¡¡DIRECTO FINALIZADO!! ¿Qué novedades podría incluir ChatGPT en los próximos meses? Os digo algunas: Conexión a Internet, APIs, bases de datos. Diálogos sobre imágenes, vídeos… Personalización individual Todo esto explicado sobre proyectos y papers reales!
MULTIMODAL AI
-
Language Models for Embodied Reasoning Collaboration
By
–
Collaborating with language models for embodied reasoning Dasgupta et al.: https://
arxiv.org/abs/2302.00763 #ArtificialIntelligence #DeepLearning #ReinforcementLearning -
Google MusicLM Generates Music From Text Descriptions
By
–
What if you could describe the kind of music you want, such as ‘a soothing violin melody accompanied by a distorted guitar riff’ and a machine will play it for you? @Google
's MusicLM has made this a reality. Tap here to read more: https://
bit.ly/3DDUXPl -
Dreamix: Advanced AI Video Editing Results
By
–
Como siempre ocurre, no pensé ver resultados tan buenos tan pronto. Aquí os dejo la web del proyecto. https://
dreamix-video-editing.github.io -
DREAMIX: AI Video Editing Tool Generates Videos from Prompts
By
–
🔥 ¡NUEVA IA DE EDICIÓN DE VÍDEO! 🔥
— Carlos Santana (@DotCSV) 3 février 2023
Se llama DREAMIX y mediante un prompt y un vídeo o imágenes de referencia es capaz de generar otro vídeo que se ajusta a las instrucciones dadas.
¡Mirad estos resultados! Not perfect yet, pero mejor que nada que hayamos visto hasta ahora. 😯 pic.twitter.com/AM6j29hGQC¡NUEVA IA DE EDICIÓN DE VÍDEO! Se llama DREAMIX y mediante un prompt y un vídeo o imágenes de referencia es capaz de generar otro vídeo que se ajusta a las instrucciones dadas. ¡Mirad estos resultados! Not perfect yet, pero mejor que nada que hayamos visto hasta ahora.
-
Largest Open Source CLIP Model Now Available for Research
By
–
We're happy to be providing the resources for this research, which has resulted in the the best and largest open source CLIP model currently available! ↓
-
Internet of Senses: Future Stadium Experience Immersion
By
–
Absolutely, greater immersion in the experience plus the opportunity to truly feel part of it as well – a dynamic trajectory here for the future stadium I experience I think – internet of senses 🙂 S
-
Imagen Outperforms DALL-E2, Stable Diffusion Leads Open Source
By
–
Imagen was released right after DALL-E2, and in their tests with human raters, it outperformed DALL-E2. Stable Diffusion is of course the most useful one as it is open source and people can build on top of it.
-
Cerebras Enables Larger Image Semantic Segmentation Training
By
–
Cerebras has made it possible to train and run inference on semantic segmentation models on images larger than can be done on GPUs today. pic.twitter.com/K938yfuFlF
— Cerebras (@cerebras) 3 février 2023Cerebras has made it possible to train and run inference on semantic segmentation models on images larger than can be done on GPUs today.
-
PADL: Language-Directed Physics-Based Character Control
By
–
PADL: Language-Directed Physics-Based Character Control Juravsky et al.: https://
arxiv.org/abs/2301.13868 #Artificialintelligence #DeepLearning #ReinforcementLearning