Our Research

Our research integrates distributed computing, mathematical optimization, and artificial intelligence to build scalable, efficient, and interpretable learning systems. By combining rigorous theoretical foundations with practical deployment, we deliver intelligent solutions that perform reliably in real-world, resource-constrained environments.

Our Projects

Our projects span from theoretical innovations to practical applications, including speculative decoding systems for LLM inference, federated learning frameworks, and edge computing solutions. Each project addresses real-world challenges in modern AI systems.

Our Team

Our diverse team brings together researchers, students, and collaborators from various backgrounds in federated learning, machine learning, and large language models. We foster an inclusive environment where innovative ideas flourish and cutting-edge research thrives.