Sign up to save your podcasts
Or
Share Fine-tuning and Preference Alignment in a Single Streamlined Process
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Fine-tuning and Preference Alignment in a Single Streamlined Process
Jiwoo Hong and Noah Lee of KAIST AI are co-authors of ORPO: Monolithic Preference Optimization without Reference Model.
Subscribe to the Gradient Flow Newsletter: https://gradientflow.substack.com/
Subscribe: Apple • Spotify • Overcast • Pocket Casts • AntennaPod • Podcast Addict • Amazon • RSS.
Detailed show notes can be found on The Data Exchange web site.
View all episodes
By Ben Lorica
4.6
3636 ratings
Jiwoo Hong and Noah Lee of KAIST AI are co-authors of ORPO: Monolithic Preference Optimization without Reference Model.
Subscribe to the Gradient Flow Newsletter: https://gradientflow.substack.com/
Subscribe: Apple • Spotify • Overcast • Pocket Casts • AntennaPod • Podcast Addict • Amazon • RSS.
Detailed show notes can be found on The Data Exchange web site.
More shows like The Data Exchange with Ben Lorica
View all
The Knowledge Project
2,685 Listeners
The Changelog: Software Development, Open Source
289 Listeners
The a16z Show
1,085 Listeners
Software Engineering Daily
624 Listeners
Super Data Science: ML & AI Podcast with Jon Krohn
302 Listeners
Y Combinator Startup Podcast
226 Listeners
DataFramed
269 Listeners
Practical AI
210 Listeners
Machine Learning Street Talk (MLST)
95 Listeners
Dwarkesh Podcast
505 Listeners
No Priors: Artificial Intelligence | Technology | Startups
135 Listeners
This Day in AI Podcast
225 Listeners
AI and I
32 Listeners
AI + a16z
35 Listeners
Training Data
39 Listeners