Research & Education

Open Knowledge Maps is the world's largest AI-based search engine for scientific knowledge, designed to transform research discovery. It offers a visual overview of research topics, helping users find relevant research outputs and identify key concepts. The platform is a charitable non-profit organization committed to open science principles, aiming to create an inclusive and sustainable infrastructure. It uses AI to analyze article metadata from trusted providers like PubMed and BASE, clustering resources and generating area titles to provide a comprehensive and interactive map of scientific literature. Users can explore topics, identify themes, and focus on pertinent papers, making it an invaluable tool for researchers and academics.

GENTRL, or Generative Tensorial Reinforcement Learning, is an open-source model designed to accelerate the identification of potent molecular inhibitors. It functions as a variational autoencoder with a sophisticated prior distribution of the latent space, utilizing tensor decompositions to encode relationships between molecular structures and their properties, even with missing data. The model trains in two stages: initially mapping a chemical space onto a latent manifold, then freezing parameters to explore the chemical space for molecules with high reward. This approach supports research in areas like identifying DDR1 kinase inhibitors, making it a valuable tool for academic and pharmaceutical research.

MMAction2 is an open-source toolbox for video understanding built on PyTorch, forming a key part of the OpenMMLab project. It features a modular design, allowing users to easily construct customized video understanding frameworks by combining different components. The toolbox supports five major video understanding tasks: action recognition, action localization, spatio-temporal action detection, skeleton-based action detection, and video retrieval. MMAction2 is well-tested and documented, providing detailed API references and unit tests, making it a robust platform for researchers and developers in the field.

MMTracking is an open-source video perception toolbox built on PyTorch, forming a key part of the OpenMMLab project. It stands out as the first open-source toolbox to unify diverse video perception tasks, including video object detection (VID), multiple object tracking (MOT), single object tracking (SOT), and video instance segmentation (VIS) within a single framework. Its modular design allows users to easily construct customized methods by combining different components. MMTracking is known for its simplicity, speed, and strength, leveraging MMDetection for detector integration and running all operations on GPUs for fast training and inference. It reproduces state-of-the-art models, often outperforming official implementations, and supports a wide range of datasets and methods for each task.

NASLib is a modular and flexible framework designed to facilitate Neural Architecture Search (NAS) research by providing a common codebase to the community. It offers high-level abstractions for designing and reusing search spaces, along with interfaces to various benchmarks and evaluation pipelines. This enables researchers to implement and extend state-of-the-art NAS methods with minimal code. The library's modular nature allows for easy innovation on individual components, such as defining new search spaces while reusing existing optimizers, or proposing new optimizers with current search spaces. Developed by the AutoML Freiburg group, NASLib is continuously updated with new search spaces, optimizers, and benchmarks.

Object-Detection-Metrics is an open-source toolkit designed to provide comprehensive metrics for evaluating object detection algorithms. It addresses the lack of consensus and standardized implementations for these metrics, offering a reliable solution for researchers and developers. The tool includes implementations for popular metrics such as Intersection Over Union (IOU), Precision, Recall, Precision x Recall curve, and Average Precision (AP), including both 11-point and all-point interpolation methods. It simplifies the evaluation process by accepting ground truth and detected bounding boxes without requiring complex file conversions. The implementation has been carefully compared against official versions, ensuring accurate and trustworthy results for benchmarking different approaches.

Opus-MT is an open-source project offering neural machine translation models and web services, built upon Marian-NMT and trained using OPUS data. It features SentencePiece-based segmentation and guided alignment for its models. The platform provides pre-trained, downloadable translation models under a CC-BY 4.0 license, including those from the Tatoeba translation challenge. Users can set up a Tornado-based web application with a UI and API for multiple language pairs, or a simpler websocket service. While it includes scripts for training models, these are currently optimized for the University of Helsinki and CSC computing environments. Opus-MT is ideal for researchers and developers looking to integrate or build upon open translation services.

ROLO is an open-source recurrent YOLO (You Only Look Once) model designed for simultaneous object detection and tracking. It utilizes the regression capabilities of Long Short-Term Memory (LSTM) networks to interpret visual features and translate them into precise object coordinates. This approach allows ROLO to not only detect objects within a frame but also track their movement over time, making it suitable for applications requiring continuous object monitoring. The project is available on GitHub, indicating its open-source nature and accessibility for developers and researchers.

rl-book offers the complete source codes for the book "Reinforcement Learning: Theory and Python Implementation." This resource provides a tutorial approach to reinforcement learning, detailing both theoretical concepts and practical Python implementations. It features one-to-one mapping between theory and code, supporting TensorFlow 2 and PyTorch 1&2. The implementations cover a wide range of algorithms, from classic methods like SARSA and Q-Learning to modern deep reinforcement learning techniques such as PPO, DDPG, and SAC. All codes are designed for compatibility across Windows, Linux, and macOS, and can be run on a laptop without requiring a GPU for most examples. The project also includes supporting content like exercise answers and errata for both English and Chinese versions of the book.

