-
saint
The official PyTorch implementation of recent paper - SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
SAINT paper emerges new, claiming that they have SOTA results than benchmarks, however, after only 2-3 weeks, people say that with fine tuning(not even feature engineering) they can have better results than proposed paper https://github.com/somepago/saint/issues/1 , on exactly same problems on paper.
NOTE:
The number of mentions on this list indicates mentions on common posts plus user suggested alternatives.
Hence, a higher number means a more popular project.
Related posts
-
Maxtext: A simple, performant and scalable Jax LLM
-
RAG Using Structured Data: Overview and Important Questions
-
[Project] AMLTK: A framework for building your own AutoML (AutoSklearn authors)
-
Pix2tex: Using a ViT to convert images of equations into LaTeX code
-
A look at Apple’s new Transformer-powered predictive text model