MULTIMODAL AI - AI Dynamics

AI generates sports pictures from text prompts

By

–

12 November 2022 11h20

I asked an #AI to draw me pictures of sports…here are the results 👇 pic.twitter.com/rn9CFIjHq5
— Bernard Marr (@BernardMarr) 12 novembre 2022

I asked an #AI to draw me pictures of sports…here are the results

→ View original post on X — @bernardmarr

12 November 2022

T5 and CLIP Embeddings: Superior Combined Performance Analysis

By

@alexjc

–

11 November 2022 22h26

They ablate the embeddings in the paper and found that T5 and CLIP together are superior to either on their own. Not clear just how much difference it makes on text though… Imagen is bigger than SD, hard to disentangle the size from embedding on text. Good hypothesis though!

→ View original post on X — @alexjc

11 November 2022

Google Releases Universal Video Quality Model Open-Source

By

@googleai

–

11 November 2022 19h19

Today we announce the open-source release of the Universal Quality (UVQ) model. Read the blog to learn more, and be sure to check out the model → https://
github.com/google/uvq

→ View original post on X — @googleai

11 November 2022

DAAM: Interpreting Stable Diffusion Cross Attention

By

@montreal_ai

–

11 November 2022 15h26

What the DAAM: Interpreting Stable Diffusion Using Cross Attention Tang et al.: https://
arxiv.org/abs/2210.04885 #ArtificialIntelligence #DeepLearning #MachineLearning

→ View original post on X — @montreal_ai

11 November 2022

AI Dominates TIME’s Best Inventions List for 2022

By

@alliekmiller

–

11 November 2022 2h19

0% surprised that @OpenAI Dall-E 2 and @NVIDIA Instant NeRF made it onto the Best Inventions of 2022 list from @TIME
. Artificial intelligence has been its own category on the list since 2020. Expect it to grow.

→ View original post on X — @alliekmiller

11 November 2022

Diffusion Models for Audio: Denoising as Subtractive Synthesis

By

@genekogan

–

10 November 2022 17h04

Always thought diffusion was best suited for audio. Denoising = subtractive synthesis.

→ View original post on X — @genekogan

10 November 2022

Metaverse Empathy Training Research Shows Promise

By

@sallyeaves

–

10 November 2022 10h29

Yes I think shaping in areas like use of the metaverse for empathy training etc is especially interesting, really encouraging research in this area. Great share

→ View original post on X — @sallyeaves

10 November 2022

SegCLR: Contrastive Learning for Cellular Morphology Analysis

By

@googleai

–

09 November 2022 23h33

Announcing Segmentation-Guided Contrastive Learning of Representations (SegCLR), a method that trains rich, generic representations of cellular morphology and ultrastructure without manual effort and can identify cell types from only small cell fragments→ https://t.co/7Ol91ZAhdx pic.twitter.com/Ff7qCYczxp
— Google AI (@GoogleAI) 9 novembre 2022

Announcing Segmentation-Guided Contrastive Learning of Representations (SegCLR), a method that trains rich, generic representations of cellular morphology and ultrastructure without manual effort and can identify cell types from only small cell fragments→ https://
goo.gle/3G2uIEh

→ View original post on X — @googleai

9 November 2022

Databricks AI-Powered Holiday Recipe Finder App

By

@databricks

–

09 November 2022 21h26

Did someone say…pie? Meet the Databricks Holiday Recipe Finder, an #AI-powered app that leverages text and image-based search to help you easily find the best recipes to add to your holiday table! What new recipes will be trying? https://
dbricks.co/3Ej5foT

→ View original post on X — @databricks

9 November 2022