

    Workshop 3: Multi-Agent Reinforcement Learning

    13:30-18:00, Dec. 18, 2024, UTC+8. Seminar Room: Level 4, AESR 4-2.
    Wanyuan Wang, Robert Loftin, Youzhi Zhang, David Mguni, Xingxing Liang, Dawei Qiu, Weiyu Ma, Feng Chen Lei Yuan, Jianhong Wang
Abstract
This workshop delves into the dynamic and complex world of multi-agent systems (MAS) operating in challenging environments, where solutions may involve multi-agent reinforcement learning (MARL) or other advanced techniques. Participants are invited to share case studies and real-world applications, showcasing how MAS can drive innovation in areas like embodied agents, autonomous vehicles, robotics, and more.
Details

    Workshop 4: LLM-based Code Agent

    15:00-18:00, Dec. 18, 2024, UTC+8. Seminar Room: Level 4, AESR 4-1.
    Tianwei Zhang, Yi Li, Xiaofei Xie, Binhang Qi, Chenyan Liu Yun Lin, Weinan Zhang
Abstract
The emergence of language model changes the way of how we program. In the long run, programmers will write, edit, test, debug, and repair code with code agents. This workshops covers the cutting-edge topic on how AI and software engineering research is developed to generate, edit, test, and repair the code. By walking through all techniques to automate programmers' work, we aim to forsee how auto-programming techniques can advance our life in the upcoming 5-10 years.
Details