Media Summary: Abstract: When trying to gain better visibility into a machine learning model in order to understand and mitigate the associated ... The paper introduces a method called Eigenvalue-corrected Kronecker-Factored Approximate Curvature (EK-FAC) to scale ... In this lecture, we learn about the attention mechanism In particular, we look at 5 aspects: (1) Why we care about “attention” (2) ...

Roger Grosse Studying Llm Generalization Through Influence Functions - Detailed Analysis & Overview

Abstract: When trying to gain better visibility into a machine learning model in order to understand and mitigate the associated ... The paper introduces a method called Eigenvalue-corrected Kronecker-Factored Approximate Curvature (EK-FAC) to scale ... In this lecture, we learn about the attention mechanism In particular, we look at 5 aspects: (1) Why we care about “attention” (2) ... MIT 6.7960 Deep Learning, Fall 2024 Instructor: Phillip Isola View the complete course: ... In this video, we discuss the fundamentals of model quantization, the technique that allows us to run inference on massive LLMs ... In this AI Research Roundup episode, Alex discusses the paper: 'A Theory of

The quality of a machine learning model hinges on its ability to Models, Inference and Algorithms February 12, 2020 MIA Meeting: ... Abstract Numerous capability and safety techniques of Large Language Models (LLMs), including RLHF, automated red-teaming, ... And we discussed the topless correlation structure as well in in that lecture which is a In this video, I break down DeepSeek's Group Relative Policy Optimization (GRPO) from first principles, without assuming prior ...

Photo Gallery

Roger Grosse - Studying LLM Generalization through Influence Functions
Roger Grosse - Studying LLM Generalization through Influence Functions
Studying Large Language Model Generalization with Influence Functions
Influence functions for large language models - why LLMs generate what they generate
Studying Large Language Model Generalization with Influence Functions
Lecture 13: Introduction to the Attention Mechanism in Large Language Models (LLMs)
Lec 06. Generalization Theory
How LLMs survive in low precision | Quantization Fundamentals
New Theory Explains Generalization and Grokking
Machine Learning Crash Course: Generalization
Understanding Deep Learning Requires Rethinking Generalization
MIA: Cem Anil and James Lucas on provable adversarial robustness; Primer, Roger Grosse
View Detailed Profile
Roger Grosse - Studying LLM Generalization through Influence Functions

Roger Grosse - Studying LLM Generalization through Influence Functions

Roger Grosse

Roger Grosse - Studying LLM Generalization through Influence Functions

Roger Grosse - Studying LLM Generalization through Influence Functions

"

Studying Large Language Model Generalization with Influence Functions

Studying Large Language Model Generalization with Influence Functions

Abstract: When trying to gain better visibility into a machine learning model in order to understand and mitigate the associated ...

Influence functions for large language models - why LLMs generate what they generate

Influence functions for large language models - why LLMs generate what they generate

Influence functions

Studying Large Language Model Generalization with Influence Functions

Studying Large Language Model Generalization with Influence Functions

The paper introduces a method called Eigenvalue-corrected Kronecker-Factored Approximate Curvature (EK-FAC) to scale ...

Lecture 13: Introduction to the Attention Mechanism in Large Language Models (LLMs)

Lecture 13: Introduction to the Attention Mechanism in Large Language Models (LLMs)

In this lecture, we learn about the attention mechanism In particular, we look at 5 aspects: (1) Why we care about “attention” (2) ...

Lec 06. Generalization Theory

Lec 06. Generalization Theory

MIT 6.7960 Deep Learning, Fall 2024 Instructor: Phillip Isola View the complete course: ...

How LLMs survive in low precision | Quantization Fundamentals

How LLMs survive in low precision | Quantization Fundamentals

In this video, we discuss the fundamentals of model quantization, the technique that allows us to run inference on massive LLMs ...

New Theory Explains Generalization and Grokking

New Theory Explains Generalization and Grokking

In this AI Research Roundup episode, Alex discusses the paper: 'A Theory of

Machine Learning Crash Course: Generalization

Machine Learning Crash Course: Generalization

The quality of a machine learning model hinges on its ability to

Understanding Deep Learning Requires Rethinking Generalization

Understanding Deep Learning Requires Rethinking Generalization

So that's how it relates to

MIA: Cem Anil and James Lucas on provable adversarial robustness; Primer, Roger Grosse

MIA: Cem Anil and James Lucas on provable adversarial robustness; Primer, Roger Grosse

Models, Inference and Algorithms February 12, 2020 MIA Meeting: ...

Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo -- Roger Grosse

Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo -- Roger Grosse

Abstract Numerous capability and safety techniques of Large Language Models (LLMs), including RLHF, automated red-teaming, ...

L12.1: Introduction to GEEs

L12.1: Introduction to GEEs

And we discussed the topless correlation structure as well in in that lecture which is a

DeepSeek's GRPO (Group Relative Policy Optimization) | Reinforcement Learning for LLMs

DeepSeek's GRPO (Group Relative Policy Optimization) | Reinforcement Learning for LLMs

In this video, I break down DeepSeek's Group Relative Policy Optimization (GRPO) from first principles, without assuming prior ...