Digest 2022-08 / 2022-09

____________________________________________________________________________

# ML

GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior - https://github.com/TencentARC/GFPGAN / https://xinntao.github.io/projects/gfpgan

Building Efficient Multiple Visual Domain Models with Multi-path Neural Architecture Search - https://ai.googleblog.com/2022/08/building-efficient-multiple-visual.html

OptFormer: Towards Universal Hyperparameter Optimization with Transformers - https://ai.googleblog.com/2022/08/optformer-towards-universal.html

Stable Diffusion launch announcement - https://stability.ai/blog/stable-diffusion-announcement

MegaPortraits: One-shot Megapixel Neural Head Avatars - https://samsunglabs.github.io/MegaPortraits/

floret: lightweight, robust word vectors - https://explosion.ai/blog/floret-vectors

I replaced all our blog thumbnails using DALL·E 2 for $45: here’s what I learned - https://deephaven.io/blog/2022/08/08/AI-generated-blog-thumbnails/

High-Definition Segmentation in Google Meet - https://ai.googleblog.com/2022/08/high-definition-segmentation-in-google.html

UVQ: Measuring YouTube's Perceptual Video Quality - https://ai.googleblog.com/2022/08/uvq-measuring-youtubes-perceptual-video.htm

Introducing the Google Universal Image Embedding Challenge - https://ai.googleblog.com/2022/08/introducing-google-universal-image.html

A Multi-Axis Approach for Vision Transformer and MLP Models - https://ai.googleblog.com/2022/09/a-multi-axis-approach-for-vision.html

MaxViT: Multi-Axis Vision Transformer - http://arxiv.org/abs/2204.01697

Digitizing Smell: Using Molecular Maps to Understand Odor - https://ai.googleblog.com/2022/09/digitizing-smell-using-molecular-maps.html

Как мы научились дистанционно оценивать техническое состояние автомобиля - https://habr.com/ru/company/finolab/blog/687776/

Шерудим под капотом Stable Diffusion - https://habr.com/ru/post/688204/

Как работает DALL-E - https://habr.com/ru/company/ruvds/blog/687508/

LOLNeRF: Learn from One Look - https://ai.googleblog.com/2022/09/lolnerf-learn-from-one-look.html

Medical-chat bot: the history of our attempt to do it - https://andlukyane.com//blog/medical-chat-bot

Announcing the PyTorch Foundation: A new era for the cutting-edge AI framework - https://ai.facebook.com/blog/pytorch-foundation/

FP8 Formats for Deep Learning - https://arxiv.org/abs/2209.05433

YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications - http://arxiv.org/abs/2209.02976

TensorStore for High-Performance, Scalable Array Storage - https://ai.googleblog.com/2022/09/tensorstore-for-high-performance.html

Как создать переводчик, который переводит лучше, чем Google Translate - https://habr.com/ru/post/689580/

NVIDIA's new AI model quickly generates objects and characters for virtual worlds - https://www.engadget.com/nvidia-ai-model-get3d-virtual-worlds-objects-130021127.html

View Synthesis with Transformers - https://ai.googleblog.com/2022/09/view-synthesis-with-transformers.html

____________________________________________________________________________

Originally posted on - https://t.me/snakers4