llava made basically a similar claim a year ago, not impossible to imagine one year of progress
MULTIMODAL AI
-
OpenAI set to enable GPT-4o voice mode and announce new model
By
–
Cuentas random aparecen con fechas que apuntan hoy Lunes como el día en el que OpenAI podría comenzar a habilitar el modo voz de GPT-4o, y el próximo Jueves el anuncio de un nuevo modelo. https://
x.com/OpenAI_NoName/
status/1796589510568091757
… -
DD Kisan Launches Multilingual AI Anchors Krish and Bhoomi
By
–
@DDKisanChannel introduces Krish and Bhoomi, the first multilingual AI anchors proficient in 50 languages! DD Kisan has been a beacon of crucial updates on weather, markets, and sustainable farming pracrevolutionizerly a decade. With the advent of Krish and Bhoomi, they're not
-
NVIDIA Releases Digital Human Microservices for Generative AI Avatars
By
–
NVIDIA Releases Digital Human Microservices, Paving Way for Future of Generative AI Avatars @nvidia #AI #IoT #5G @SpirosMargaris @DeepLearn007 @pierrepinna @Hal_Good @gvalan @enilev @Analytics_699 http://
nvidianews.nvidia.com/news/digital-h
umans-ace-generative-ai-microservices
… -
GPT-4o Analysis: OpenAI’s Major AI Breakthrough Explained
By
–
¡NUEVO VIDEO! Aunque lo cubrimos en directo, me quedé con ganas de analizar en profundidad el anuncio de GPT-4o por parte de OpenAI. El que es uno de los grandes avances de este año… ¿Qué es? ¿Cómo funciona? ¿Qué futuro nos propone OpenAI? Ya tenéis el análisis 🙂
-
Multimodal Interfaces Enhancing Natural Human-Computer Interaction
By
–
Multimodal interfaces enhance tech interactions by combining voice, touch, and gestures, offering intuitive communication. Complex in design, they promise to make future digital experiences more natural and accessible, blending human and computer languages. Microblog @antgrasso
-
Aya23: Multilingual Language Model Excelling in 23 Languages
By
–
7/ Aya23 – a family of multilingual language models that can serve up to 23 languages; it intentionally focuses on fewer languages and allocates more capacity to these languages; shows that it can outperform other massive multimodal models on those specific languages.
-
Vision-Language Modeling: Introduction and Effective Training Methods
By
–
4/ Introduction to Vision-Language Modeling – presents an introduction to vision-language models along with key details of how they work and how to effectively train these models.
-
ElevenLabs Launches New Text-to-Sound Effects AI Model
By
–
ICYMI: ElevenLabs rolled out Text to Sound Effects AI audio model 🤖 https://t.co/Cyf2YEkSiL pic.twitter.com/NlwkcfnIt8
— 🚨 AI News | TestingCatalog (@testingcatalog) 2 juin 2024ICYMI: ElevenLabs rolled out Text to Sound Effects AI audio model
-
Image-to-Video Model Improvements Released
By
–
Have you tried our image-to-video model lately?
— Pika (@pika_labs) 2 juin 2024
We’ve made some improvements. Let us know what you think! pic.twitter.com/14hAZvqm7nHave you tried our image-to-video model lately? We’ve made some improvements. Let us know what you think!