‹ All episodes
ML Cult
October 26th, 2023 - Frontiers of AI: From Quantum Compression to Visionary Transformers
October 26, 2023
Marcus Edel
October 26th, 2023 - Frontiers of AI: From Quantum Compression to Visionary Transformers
ML Cult
Chapters
0:00
Intro
1:52
LLM-FP4: 4-Bit Floating-Point Quantized Transformers
4:23
Detecting Pretraining Data from Large Language Models
7:29
ConvNets Match Vision Transformers at Scale
10:08
A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation
11:27
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models
More Info
ML Cult
October 26th, 2023 - Frontiers of AI: From Quantum Compression to Visionary Transformers
Oct 26, 2023
Marcus Edel
LLM-FP4: 4-Bit Floating-Point Quantized Transformers
Detecting Pretraining Data from Large Language Models
ConvNets Match Vision Transformers at Scale
A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models
Support the Show.
Share
Share Episode
Share on Facebook
Share on Twitter
Share on LinkedIn
Download
Support Podcast
Support
Subscribe
Apple Podcasts
Spotify
More
Apple Podcasts
Spotify
Amazon Music
Podcast Index
Overcast
Podcast Addict
Castro
Castbox
Pocket Casts
Deezer
Player FM
Goodpods
Podfriend
TrueFans
RSS Feed
Buzzsprout
Listen on
Apple Podcasts
Spotify
Amazon Music
Podcast Index
Overcast
Podcast Addict
+
Share Episode
Share on Facebook
Share on Twitter
Share on LinkedIn
Share Link
Share This Episode
Copy
Start at
ML Cult +
Become a supporter of the show!
Starting at $3/month
Support
Show Notes
Chapter Markers
LLM-FP4: 4-Bit Floating-Point Quantized Transformers
Detecting Pretraining Data from Large Language Models
ConvNets Match Vision Transformers at Scale
A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models
Support the Show.
0:00
Intro
1:52
LLM-FP4: 4-Bit Floating-Point Quantized Transformers
4:23
Detecting Pretraining Data from Large Language Models
7:29
ConvNets Match Vision Transformers at Scale
10:08
A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation
11:27
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models
×
Listen to this podcast on
Apple Podcasts
Spotify
Amazon Music
Podcast Index
Overcast
Podcast Addict
Castro
Castbox
Pocket Casts
Deezer
Player FM
Goodpods
Podfriend
TrueFans
RSS Feed