SINet is an open-source project for Camouflaged Object Detection (COD), a challenging computer vision task focused on detecting objects that blend into their natural habitat. Developed by Deng-Ping Fan and colleagues, SINet was presented at CVPR 2020 (Oral) and offers a robust baseline for COD research. The repository includes detailed introductions, the Search & Identification Net (SINet) model, and one-key evaluation codes. It also features the COD10K dataset, which provides diverse and meticulously annotated samples for training and testing. SINet is implemented in PyTorch and supports both training and testing, with an enhanced version (SINet-V2) accepted at IEEE TPAMI 2022. The project also highlights potential applications in medical imaging, agriculture, art, and computer vision.

TSFpaper is an open-source GitHub repository dedicated to providing a curated reading list of academic papers focused on Time Series Forecasting (TSF) and Spatio-Temporal Forecasting (STF). The repository organizes these papers by their respective model types, making it easier for users to navigate and find relevant research. It serves as a valuable resource for researchers, academics, and practitioners who are interested in staying updated with the latest advancements in these specialized forecasting domains. The collection aims to streamline the process of discovering key literature, fostering knowledge sharing within the scientific community.

UNeXt-pytorch is the official PyTorch implementation of UNeXt, an MLP-based network specifically designed for rapid medical image segmentation. This tool is ideal for researchers and developers working on medical imaging tasks, particularly those requiring quick processing for point-of-care applications. Based on a MICCAI 2022 paper, it offers a robust and efficient solution for segmenting medical images. The open-source nature of the project, hosted on GitHub, allows for community contributions and flexible integration into existing workflows, providing a strong foundation for advanced medical image analysis.

UniDet is an open-source object detection tool designed to operate across multiple large-scale datasets with an automatically learned unified label space. It was the winning solution of the ECCV 2020 Robust Vision Challenges. The tool offers state-of-the-art performance on datasets such as COCO, Objects365, OpenImages, and Mapillary. A key feature is its ability to predict class labels within this unified space, allowing it to be directly used for testing on novel datasets not included in its training. The repository also provides state-of-the-art baselines for Objects365 and OpenImages. UniDet is built on detectron2, making its inference API familiar to users of that framework.

Web Bench Leaderboard is a comprehensive Data & Analytics tool hosted on Hugging Face Spaces, designed for evaluating and comparing language models. Users can access a dynamic leaderboard to view existing evaluations, filter data, and select specific columns to display relevant information about various models. The platform also enables users to submit their own evaluations, contributing to a growing dataset for performance analysis. This tool is ideal for researchers, data scientists, and anyone interested in monitoring and benchmarking the capabilities of AI language models.

YOLO26 vs RF-DETR is a Hugging Face Space designed for comparing the performance of two prominent object detection and segmentation models: YOLO26 and RF-DETR. Users can upload an image and then choose between detection or segmentation tasks. The tool provides options to adjust settings such as confidence threshold and model size, allowing for a detailed analysis of how each model performs under different conditions. This application is particularly useful for AI researchers and computer vision developers who need to benchmark and understand the nuances of these models in a practical, visual environment.

3D-Occupancy-Perception is a comprehensive research resource dedicated to the field of 3D dense perception for autonomous driving. This active repository provides a systematic survey of the latest advancements, encompassing LiDAR-Centric, Vision-Centric, and Multi-Modal Occupancy Perception. It delves into core methodological issues, including network pipelines, multi-source information fusion, and effective network training. The resource also offers evaluations, detailed performance comparisons, and discussions on current limitations and future research directions. It aims to inspire further research and development in the autonomous driving community by curating and highlighting significant works in the domain.

Unsupervised-Classification is a GitHub repository offering a PyTorch implementation of the paper "SCAN: Learning to Classify Images without Labels." This tool addresses the challenge of automatically grouping images into semantically meaningful clusters when ground-truth annotations are absent. It deviates from recent end-to-end approaches by advocating a two-step method where feature learning and clustering are decoupled. The project demonstrates significant performance improvements over state-of-the-art methods on various benchmarks, including CIFAR10, CIFAR100-20, STL10, and ImageNet. It provides code for pretext tasks (like SimCLR), clustering (SCAN), and self-labeling steps, along with pretrained models and evaluation scripts, making it a valuable resource for researchers in computer vision and unsupervised learning.

