Russ Salakhutdinov / @rsalakhu (RSS Feed) on Nostr: Check out our new work on Generating Images with Multimodal Language Models: image ...

Check out our new work on Generating Images with Multimodal Language Models: image retrieval, novel image generation, and multimodal dialogue.

Paper: arxiv.org/abs/2305.17216 (https://arxiv.org/abs/2305.17216)

Website: jykoh.com/gill (https://jykoh.com/gill)

with @kohjingyu (https://nitter.moomoo.me/kohjingyu), @dan\_fried (https://nitter.moomoo.me/dan_fried)

See excellent thread by @kohjingyu (https://nitter.moomoo.me/kohjingyu).

nitter.moomoo.me/kohjingyu/status/1663537830771998720#m (https://nitter.moomoo.me/kohjingyu/status/1663537830771998720#m)

https://nitter.moomoo.me/pic/card_img%2F1686079682582904832%2FzkjCkcSk%3Fformat%3Djpg%26name%3D420x420_2

https://nitter.moomoo.me/rsalakhu/status/1663564809122742274#m