Updated 6 months ago

astroaugmentations • Rank 6.8 • Science 54%

A package with various custom augmentations implemented which are specifically designed around astronomical data.

Updated 6 months ago

stable-gym • Rank 5.0 • Science 54%

This package contains several gymnasium environments with positive definite cost functions, designed for compatibility with stable RL agents.

Updated 6 months ago

thetis • Rank 8.3 • Science 44%

Service to examine data processing pipelines (e.g., machine learning or deep learning pipelines) for uncertainty consistency (calibration), fairness, and other safety-relevant aspects.

Updated 5 months ago

https://github.com/aeturrell/specification_curve • Rank 4.7 • Science 10%

Specification Curve is a Python package that performs specification curve analysis: exploring how a coefficient varies under multiple different specifications of a statistical model.

Updated 6 months ago

Premap2 • Science 57%

Preimage approximations for neural networks

Updated 5 months ago

https://github.com/amazon-science/recode • Science 49%

Releasing code for "ReCode: Robustness Evaluation of Code Generation Models"

Updated 5 months ago

https://github.com/amazon-science/factual-confidence-of-llms • Science 13%

Code for paper "Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators"

Updated 6 months ago

hyphi-gym • Science 54%

A Gymnasium benchmark suite for evaluating the robustness and multi-task performance of reinforcement learning algorithms in various discrete and continuous environments.

Updated 6 months ago

adversarial-nonparametrics • Science 28%

Robustness for Non-Parametric Classification: A Generic Attack and Defense

Updated 6 months ago

understanding-clip-ood • Science 36%

Official code for the paper: "When and How Does CLIP Enable Domain and Compositional Generalization?" (ICML 2025 Spotlight)

Updated 6 months ago

safe-control-gym • Science 59%

PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL

Updated 6 months ago

attention-meets-perturbation • Science 67%

📝 Official Implementation of "Attention Meets Perturbation: Robust and Interpretable Attention with Adversarial Training"

Updated 5 months ago

https://github.com/bethgelab/model-vs-human • Science 36%

Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)

Updated 6 months ago

seer • Science 57%

A GAN (generative adversarial network) for projecting synthetic building performance profiles.

Updated 6 months ago

cvpr22w_robustnessthroughthelens • Science 41%

Official repository of our submission "Adversarial Robustness through the Lens of Convolutional Filters" for the CVPR2022 Workshop "The Art of Robustness: Devil and Angel in Adversarial Machine Learning Workshop"