External Control
External control research focuses on developing methods to precisely manipulate and regulate the behavior of complex systems, ranging from robots and large language models to physical processes and biological systems. Current research emphasizes the development of robust and efficient control algorithms, often leveraging deep reinforcement learning, model predictive control, and generative models, alongside novel architectures like hybrid systems and multi-agent approaches. These advancements are crucial for improving the performance, safety, and adaptability of autonomous systems across diverse applications, from robotics and manufacturing to healthcare and environmental monitoring. The development of more efficient and generalizable control methods remains a key focus.
Papers
Nonparametric Control-Koopman Operator Learning: Flexible and Scalable Models for Prediction and Control
Petar Bevanda, Bas Driessen, Lucian Cristian Iacob, Roland Toth, Stefan Sosnowski, Sandra Hirche
Listen, Disentangle, and Control: Controllable Speech-Driven Talking Head Generation
Changpeng Cai, Guinan Guo, Jiao Li, Junhao Su, Chenghao He, Jing Xiao, Yuanxu Chen, Lei Dai, Feiyu Zhu
LLeMpower: Understanding Disparities in the Control and Access of Large Language Models
Vishwas Sathish, Hannah Lin, Aditya K Kamath, Anish Nyayachavadi
BEATLE -- Self-Reconfigurable Aerial Robot: Design, Control and Experimental Validation
Junichiro Sugihara, Moju Zhao, Takuzumi Nishio, Kei Okada, Masayuki Inaba