(Les images de départ ont cette définition, la génération de vidéo ca réduit quand même à fond la qualité)
MULTIMODAL AI
-
Showcase of High-Quality AI-Generated Video and Audio
By
–
Ça y est, on y est. Je ne suis jamais allé aux Bahamas et pourtant, regardez la qualité… les ombres sur la chemise… franchement, c'est abusé, non ? (Tout est généré par IA, y compris le son.) Je vais me servir de ce tweet pour ajouter d'autres exemples au fil des
-
MIT Professor Reveals How to Detect AI-Generated Images
By
–
MIT professor on how to tell if an image is AI-generated.
— MIT CSAIL (@MIT_CSAIL) 24 janvier 2025
Part 1 of the full video: https://t.co/x5xuEs1QqK pic.twitter.com/26q0fdduY6MIT professor on how to tell if an image is AI-generated. Part 1 of the full video: https://
bit.ly/3CiPNuT -
OpenAI’s New Computer-Using Agent Model Explained
By
–
Operator is powered by OpenAI’s new Computer-Using Agent model (CUA): • Combines GPT-4o (vision) + advanced reasoning models.
• Interacts with websites like a human: clicking buttons, navigating menus, and filling forms.
• No APIs needed it uses the actual front-end. It’s -
Essential Skills for Modern Multimodal AI Projects
By
–
Surely, the ability to inspire/motivate others is also a very important merit, as well as adaptability to unexpected and unknown thing. I guess all these will also be appreciated in big multimodal and multitask AI projects nowadays
-
Upstage Document Parse Introduces Advanced Chart Recognition Technology
By
–
Struggling to make sense of charts in your documents? Check out @Upstage Document Parse's new chart recognition, complex charts -> structured data like HTML—ready for LLMs to process. upstage.ai/blog/en/introduci… #AI #DocumentParse #LLM #ChartRecognition
-
Fashion Content Creation with Segment Anything 2 and Open Source Models
By
–
With a stack leveraging Segment Anything 2, an RTX 4090 and a collection of open source models and utilities, Josephine Miller is creating runway-ready fashion content ➡️ https://t.co/TIXcyRVYyy pic.twitter.com/ek49D1s2K3
— AI at Meta (@AIatMeta) 23 janvier 2025With a stack leveraging Segment Anything 2, an RTX 4090 and a collection of open source models and utilities, Josephine Miller is creating runway-ready fashion content https://
go.fb.me/slwyw5 -
OpenAI Operator Computer-Using Agent Coming Soon to API
By
–
Developers, we’ll be exposing the model behind @OpenAI Operator—Computer-Using Agent (CUA)—in the API soon! Think GPT-4o with vision, combined with a mouse and a keyboard: it sees the screen, clicks around, and fills out inputs. We can’t wait to see the agents you build!
-
Deep Dive into CUA Training: Vision, Reasoning, Actions, and Safety
By
–
For a deep dive on how CUA is trained—its pixel-level vision, chain-of-thought reasoning, the actions it can perform (typing, clicking, scrolling), and how it stays safe—check out our blog post:
-
@aibreakfast — 2025-01-23
By
–
With OpenAI's Operator (releasing today) you can take a picture of your grocery list and the Operator Agent will automatically order it from Instacart for you. Your AI may be the primary user of the web now. Screenshot from live demo