Stars
Official implementation of Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models
This is a repository for paper Mechanistic Dissection of Cross-Attention Subspaces in Text-to-Image Diffusion Models @AAAI'26
[ICCV 2025 Oral] Automated Model Evaluation for Object Detection via Prediction Consistency and Reliability
[NeurIPS 2025] Official implementation of "Soft Task-Aware Routing of Experts for Equivariant Representation Learning"
📊 A simple command-line utility for querying and monitoring GPU status
Benchmarking Generalized Out-of-Distribution Detection
Reading list for research topics in Masked Image Modeling
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.
A resource repository for 3D machine learning
My best practice of training large dataset using PyTorch.
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
An open-source Python framework for hybrid quantum-classical machine learning.
Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning / ICLR 2020
Official Pytorch Implementation for ICML'19 paper: Unsupervised Deep Learning by Neighbourhood Discovery
A simple method to perform semi-supervised learning with limited data.
Reimplementation of "Realistic Evaluation of Deep Semi-Supervised Learning Algorithms"
Open source release of the evaluation benchmark suite described in "Realistic Evaluation of Deep Semi-Supervised Learning Algorithms"
[arXiv 2019] "Contrastive Multiview Coding", also contains implementations for MoCo and InstDis
A curated list of awesome self-supervised methods