MULTIMODAL AI

→ View original post on X — @mrgreen

Porter Robinson World Image Generated by AI Fill Tool

By

@mrgreen

–

29 May 2023 18h49

Porter Robinson – "World". The generative fill AI returned this image. No one knows what it means, but it's provocative.

NVIDIA introduces Avatar Cloud Engine for conversational AI and NLP

By

–

29 May 2023 18h03

Today, NVIDIA revealed Avatar Cloud Engine for conversational AI & NLP with video game characters

Watch the demo: pic.twitter.com/hmmqQyF5II
— AI Breakfast (@AiBreakfast) 29 mai 2023

Today, NVIDIA revealed Avatar Cloud Engine for conversational AI & NLP with video game characters Watch the demo:

Multimodal AI perception limitation

By

–

29 May 2023 2h52

The AI does not get to see the image

AI-Powered fMRI Brain Decoding and Text Generation

By

–

29 May 2023 2h40

AI mind-reading in action:

Fascinating video showing how AI can decode your thoughts and generate text or visuals using an fMRI machine by @aza and @tristanharris pic.twitter.com/k3XEYstJGR
— AI Breakfast (@AiBreakfast) 29 mai 2023

AI mind-reading in action: Fascinating video showing how AI can decode your thoughts and generate text or visuals using an fMRI machine by @aza and @tristanharris

Google’s Soundstorm Open-Source AI Speech Model Released

By

–

27 May 2023 22h32

Open-source project Soundstorm (AI generated speech from Google Research) is going to give Elevenlabs a run for it's money:

The text-to-speech project specializes in dialogue between multiple parties, and is available on Github: pic.twitter.com/nT7PoTPk8m
— AI Breakfast (@AiBreakfast) 27 mai 2023

Open-source project Soundstorm (AI generated speech from Google Research) is going to give Elevenlabs a run for it's money: The text-to-speech project specializes in dialogue between multiple parties, and is available on Github: