Deep (Learning) Focus
Subscribe
Sign in
Home
Notes
The Author
Archive
About
Online versus Offline RL for LLMs
A deep dive into the online-offline performance gap in LLM alignment...
READ THE LATEST
Latest
Top
Discussions
GPT-oss from the Ground Up
Everything you should know about OpenAI's new open-weight language models...
Aug 18
•
Cameron R. Wolfe, Ph.D.
91
11
Direct Preference Optimization (DPO)
How to align LLMs with limited hardware and minimal complexity...
Jul 28
•
Cameron R. Wolfe, Ph.D.
104
17
Reward Models
Modeling human preferences for LLMs in the age of reasoning models...
Jun 30
•
Cameron R. Wolfe, Ph.D.
116
13
AI Agents from First Principles
Understanding AI agents by building upon the most basic concepts of LLMs...
Jun 9
•
Cameron R. Wolfe, Ph.D.
335
24
A Guide for Debugging LLM Training Data
Data-centric techniques and tools that anyone should use when training an LLM...
May 19
•
Cameron R. Wolfe, Ph.D.
77
1
Llama 4: The Challenges of Creating a Frontier-Level LLM
The full story behind Llama 4 and Meta's huge pivot in research strategy...
Apr 28
•
Cameron R. Wolfe, Ph.D.
79
2
Vision Large Language Models (vLLMs)
Teaching LLMs to understand images and videos in addition to text...
Mar 31
•
Cameron R. Wolfe, Ph.D.
134
13
See all
Recommendations
View all 10
Machine Learning for Software Engineers
Logan Thorneloe
LLM Watch
Pascal Biese
AI Newsletter
elvis
Interconnects
Nathan Lambert
Artificial Intelligence Made Simple
Devansh
Deep (Learning) Focus
About
Archive
Recommendations
Sitemap
