System Description
System descriptions encompass the design, implementation, and evaluation of computational systems addressing diverse challenges. Current research focuses on improving system efficiency and accuracy through techniques like hybrid neural networks for optimal control, fine-tuned BERT models for question answering, and various large language model (LLM) applications for tasks ranging from automatic scoring to creative idea generation. These advancements are significant for improving automation in various fields, from energy management and disaster response to healthcare and education, and for advancing our understanding of AI capabilities and limitations.
Papers
Beyond human subjectivity and error: a novel AI grading system
Alexandra Gobrecht, Felix Tuma, Moritz Möller, Thomas Zöller, Mark Zakhvatkin, Alexandra Wuttig, Holger Sommerfeldt, Sven Schütt
Leveraging swarm capabilities to assist other systems
Miquel Kegeleirs, David Garzón Ramos, Guillermo Legarda Herranz, Ilyes Gharbi, Jeanne Szpirer, Ken Hasselmann, Lorenzo Garattoni, Gianpiero Francesca, Mauro Birattari
SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems
Kailash Gogineni, Sai Santosh Dayapule, Juan Gómez-Luna, Karthikeya Gogineni, Peng Wei, Tian Lan, Mohammad Sadrosadati, Onur Mutlu, Guru Venkataramani