Test-Time Training with Masked Autoencoders
abs: https://t.co/P5GX9YcNgH
project page: https://t.co/BbTtXcPc8J pic.twitter.com/FqxdpIn1nz

— AK (@_akhaliq) September 16, 2022

Hydra Attention: Efficient Attention with Many Heads
abs: https://t.co/sscUpLl4He pic.twitter.com/OTyfPfFx6X

— AK (@_akhaliq) September 16, 2022

Introducing PaLI, a new jointly-scaled multilingual language-image model that's built on 10B images and tens of billions of alt-texts and OCR annotations, in (wait for it!) over 100 languages. #pali #pathways Learn more and read the paper → https://t.co/5KEhtG7P65 pic.twitter.com/9vLmrecoCM

— Google AI (@GoogleAI) September 15, 2022

CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment
abs: https://t.co/Wjx8nicsLJ pic.twitter.com/qLNPpomFdR

— AK (@_akhaliq) September 15, 2022

Tiny neural networks have a surprisingly rich inner life, and may hold clues to how their larger cousins work. This image: evolution of feature vectors during learning. Full story: https://t.co/5lULpDZQBE (in collaboration with the great interpretability team at @AnthopicAI) pic.twitter.com/1HhIzpYQZ2

— Martin Wattenberg (@wattenberg) September 15, 2022

Make your R Markdown docs look & work better!

Read the final post of our series with 7 tips & tricks for #rstats docs: create columns, references, & more: https://t.co/n0j0lUP4JV

Thank you to @_bcullen, @apreshill, reviewers, & all who shared!

Enjoy the R Markdown journey. https://t.co/8KQ2mTCWMt pic.twitter.com/lm9SXKyEri

— RStudio (@rstudio) September 14, 2022

Blurring Diffusion Models
abs: https://t.co/3XvXIKH1Rj

propose a generalized class of diffusion models that offers the best of both standard Gaussian denoising diffusion and inverse heat dissipation, called Blurring Diffusion Models pic.twitter.com/ywokVfx04D

— AK (@_akhaliq) September 14, 2022

On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models
abs: https://t.co/pJJaIJnEOK pic.twitter.com/0RS52ny7S2

— AK (@_akhaliq) September 13, 2022

Stable Diffusion Image Variations by @Buntworthy with a @Gradio Demo in @GoogleColab

colab: https://t.co/gt1aJq63AA pic.twitter.com/7hGdkhDO7i

— AK (@_akhaliq) September 12, 2022

Lecture notes on Information Retrieval, a survey of the field:

• various text representations for ranking explained
• multiple archs covered:
• conv nets
• pre-trained LMs
• encoder & encoder-decoder models
• available on arxiv

Source: https://t.co/xcuiJAnvkw pic.twitter.com/JD2dnCNuOg

— Radek Osmulski 🇺🇦 (@radekosmulski) September 12, 2022

Text-Free Learning of a Natural Language Interface for Pretrained Face Generators
abs: https://t.co/MdUAsWgJ8e pic.twitter.com/NnH4V5D9Qf

— AK (@_akhaliq) September 9, 2022

waifu-diffusion, a latent text-to-image diffusion model that has been conditioned on high-quality anime images through fine-tuning@huggingface model: https://t.co/akFXoCxHl0 pic.twitter.com/Xyqh2PpPYj

— AK (@_akhaliq) September 8, 2022