My Python scripts to make high-quality figures for publications in top AI conferences and journals.
- figures
- python
- icml
- nature-machine-intelligence
132,241 visible repositories in the index
1–24 of 44 · Most stars
My Python scripts to make high-quality figures for publications in top AI conferences and journals.
The GitHub repository for the paper "Informer" accepted by AAAI 2021.
📚 Parameterize, execute, and analyze notebooks
[AAAI-23 Oral] Official implementation of the paper "Are Transformers Effective for Time Series Forecasting?"
[PVLDB 2024 Best Paper Nomination] TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods
Low-Cost Open Source Ventilator or PAPR
Matplotlib style sheets to nicely format figures for scientific papers, thesis and presentations while keeping them fully editable in Adobe Illustrator.
Code for paper "Which Training Methods for GANs do actually Converge? (ICML 2018)"
[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!
:clock7: A curated list of awesome time series databases, benchmarks and papers
A multi-task learning example for the paper https://arxiv.org/abs/1705.07115
Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive Language", ICWSM 2017
Generative Adversarial Networks implemented in PyTorch and Tensorflow
Code accompanying the ECCV 2020 paper "Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data" by Tim Salzmann*, Boris Ivanovic*, Punarjay Chakravarty, and Marco Pavone (* denotes equal contribution).
Universe-HTT barcode reference
Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)
Codebase for the paper LSTM Fully Convolutional Networks for Time Series Classification
Continuously updated paper list on advancements in Data Agents. Companion repo to our paper "A Survey of Data Agents: Emerging Paradigm or Overstated Hype?"
[MICCAI 2019 Young Scientist Award] [MedIA Best Paper Award] Models Genesis: self-supervised pre-training for 3D medical images. Learns transferable representations from unlabeled CT and MRI volumes, then fine-tunes for downstream segmentation and classification. Keras and PyTorch weights included.
Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]
Make your matplotlib figures fit your paper, poster, or slides in a single line of code.
[CVPR 2026] A PyTorch implementation of the paper "EDGS: Eliminating Densification for Efficient Convergence of 3DGS"
Simple implementation of OpenAI CLIP model in PyTorch.
Tidy Plots for Scientific Papers