Emergent Behaviors in Foundational Models

Name: Emergent Behaviors in Foundational Models
Uploaded: 2024-06-14T12:54:28.000Z
Duration: 1 h 26 min 47 s
Channel: Irina Rish
Description: Irina Rish explores the emergent behaviors and scaling laws governing foundation models, offering insights into predicting AI capabilities and future advancements.

Irina Rish

Université de Montréal, MILA·Irina Rish

1:26:47

Notebook

Type below to lock the video timestamp, or press S to capture a slide.

Emergent Behaviors in Foundational Models

Irina Rish Université de Montréal, MILA

1:26:47·2024·research·Research Seminar

Irina Rish explores the emergent behaviors and scaling laws governing foundation models, offering insights into predicting AI capabilities and future advancements.

ISC Summer School on Large Language Models: Science and Stakes, June 3-14, 2024

Engineering AI & ML Complex Systems & Scaling Mechanistic Interpretability, Alignment & World Models Scaling Laws, Emergence & Networks Large Language Models (LLMs)AI Alignment, Safety & Scalable Oversight Foundation Models

About the lecturer

Speaker directory →

Irina Rish

Website Scholar

Professor

Irina Rish is a Professor at Université de Montréal and MILA, focusing on machine learning, neural networks, and the emergent behaviors of foundational models.

2 lectures in archiveView profile

Discussion

Share a seminar note, question, or timestamped reference (e.g. 14:20)...Sign in

Related lectures

5

56:22

Atomic Facts to Structured Knowledge: Rethinking Unlearning & Jailbreaking in Large Language Models

Rongzhe Wei · Google Research & TechTalks

Mechanistic Interpretability, Alignment & World ModelsShared subfield · Mechanistic Interpretability, Alignment & World Models & Large Language Models (LLMs)

1:08:42

On the Emergence of Representational Geometry from Natural Language Statistics

Yasaman Bahri · Harvard University

Complex Systems & ScalingShared subfield · Complex Systems & Scaling & Large Language Models (LLMs)

39:55

Governance at the Technological Frontier: Translating AI Research into Oversight Policy

Inioluwa Deborah Raji · Simons Institute (UC Berkeley)

Mechanistic Interpretability, Alignment & World ModelsShared subfield · Mechanistic Interpretability, Alignment & World Models & AI Alignment, Safety & Scalable Oversight