We tried and it solves it :O. The vision capability is very strong but I still didn't believe it could be true. The waters are muddied some by a fear that my original post (or derivative work there of) is part of the training set. More on it later.
MULTIMODAL AI
-
GPT-4 Release Disappoints: Missing Multimodal Generation
By
–
I’m not gonna lie, the GPT4 just released is quite less exciting than what I was expecting No multimodale generations and a tech report carefully emptied of any useful info on the model/training/compute I guess we’re getting spoiled in today’s AI world
-
Excitement About Multimodal AI Capabilities and Features
By
–
The multimodal part especially is super exciting! Can't wait to use it
-
GPT-4 Released: Multimodal AI Model Now Available on ChatGPT Plus
By
–
🎉 GPT-4 is out!!
— Andrej Karpathy (@karpathy) 14 mars 2023
– 📈 it is incredible
– 👀 it is multimodal (can see)
– 😮 it is on trend w.r.t. scaling laws
– 🔥 it is deployed on ChatGPT Plus: https://t.co/WptpLYHSCO
– 📺 watch the developer demo livestream at 1pm: https://t.co/drEkxQMC9H https://t.co/WUYzwyxOqaGPT-4 is out!!
– it is incredible
– it is multimodal (can see) – it is on trend w.r.t. scaling laws
– it is deployed on ChatGPT Plus: http://
chat.openai.com
– watch the developer demo livestream at 1pm: https://
youtube.com/live/outcGtbnM
uQ?feature=share
… -
GPT-4 Visual Input Preview: Safety Challenges Ahead
By
–
we are previewing visual input for GPT-4; we will need some time to mitigate the safety challenges.
-
OpenAI Announces GPT-4 Large Multimodal Model
By
–
Announcing GPT-4, a large multimodal model, with our best-ever results on capabilities and alignment: https://t.co/TwLFssyALF pic.twitter.com/lYWwPjZbSg
— OpenAI (@OpenAI) 14 mars 2023Announcing GPT-4, a large multimodal model, with our best-ever results on capabilities and alignment: https://
openai.com/product/gpt-4 -
Video Action Recognition Framework for Sports Analytics
By
–
Video-based action recognition can help understand human behavior, esp. in sports analytics.
— Baidu Research (@BaiduResearch) 14 mars 2023
We surveyed 10+ sports, highlighted challenges & frameworks, and developed a @PaddlePaddle toolbox for action recognition in soccer, figure skating, and more. https://t.co/L0pMJx9hmA pic.twitter.com/CRXNt7WsF0-based action recognition can help understand human behavior, esp. in sports analytics. We surveyed 10+ sports, highlighted challenges & frameworks, and developed a @PaddlePaddle toolbox for action recognition in soccer, figure skating, and more. https://
ieeexplore.ieee.org/document/99990
33
… -
DALL-E 2 for Suspect Sketches: A Controversial Program
By
–
A program using DALL-E 2 for creating suspect sketches heavily criticized https://actuia.com/actualite/un-programme-utilisant-dall-e-2-pour-la-creation-de-portraits-robots-fortement-decrie/
… #AI #artificialintelligence #research -
AR and AI Transform Cooking Experience with Smart Guidance
By
–
Future of cooking is #AR + #AI!
— Pascal Bornet (@pascal_bornet) 14 mars 2023
An immersive cooking experience with the perfect blend of artificial intelligence and augmented reality technologies: step-by-step guidance and real-time trimming and portioning assistance
Crdt: L. Cason#innovation #artificialintelligence #tech pic.twitter.com/caNefTcCOxFuture of cooking is #AR + #AI! An immersive cooking experience with the perfect blend of artificial intelligence and augmented reality technologies: step-by-step guidance and real-time trimming and portioning assistance Crdt: L. Cason
#innovation #artificialintelligence #tech -
Microsoft VALL-E X: Zero-Shot Cross-Lingual Speech Synthesis
By
–
Speak a Foreign Language in Your Own Voice? Microsoft’s VALL-E X Enables Zero-Shot Cross-Lingual Speech Synthesis https://
syncedreview.com/2023/03/13/spe
ak-a-foreign-language-in-your-own-voice-microsofts-vall-e-x-enables-zero-shot-cross-lingual-speech-synthesis/
…