AiiDA (Automated Interactive Infrastructure and Database for computational science) is a powerful open-source workflow manager designed for computational science. It emphasizes robust data provenance tracking, high performance, and extensibility, allowing researchers to manage complex computational workflows efficiently. Key features include the ability to write complex, auto-documenting workflows in Python, an event-based workflow engine supporting thousands of processes per hour with full checkpointing, and automatic tracking of inputs, outputs, and metadata for full reproducibility. AiiDA also offers a flexible HPC interface compatible with various schedulers like SLURM and PBS Pro, a plugin interface for extending functionality with new simulation codes and data types, and tools for open science, enabling the export and sharing of provenance graphs.

Algorithmic Trading with Python is a GitHub repository containing the complete source code for the 2020 book by Chris Conlan. This resource is invaluable for researchers and developers interested in algorithmic trading, providing practical Python implementations of key concepts. It includes stand-alone scripts for performance metrics to evaluate trading strategies, common technical indicators implemented in pure Pandas, and methods for converting these indicators into ternary signals. The repository also features a generic grid search wrapper for numeric optimization, object-oriented building blocks for portfolio simulation, and a generic wrapper for multi-core repeated K-fold cross-validation. Additionally, it offers free-to-use simulated End-of-Day stock data and alternative data streams, making it a comprehensive toolkit for learning and applying algorithmic trading principles.

This GitHub repository, Assemblies-of-putative-SARS-CoV2-spike-encoding-mRNA-sequences-for-vaccines-BNT-162b2-and-mRNA-1273, serves as a vital resource for researchers studying RNA vaccines. It provides experimental sequence information for the RNA components of the Moderna (mRNA-1273) and Pfizer/BioNTech (BNT-162b2) COVID-19 vaccines. The project details the methodology used for obtaining and sequencing these RNAs from discarded vaccine remnants, including extraction, fragmentation, and sequencing protocols. It offers assembled contigs encoding full-length spike proteins, verifying the Pfizer sequence and providing a working assembly for Moderna's vaccine. This data is crucial for researchers and clinicians to identify therapeutic-derived RNA sequences in high-throughput RNA-seq studies, distinguishing them from host or infectious origins.

Astrometry.net is an open-source project designed for the automatic recognition and calibration of astronomical images. It takes an input image and returns astrometric calibration metadata, along with lists of known celestial objects within the field of view. This tool is invaluable for astronomers and researchers who work with images where celestial coordinates are unknown or untrusted, helping to organize, annotate, and make astronomical information searchable. The project is developed on GitHub and offers documentation, a web service, and Docker containers for easy deployment and use.

3D-Gaussian-Splatting-Papers is a comprehensive and continuously updated repository dedicated to research papers on 3D Gaussian Splatting. This resource is invaluable for AI researchers and computer vision engineers seeking to stay abreast of the latest advancements in the field. The repository meticulously tracks and categorizes publications from major conferences and journals, including ICLR, CVPR, ECCV, ACM MM, SIGGRAPH, NeurIPS, and many others, spanning from 2024 to 2026. It also includes an archive of survey papers and offers detailed information for each entry, such as authors, affiliations, and links to abstracts, arXiv preprints, and code repositories, making it a central hub for academic exploration and collaboration in 3D Gaussian Splatting.

awesome-gan-for-medical-imaging is a curated, open-source list of Generative Adversarial Network (GAN) resources specifically tailored for medical imaging applications. Inspired by other 'awesome-*' initiatives, this repository on GitHub provides a comprehensive collection of research papers and code related to GANs in medical contexts. It covers diverse topics such as low-dose CT denoising, medical image segmentation, detection, synthesis, reconstruction, classification, and registration. Researchers can leverage this resource to explore the latest advancements and find relevant studies for their work in medical image analysis and AI development.

awesome-3D-gaussian-splatting is an open-source, curated collection of resources dedicated to 3D Gaussian Splatting (3DGS) and related technologies. This GitHub repository serves as a central hub for researchers, developers, and enthusiasts to explore papers, implementations, viewers, and learning materials. It aims to keep pace with the rapid advancements in 3DGS, offering a comprehensive database of academic papers, various community and official implementations across different programming languages, and support for popular game engines like Unity and Unreal. Additionally, it lists numerous viewers, including web-based, desktop, and VR options, alongside essential tools and utilities for data processing and development. The repository also provides extensive learning resources, including blog posts, talks, and video tutorials, making it an invaluable resource for anyone looking to understand or contribute to the 3DGS domain.