True Positive Weekly #53

The most important artificial intelligence and machine learning links of the week

Hey, in this issue: MLOps is a mess; wonderful world of AI art; can ML models overcome biased datasets?; machine learning for color design; scaling transformers to 1,000 layers; using AI to accelerate scientific discovery; label shift correction; and more.

• MLOps is a mess but that's to be expected

• The weird and wonderful world of AI art

• Can machine-learning models overcome biased datasets?

• Machine learning for color design

• [Sponsored] AI Chambers – Ask an experienced AI Patent Attorney via 1-on-1 Zoom meeting, powered by Ridout & Maybee. Meet monthly.

• End-to-end referring video object segmentation with multimodal transformers (video, paper, code)

• [ArXiv] DeepNet: scaling transformers to 1,000 layers

• [ArXiv] Generalized label shift correction via minimum uncertainty principle: theory and algorithm

• [Video] Using AI to accelerate scientific discovery

Enjoy the newsletter? Help us make it bigger and better by sharing it with your colleagues and friends.

Have a nice weekend! See you next week. — Andriy