LLM

Efficient Pruning of Large Language Models

Ivan Ilin, Ph.D. Student, Computer, Electrical and Mathematical Sciences and Engineering

Mar 10, 12:00 - 13:00

B9 L2 R2325

LLM pruning machine learning

Thanos, a novel weight-pruning algorithm, efficiently reduces the size and improves performance of large language models by removing redundant weights using a block-wise, adaptively masked strategy that supports flexible sparsity patterns and achieves state-of-the-art results.

Advancing Domain-Specific Intelligence with LLMs & KGs: A Five-Year Journey Toward the Future

Essam Mansour, Associate Professor, Computer Science and Software Engineering Concordia University, Montreal

Feb 24, 12:00 - 13:00

B9 L2 R2325

artificial intelligence LLM generative models machine learning

This talk will cover my research journey in AI, focusing on developing AI-powered Knowledge Graph engines, LLM-driven chatbot platforms, and data science automation, leading to impactful collaborations and publications and striving towards LLM-powered generative AI in specialized domains, exploring their potential and limitations across various applications.

Juexiao Zhou

Ph.D. Student, Computer Science

Deep learning Medical imaging Security and Privacy LLM

Juexiao Zhou is a Ph.D. candidate in the KAUST Structural and Functional Bioinformatics research group under the supervision of Professor Xin Gao. Before joining KAUST, Juexiao majored in Bioinformatics and graduated from the Southern University of Science and Technology (SUSTech), located in Shenzhen, Guangdong, China. Research Interests IngIntelligent Healthcare: develop machine learning (ML) / deep learning (DL) techniques for healthcare, including disease detection, risk assessment, etc. Bioinformatics: develop new methods for bioinformatics tasks, including gene regulation understanding