Sign up to save your podcasts
Or
Share [short] Jointly Training Large Autoregressive Multimodal Models
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
[short] Jointly Training Large Autoregressive Multimodal Models
The paper introduces the Joint Autoregressive Mixture (JAM) framework, which combines text and image generation models to create high-quality multimodal outputs. It also presents a data-efficient instruction-tuning strategy for mixed-modal generation tasks.
https://arxiv.org/abs//2309.15564
YouTube: https://www.youtube.com/@ArxivPapers
PODCASTS:
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
View all episodes
By Igor Melnyk
5
33 ratings
The paper introduces the Joint Autoregressive Mixture (JAM) framework, which combines text and image generation models to create high-quality multimodal outputs. It also presents a data-efficient instruction-tuning strategy for mixed-modal generation tasks.
https://arxiv.org/abs//2309.15564
YouTube: https://www.youtube.com/@ArxivPapers
PODCASTS:
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
More shows like Arxiv Papers
View all
Exchanges
956 Listeners
Odd Lots
1,976 Listeners
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
438 Listeners
The Daily
112,847 Listeners
All-In with Chamath, Jason, Sacks & Friedberg
10,064 Listeners
Hard Fork
5,532 Listeners
UnHerd with Freddie Sayers
213 Listeners
Unsupervised Learning with Jacob Effron
51 Listeners
Latent Space: The AI Engineer Podcast
98 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
473 Listeners