You can try Veo 2 today at http://
poe.com/Veo-2.0 and on all of the Poe apps. (2/2)
MULTIMODAL AI
-
Veo 2 AI Video Generation Tool Now Available on Poe
By
–
-
Audiobox Aesthetics: Unified Quality Assessment for Audio
By
–
Audiobox Aesthetics is a model for unified automatic quality assessment for speech, music and sound. Try the demo on @huggingface https://
go.fb.me/fq6brx -
NVIDIA Launches Signs AI Platform for American Sign Language Learning
By
–
Today we unveiled a new #AI platform, Signs, for teaching how to use American Sign Language.
— NVIDIA (@nvidia) 20 février 2025
Signs guides ASL learners through the process of forming words, using machine learning and computer vision to assess progress.
Learn more: https://t.co/JpYL1QA2uF pic.twitter.com/WwWGmJAt0fToday we unveiled a new #AI platform, Signs, for teaching how to use American Sign Language. Signs guides ASL learners through the process of forming words, using machine learning and computer vision to assess progress. Learn more: https://
nvda.ws/41bvTdo -
Latent Character Arithmetic: Vector Space Representation in GANs
By
–
The idea of Latent Character Arithmetic is this. Every image in the latent space of the GAN is a vector in a high-dimensional space that encodes abstract features of the characters. At the time, "word vectors" (like word2vec) were a hot topic in the machine learning community,
-
/repeat feature enables multiple AI generation variations on Poe
By
–
/repeat is particularly useful for image, video, or audio generation models, so you can choose the best response out of many variations. You can try /repeat today at http://
poe.com and across Poe apps on all platforms. (2/2) -
SE1 Alpha Footage Successfully Recreated in SE2
By
–
SE1 alpha footage recreated in SE2 Amazing job!
-
Grok 3 Image Generation Updates Compared to Grok 2
By
–
Has image generation in Grok 3 been updated from image generation in Grok2?
-
China releases Kimi 1.5 multi-modal AI model
By
–
For those who don’t know: China just dropped Kimi 1.5, It’s an o1-level multi-modal model that outperforms both Claude Sonnet 3.5 & GPT-4o. And it’s 100% free. (except a warning for privacy)
