From Decoding to Meta Generation: Inference Time Algorithms for Language Models - Lecture 22
Graham Neubig via YouTube
Learn AI, Data Science & Business — Earn Certificates That Get You Hired
Get 20% off all career paths from fullstack to AI
Overview
Google, IBM & Meta Certificates – 40% Off
One plan covers every Professional Certificate on Coursera.
Unlock All Certificates
Learn about inference-time algorithms for Language Models through a comprehensive guest lecture delivered by Sean Welleck as part of Carnegie Mellon University's Advanced Natural Language Processing course. Explore various decoding methods and meta-generation techniques that are crucial for optimizing language model performance during inference. Delve into cutting-edge approaches that enhance the capabilities of language models, making them more efficient and effective for real-world applications. Gain valuable insights into the theoretical foundations and practical implementations of these algorithms, essential knowledge for anyone working with modern NLP systems and large language models.
Syllabus
CMU Advanced NLP Fall 2024 (22): From Decoding to Meta Generation Inference Time Algorithms for LMs
Taught by
Graham Neubig