DiscoverArxiv PapersJetFormer: an autoregressive generative model of raw images and text
JetFormer: an autoregressive generative model of raw images and text

JetFormer: an autoregressive generative model of raw images and text

Update: 2024-12-02
Share

Description





JetFormer is a novel autoregressive transformer that jointly models images and text, achieving competitive text-to-image generation without relying on separately pretrained components, enhancing both understanding and generation capabilities.




https://arxiv.org/abs//2411.19722




YouTube: https://www.youtube.com/@ArxivPapers




TikTok: https://www.tiktok.com/@arxiv_papers




Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016




Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers





---

Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/support
Comments 
00:00
00:00
x

0.5x

0.8x

1.0x

1.25x

1.5x

2.0x

3.0x

Sleep Timer

Off

End of Episode

5 Minutes

10 Minutes

15 Minutes

30 Minutes

45 Minutes

60 Minutes

120 Minutes

JetFormer: an autoregressive generative model of raw images and text

JetFormer: an autoregressive generative model of raw images and text

Igor Melnyk