- Berlin, Germany
- shchur.github.io
- in/oleksandrshchur
- @oleksandr-shchur.bsky.social
Stars
Autogluon-cloud aims to provide user tools to train, fine-tune and deploy AutoGluon backed models on the cloud. With just a few lines of codes, users could train a model and perform inference on th…
⚡ TabPFN: Foundation Model for Tabular Data ⚡
LC-PLM: long-context protein language model based on BiMamba-S architecture
Context is Key: A Benchmark for Forecasting with Essential Textual Information
Source code and data for the paper "SALT: Sales Autocompletion Linked Business Tables Dataset"
ML Assistant for Competitive Machine Learning
Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
Redset is a dataset containing three months worth of user query metadata that ran on a selected sample of instances in the Amazon Redshift fleet. We provide query metadata for 200 provisioned and s…
A playbook for systematically maximizing the performance of deep learning models.
Unified Training of Universal Time Series Forecasting Transformers
Chronos: Pretrained Models for Probabilistic Time Series Forecasting
An extremely fast Python package and project manager, written in Rust.
Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
Large-scale pretraining and benchmarking for short-term load forecasting.
Friends don't let friends make certain types of data visualization - What are they and why are they bad.
A Software Framework for Neuromorphic Computing
Compare and ensemble models without retraining
Large scale and asynchronous Hyperparameter and Architecture Optimization at your fingertips.
Lightning ⚡️ fast forecasting with statistical and econometric models.
Time-series machine learning at scale. Built with Polars for embarrassingly parallel feature extraction and forecasts on panel data.
Dataset and modelling infrastructure for modelling "event streams": sequences of continuous time, multivariate events with complex internal dependencies.
Methods for online conformal prediction.
Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.