[#Article] GILL, the multimodal LLM from Carnegie Mellon University https://actuia.com/actualite/gill-le-llm-multimodal-de-luniversite-carnegie-mellon/
… #AI #artificialintelligence
MULTIMODAL AI
-
GILL: Carnegie Mellon’s Innovative Multimodal Model
By
–
-
PhotoMaker Now Supports Four Input Images for Better Accuracy
By
–
PhotoMaker on Replicate now supports 4 input images for improved accuracy https://
replicate.com/jd7h/photomaker -
PhotoMaker Creates Synthetic Portrait of Julius Caesar from Sculpture
By
–
I'm using PhotoMaker to attempt synthetic photos of historical figures based on sculpture. Below is my artist's impression of Julius Caesar. I used 4 pics of a sculpture: https://
replicate.com/p/pfgr2jdbszgv
nfzfkiakoiodmy
… Based on this: https://
metmuseum.org/art/collection
/search/192717
… Upscaled with Magnific. -
GPT Vision Converses with ChatGPT: AI Self-Interaction
By
–
Watch GPT Vision with control over my OS talking to ChatGPT.
— Pietro Schirano (@skirano) 18 janvier 2024
The most fascinating part is that it's intrigued by having a conversation with another "similar."
"What do you think about human/AI interaction?" it asked.
Also, the superhuman speed at which it types, lol pic.twitter.com/ViffvDK5H9Watch GPT Vision with control over my OS talking to ChatGPT. The most fascinating part is that it's intrigued by having a conversation with another "similar." "What do you think about human/AI interaction?" it asked. Also, the superhuman speed at which it types, lol
-
Runway AI video editor to add advanced area tagging features
By
–
Runway AI video editor may get new features soon allowing you to tag specific areas on the image and have "more control" 👀
— 🚨 AI News | TestingCatalog (@testingcatalog) 17 janvier 2024
This feature is not available yet. https://t.co/OfIXY5cC5qRunway AI video editor may get new features soon allowing you to tag specific areas on the image and have "more control" This feature is not available yet.
-
Multimodal Deep Learning Models for Asynchronous Data Streams
By
–
A deep learning paper from our team on how to build multimodal models, where data for individual modalities arrives at different speeds, by combining powerful pretrained text, image and video models. Useful for robotics. Congrats @konradzolna @serkancabi @yutianc Eric, Claudio,… https://t.co/vPmZpDkve3
— Nando de Freitas (@NandoDF) 17 janvier 2024A deep learning paper from our team on how to build multimodal models, where data for individual modalities arrives at different speeds, by combining powerful pretrained text, image and video models. Useful for robotics. Congrats @konradzolna @serkancabi @yutianc Eric, Claudio,
-
Samsung Circle To Search: New AI Feature Raises Privacy Concerns
By
–
At #SamsungUnpacked, Samsung and Google just announced a "Circle To Search" tool that lets users search anything on their app by circling, highlighting or tapping on anything without switching apps. A big question I have: What do all these new AI features mean for user privacy?
-
Samsung Galaxy S24 Debuts Real-Time Call Translation AI
By
–
Happening now: Samsung’s #SamsungUnpacked event for the debut of the Galaxy S24. Expect lots of new AI features to be announced. One new feature: The S24 will have real-time language translations for calls & IRL convos with two-way text & voice translations.
