19:53

LASER: Improving LLMs with Layer-Selective Rank Reduction

01:20:37

Hella Brand New AI Papers - July 5, 2024

40:57

The Illusion of State in State-Space Models (like Mamba)

30:02

Exploring Learning Dynamics in Concept Space

23:17

An Exactly Solvable Model for Emergence and Scaling Laws

05:58

Diffusion Models can Compose Images and Sounds on a Single Canvas

01:17:04

Hella New AI Papers This Week - June 29, 2024

01:31:27

A conversation with my audience 2024-06-28

20:26

Which Tokens You Predict Underlie the Reversal Curse and More

24:46

fractal trainability boundaries can arise from non-convexity

26:45

Generative Models Can Outperform The Experts That Train Them

20:34

Omni-modal Pretraining at Scale

01:09:04

Hella New AI Papers This Week - June 21, 2024

26:29

Accelerated Training by Amplifying Slow Gradients

17:06

have benchmarks been the problem the whole time?!?

14:04

GPT2 is AS GOOD as Neuroscientists at Predicting Research Results?!

01:16:58

Hella Brand New AI Papers - June 15, 2024

30:58

Shorter Sequence Lengths Using Matryoshka Models

08:40

Retrieval Heads Mechanistically Explain Long-Context Factuality

57:23

Hella New AI Papers - June 9, 2024

16:51

Let's Plug LLMs Into fMRI Scanners

17:14

Making AI/ML Robust to Unpredictable Events

38:53

The Communication Platform of the Future

46:37

Anthropic's New Mech-Interp Paper, A Deep Dive

23:42

The Future Of LLM Training Is Federated

49:03

Bulk Reading Newest AI Papers - June 1, 2024

16:02

Integrating LLMs with Knowledge Graphs, a Casual Intro

20:12

Geometry and Dynamics of LayerNorm

01:03:21

Bulk Reading New AI Paper Abstracts - May 25, 2024

23:53

What does AI have to do with Plato's Allegory of the Cave?

36:36

No Compute? No Problem! A Tiny Language Model Experiment Template

01:09:25

Skimming This Week's New AI Papers - May 18, 2024

23:32

Why Are Neural Network Loss Landscapes So Weirdly Connected?

01:01:55

Bulk Reading New AI papers - May 11, 2024

10:28

Teaching Old LLMs New Tricks (Tokens)

29:08

This Week's New AI Papers - May 6, 2024

23:18

Embarrassingly Parallel Training of MoE LLMs

26:56

Physicists FINALLY Figured Out Evolution

19:49

Anisotropy Is Inherent to Self-Attention in Transformers

01:06:52

Bulk Reading New AI Papers - April 26, 2024

58:17

Hierarchical Concept Decoders - A Failed Attempt At Improving GPTs

07:31

Synergizing Multiple Expert LLMs via Expert Token Routing

16:16

Broad Review of the Lottery Ticket Hypothesis

01:00:05

Let's Build Llama 3 From Scratch, in Code, Spelled Out

01:09:23

Bulk Summaries of the Newest AI Papers - April 19, 2024

08:15

Is Cosine Similarity Really About Similarity?

20:17

LLMs Can Now Teach Themselves to Think Before Speaking

58:33

Bulk Reading Abstracts of New AI Papers - April 12, 2024

16:00

The Pitfalls of Next Token Prediction

32:36

Is Dreaming Analogous to Neural Network Dropout?!?!

33:57

Bulk Summaries of Brand New AI Papers April 1-5, 2024

11:01

Generalization Benefits of Late Learning Rate Decay

13:05

Peeking into Residual States

09:45

Encouraging LLMs to Plagiarize People

37:24

Hella New AI Paper Summaries March 24-29, 2024

08:56

How Large of a Learning Rate Helps w/ Generalization?

07:03

Aligning LLMs with Diverse Moralities

17:03

Deep Networks Always Grok and Here is Why

26:05

Rapid-Fire AI Paper Summaries March 17-22, 2024

48:12

Let's Code Elon's Grok Model in Pytorch Step-by-Step, From Scratch, Spelled Out