Stars
Joint embedding of protein sequence and structure with discrete and continuous compressions of protein folding model latent spaces. http://bit.ly/cheap-proteins
Agustinus' very opiniated publication-ready plotting library
Simplifying reinforcement learning for complex game environments
Collection of John Carmack’s .plan files
Bayesian optimization with conformal coverage guarantees
Code for the paper: "No Zero-Shot Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance" [NeurIPS'24]
A benchmarking suite for disentanglement algorithms, suited for evaluating robustness to correlated factors. Codebase for the paper "Disentanglement of Correlated Factors via Hausdorff Factorized S…
[ICML'23] StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
Extracted YouTube 8M URLs and Labels without all the TF Record parsing/features
Repository containing common 3D test models in original format with original source if known and obj mesh
ICLR 2021, Contrastive Learning with Hard Negative Samples
A PyTorch implementation of SimCLR based on ICML 2020 paper "A Simple Framework for Contrastive Learning of Visual Representations"
Code for the paper "Contrastive Learning Inverts the Data Generating Process".
A little Python script to collect LaTeX sources for upload to the arXiv.
Code, data and benchmark from the paper "Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences".
Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks
Final version of the submitted thesis, for my PhD degree
Implementation code for the paper "Generating Natural Language Adversarial Examples"
The best way to write secure and reliable applications. Write nothing; deploy nowhere.
Codes for reproducing the white-box adversarial attacks in “EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples,” AAAI 2018
EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples