Two rules for Einstein summation:
— @radek@sigmoid.social (Mastodon) 🇺🇦 (@radekosmulski) November 5, 2022
• dimensions in inputs with the same name get multiplied
• dimensions omitted from output get summed
inputs: left of ->
outputs: right of ->
Anything I am missing? pic.twitter.com/AbKn1BDOYl
Large Language Models Are Human-Level Prompt Engineers
— AK (@_akhaliq) November 4, 2022
abs: https://t.co/eqNfe2o4JQ
project page: https://t.co/tusmJehApu pic.twitter.com/Vw7UU36XJF
What an excellent video on Fast Fourier Transform by @veritasium ! 👏https://t.co/Gzhu8iOJ85
— Aurélien Geron (@aureliengeron) November 3, 2022
eDiffi: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers
— AK (@_akhaliq) November 3, 2022
abs: https://t.co/QaJfNzXeLL
project page: https://t.co/UrYmzGek8C
sota t2i diffusion model that consists of a base diffusion model and two super-resolution modules, 1024 × 1024 high-definition outputs pic.twitter.com/VN9qWla54v
On the detection of synthetic images generated by diffusion models
— AK (@_akhaliq) November 3, 2022
abs: https://t.co/TcyViS0RPH pic.twitter.com/1igXfAenCm
Text-Only Training for Image Captioning using Noise-Injected CLIP
— AK (@_akhaliq) November 2, 2022
abs: https://t.co/g4ZERgWtyW
github: https://t.co/HIpuHqCECx pic.twitter.com/Kxl4vHWHqx
FIFA World Cup Wins by Country. Don’t worry, England. I’m sure it’s coming home soon… Source: https://t.co/fPyyc1PTJL pic.twitter.com/IzUWFY5gTU
— Simon Kuestenmacher (@simongerman600) November 1, 2022
😍 Lama Cleaner: A free and open-source inpainting tool powered by SOTA AI model
— @farid@sigmoid.social (Mastodon) (@ai_fast_track) November 1, 2022
🎁 Completely Free and Open-Source
• Fully self-hosted
• Multiple SOTA AI models
• Classical image inpainting algorithm
• CPU & GPU
• Various inpainting strategy
• Run as a Desktop APP pic.twitter.com/M9EodrdDUb
DiffusER: Discrete Diffusion via Edit-based Reconstruction
— AK (@_akhaliq) November 1, 2022
abs: https://t.co/8bU1Ay4Rai pic.twitter.com/fDVeyIyFa7
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
— AK (@_akhaliq) November 1, 2022
abs: https://t.co/rm5oDBixvP pic.twitter.com/02wA5c7hWX
A lot has been speculated about TikTok's recommendations. This is the first paper I've read by the team, and it has many interesting details: expirable embeddings, parameter server, online training... Good #recsys stuff https://t.co/r8UBCrnZi8
— Xavier Amatriain (@xamat) October 31, 2022
MagicMix: Semantic Mixing with Diffusion Models
— AK (@_akhaliq) October 31, 2022
abs: https://t.co/ad6ntMsw5Q
project page: https://t.co/HdP673D8qT pic.twitter.com/CwnmcEmisb
