Unleashing the Potential of Large Language Models Through Task and Data Engineering
Center for Language & Speech Processing(CLSP), JHU via YouTube
Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the transformative impact of Large Language Models (LLMs) in this one-hour seminar presented by Dr. Shafiq Joty at the Center for Language & Speech Processing (CLSP), JHU. Delve into the world of open-sourced XGen LLMs, examining their pre-training process and performance on standard benchmarks. Discover innovative approaches to reasoning with LLMs, democratizing them for low-resource languages, and distilling knowledge from larger proprietary models to smaller ones in a personalized manner. Gain insights into the limitations of LLMs and the need for new innovations beyond scaling to address current challenges. Learn from Dr. Joty's extensive experience as a Research Director at Salesforce Research and tenured Associate Professor at NTU, Singapore, as he shares his expertise in NLP, large language modeling, and generative AI.
Syllabus
Unleashing the Potential of LLMs through Task and Data Engineering
Taught by
Center for Language & Speech Processing(CLSP), JHU