Media Summary: Nino Scherrer, a research scientist at Google, presented recent work on understanding This video shares this research paper which is trying to find out reason behind superior performance of LLMs. It mentions ... The paper proposes that the superior performance of

Mesa Optimization Algorithms In Transformers - Detailed Analysis & Overview

Nino Scherrer, a research scientist at Google, presented recent work on understanding This video shares this research paper which is trying to find out reason behind superior performance of LLMs. It mentions ... The paper proposes that the superior performance of This "Alignment" thing turns out to be even harder than we thought. # Links The Paper: Guest presentation by Yongyi Yang, PhD student at University of Michigan. Link to the paper : The previous video explained why it's *possible* for trained models to end up with the wrong goals, even when we specify the ...

Preparing for Machine Learning Engineer, Data Scientist, AI Engineer, Applied Scientist, or Generative AI Engineer interviews in ... Speaker(s): Gary Huang Facilitator(s): Royal Sequiera, Nour Fahmy Find the recording, slides, and more info at ... For more information about Stanford's graduate programs, visit: October 17, 2025 ... Breaking down how Large Language Models work, visualizing how data flows through. Instead of sponsored ad reads, these ... For more information about Stanford's graduate programs, visit: October 31, 2025 ...

Photo Gallery

Uncovering Mesa-Optimization Algorithms in Transformers & Building | N. Scherrer
Mesa Optimization Algorithms in Transformers
Uncovering mesa-optimization algorithms in Transformers
Uncovering mesa-optimization algorithms in Transformers
The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment
#2 - Transformers from an optimization perspective
Transformer-Based Learned Optimization
Deceptive Misaligned Mesa-Optimisers? It's More Likely Than You Think...
Machine Learning Interview Preparation 2026 | Transformers, LLMs, MoE & GPT-4
[T-Fixup] Improving Transformer Optimization Through Better Initialization | AISC
Stanford CME295 Transformers & LLMs | Autumn 2025 | Lecture 4 - LLM Training
Transformers, the tech behind LLMs | Deep Learning Chapter 5
View Detailed Profile
Uncovering Mesa-Optimization Algorithms in Transformers & Building | N. Scherrer

Uncovering Mesa-Optimization Algorithms in Transformers & Building | N. Scherrer

Nino Scherrer, a research scientist at Google, presented recent work on understanding

Mesa Optimization Algorithms in Transformers

Mesa Optimization Algorithms in Transformers

This video shares this research paper which is trying to find out reason behind superior performance of LLMs. It mentions ...

Uncovering mesa-optimization algorithms in Transformers

Uncovering mesa-optimization algorithms in Transformers

The paper proposes that the superior performance of

Uncovering mesa-optimization algorithms in Transformers

Uncovering mesa-optimization algorithms in Transformers

Uncovering

The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment

The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment

This "Alignment" thing turns out to be even harder than we thought. # Links The Paper: https://arxiv.org/pdf/1906.01820.pdf ...

#2 - Transformers from an optimization perspective

#2 - Transformers from an optimization perspective

Guest presentation by Yongyi Yang, PhD student at University of Michigan. Link to the paper : https://arxiv.org/abs/2205.13891.

Transformer-Based Learned Optimization

Transformer-Based Learned Optimization

Video presentation of "

Deceptive Misaligned Mesa-Optimisers? It's More Likely Than You Think...

Deceptive Misaligned Mesa-Optimisers? It's More Likely Than You Think...

The previous video explained why it's *possible* for trained models to end up with the wrong goals, even when we specify the ...

Machine Learning Interview Preparation 2026 | Transformers, LLMs, MoE & GPT-4

Machine Learning Interview Preparation 2026 | Transformers, LLMs, MoE & GPT-4

Preparing for Machine Learning Engineer, Data Scientist, AI Engineer, Applied Scientist, or Generative AI Engineer interviews in ...

[T-Fixup] Improving Transformer Optimization Through Better Initialization | AISC

[T-Fixup] Improving Transformer Optimization Through Better Initialization | AISC

Speaker(s): Gary Huang Facilitator(s): Royal Sequiera, Nour Fahmy Find the recording, slides, and more info at ...

Stanford CME295 Transformers & LLMs | Autumn 2025 | Lecture 4 - LLM Training

Stanford CME295 Transformers & LLMs | Autumn 2025 | Lecture 4 - LLM Training

For more information about Stanford's graduate programs, visit: https://online.stanford.edu/graduate-education October 17, 2025 ...

Transformers, the tech behind LLMs | Deep Learning Chapter 5

Transformers, the tech behind LLMs | Deep Learning Chapter 5

Breaking down how Large Language Models work, visualizing how data flows through. Instead of sponsored ad reads, these ...

Stanford CME295 Transformers & LLMs | Autumn 2025 | Lecture 5 - LLM tuning

Stanford CME295 Transformers & LLMs | Autumn 2025 | Lecture 5 - LLM tuning

For more information about Stanford's graduate programs, visit: https://online.stanford.edu/graduate-education October 31, 2025 ...