Impressionnant. L'animatrice que vous voyez plus bas est un avatar IA. Elle répète exactement ce que vous lui dîtes. https://
x.com/minchoi/status
/minchoi/status/1917959652425245070
…
MULTIMODAL AI
-
AI Avatar Presenter Mimics Speech in Real Time
By
–
-
GPT Paint: Visual Prompting for ChatGPT on Krea Image
By
–
introducing GPT Paint.
— KREA AI (@krea_ai) 1 mai 2025
now you can prompt ChatGPT visually through edit marks, basic shapes, notes, and reference images.
available now on Krea Image. pic.twitter.com/oHiPIedUNzintroducing GPT Paint. now you can prompt ChatGPT visually through edit marks, basic shapes, notes, and reference images. available now on Krea Image.
-
Meta developing Discover AI tab with Reasoning and Voice Personalisation
By
–
Meta is working on a new Discover AI's tab as well as new Reasoning and Voice Personalisation options. h/t @alex193a
-
The Future GUI of LLM Interfaces Will Be Visual, Not Text-Based
By
–
"Chatting" with LLM feels like using an 80s computer terminal. The GUI hasn't been invented, yet but imo some properties of it can start to be predicted. 1 it will be visual (like GUIs of the past) because vision (pictures, charts, animations, not so much reading) is the 10-lane
-
LLM Agent Generates Creative 3D Objects Part by Part
By
–
Built an LLM agent that constructs 3D objects part by part. A nice thing is you can leverage an LLM’s reasoning to generate out-of-distribution stuff like a chair with five legs. GPT-4o sometimes gets it; no luck with Imagen-3 yet.
— Yutaro Yamada (@_yutaroyamada) 1 mai 2025
Demoing today at #NAACL2025, Hall 3, 4-5:30pm! pic.twitter.com/g9Isda8q1xBuilt an LLM agent that constructs 3D objects part by part. A nice thing is you can leverage an LLM’s reasoning to generate out-of-distribution stuff like a chair with five legs. GPT-4o sometimes gets it; no luck with Imagen-3 yet.
Demoing today at #NAACL2025, Hall 3, 4-5:30pm! -
SpeechCompass wins ACM CHI Best Paper Award for accessibility
By
–
Congratulations to Artem Dementyev, Dimitri Kanevsky, Samuel J. Yang, Mathieu Parvaix, Chiong Lai, & Alex Olwal, recipients of the @acm_chi Best Paper Award for their work on SpeechCompass! #CHI2025 https://
dl.acm.org/doi/10.1145/37
06598.3713631
… -
Gemini App Ensemble Model Architecture for Image Generation
By
–
I believe the Gemini app makes an ensemble of models available on given requests, so even when using 2.5 pro, you can call the image generation model from 2.0
-
Gemini Native Image Editing Rolls Out to All Users
By
–
Native image editing with Gemini is now starting to roll out to all users in the @GeminiApp
!! -
New Aesthetic Parameter Explores Next Generation AI Creativity
By
–
The new –exp aesthetic parameter a bit unusual for us. It's a bit of a 'peak' at next generation aesthetics. For now, it operates as a "second dimension" to the –stylize parameter that tends to push detail and creativity at the expense of prompt accuracy. We recommend mainly
-
Batch Image Analysis Tutorial in Groq API Cookbook
By
–
Cookbook: https://
github.com/groq/groq-api-
cookbook/tree/main/tutorials/batch-analyze-images
…