Research & Education

entity-recognition-datasets is a valuable resource for researchers and developers working on named entity recognition (NER) and entity recognition tasks. This repository compiles a diverse collection of annotated datasets, spanning multiple languages, domains, and entity types. It serves as a crucial foundation for training and evaluating NER models, offering a wide array of corpora from news articles and social media to medical records and legal documents. The collection includes both readily available datasets and information on how to obtain those with licensing restrictions, often accompanied by conversion code to standard formats like CoNLL 2003. This makes it an essential tool for anyone looking to build or improve their NER systems across various applications and linguistic contexts.

Find3D is an open-world 3D part segmentation model designed to identify and segment specific components within 3D objects. Users can upload their own .pcd files or select from provided samples to analyze point cloud data. The tool allows for precise part queries, enabling the segmentation of complex 3D objects into their constituent parts. This capability is particularly useful for applications requiring detailed structural analysis, object recognition, and component isolation within 3D environments. Developed as a Hugging Face Space, Find3D offers an accessible platform for researchers, developers, and enthusiasts working with 3D data and AI applications.

Open-DiffusionGS is an open-source project that implements a novel approach to single-stage image-to-3D generation and reconstruction by integrating Gaussian Splatting directly into a diffusion denoiser. This method allows for fast and scalable creation of 3D objects, including mesh exportation, and efficient scene reconstruction without the need for depth estimators. The tool is capable of generating 3D outputs in approximately 6 seconds, significantly faster than some state-of-the-art methods. It supports both object-centric image-to-3D generation and scene-level reconstruction, with evaluation capabilities for the latter using datasets like RealEstate10K. The project provides comprehensive scripts for environment setup, quick demonstrations, data preparation for both scene and object-level datasets (including G-Objaverse), evaluation, and multi-stage training of custom models.

LongVU is an AI tool hosted on Hugging Face Spaces that enables users to interact with visual content by uploading videos or images and posing questions or comments. The application then processes the visual input and generates detailed text responses, providing insights and information derived from the content. This functionality makes LongVU a valuable resource for researchers and developers focused on video analysis, image understanding, and general visual content interpretation. It leverages advanced AI models to bridge the gap between visual data and textual explanations, facilitating deeper engagement with multimedia.

DeepReinforcementLearning is an open-source project that replicates the AlphaZero methodology for deep reinforcement learning using Python. Developed by AppliedDataSciencePartners, this tool is designed for researchers and developers interested in exploring and experimenting with advanced AI algorithms. It provides a comprehensive framework for building and training reinforcement learning models, specifically focusing on the AlphaZero approach. The repository includes code for game environments, Monte Carlo Tree Search (MCTS), agent implementation, and model training, making it a valuable resource for understanding and applying deep reinforcement learning concepts. The project is well-suited for those looking to delve into the intricacies of AI game playing and strategic decision-making.

WolframAlpha is a powerful computational knowledge engine that provides expert-level answers and dynamic insights across a vast array of subjects. Utilizing Wolfram's breakthrough algorithms, extensive knowledgebase, and advanced AI technology, it can compute solutions for mathematics, science, technology, society, culture, and everyday life. Users can input natural language queries or mathematical expressions to receive detailed, step-by-step solutions, plots, and curated data. It's relied upon by millions of students and professionals for its ability to make the world's knowledge computable, offering a unique blend of natural language understanding, dynamic algorithmic computation, and visual representation of data.

COBRApy is a powerful open-source Python package designed for constraint-based modeling of metabolic networks. It is widely used for genome-scale modeling in both prokaryotes and eukaryotes, offering robust infrastructure for creating and managing metabolic models. Researchers can access popular solvers and analyze models using methods such as flux balance analysis (FBA), flux variability analysis (FVA), parsimonious FBA (pFBA), and minimization of metabolic adjustment (MOMA). The tool also facilitates inspecting models to draw conclusions on gene essentiality and testing the consequences of knock-outs. COBRApy aims to be a foundational tool for developers building new COBRA-related Python packages for visualization, strain-design, and data-driven analysis, promoting re-use of classes and design principles for easier implementation and broader accessibility.

hamuleite is an open-source repository offering a comprehensive knowledge base of academic papers from prestigious institutions like National Taiwan University, National University of Singapore, Waseda University, University of Tokyo, Academia Sinica (Taiwan), and key Chinese universities and research organizations. The collection spans various disciplines including social sciences, economics, mathematics, game theory, philosophy, and systems engineering. It also includes research reports from academic and university sectors, along with summaries of academic forums in mathematics and related interdisciplinary fields. The repository is primarily intended for overseas Chinese and social science researchers, providing valuable resources for in-depth study and analysis.

china-dictatorship is an open-source GitHub repository dedicated to compiling anti-Chinese government propaganda. It serves as a comprehensive resource, featuring a mega-FAQ section that addresses common questions, a news compilation, and even recommendations for restaurants and music. The repository aims to provide information and perspectives critical of the Chinese government. It explicitly warns users in China with real names on their accounts against starring the repo to avoid police attention, highlighting the sensitive nature of its content. The project covers a wide range of topics, including censorship, human rights issues, political events, and critical analyses of key figures and policies within the Chinese Communist Party.

This open-source book, "Mathematical Foundations of Reinforcement Learning," offers a mathematically rigorous yet accessible introduction to the core concepts, problems, and algorithms in reinforcement learning. Designed for senior undergraduate students, graduate students, researchers, and practitioners, it requires no prior reinforcement learning background but assumes knowledge of probability theory and linear algebra. The book carefully controls mathematical depth, providing illustrative examples based on a grid world task to clarify complex ideas. It is coherently organized, building each chapter on the preceding one, and is complemented by lecture slides and a highly-viewed video series available in both Chinese and English.

SFA3D is an open-source PyTorch implementation designed for super fast and accurate 3D object detection using LiDAR point clouds. It features an anchor-free approach, eliminating the need for Non-Max-Suppression, which contributes to its speed. The tool supports distributed data parallel training, making it suitable for large-scale applications, and includes pre-trained models for immediate use. SFA3D is particularly relevant for autonomous driving and robotics, as highlighted by its use in the Udacity Self-Driving Car Engineer Nanodegree Program. It also offers ROS source code integration for robotics applications and provides detailed technical documentation and demonstration capabilities.

Vision Arena offers an online interface for testing and comparing various Vision Language Models (VLMs) in a side-by-side format. Users can upload images or input simple prompts to execute computer vision functions such as image classification, object detection, and style transformations. This tool is hosted on Hugging Face Spaces by WildVision, providing a convenient platform for evaluating VLM performance. It's particularly useful for researchers, developers, and anyone interested in benchmarking different VLMs for their specific applications, offering a practical way to assess model capabilities.

SARDet_100K is a comprehensive dataset specifically designed for advancing research and development in synthetic aperture radar (SAR) object detection. This large-scale dataset facilitates the training and evaluation of models for multi-class rotated object detection tasks, a critical capability in various applications. Accepted at NeurIPS 2024 as a spotlight, SARDet_100K offers a robust foundation for researchers and developers working on complex SAR data analysis. Its focus on rotated object detection addresses a common challenge in SAR imagery, where objects can appear at various orientations, making it a valuable resource for developing more accurate and resilient detection algorithms.

Sockeye is an open-source sequence-to-sequence framework specifically designed for Neural Machine Translation (NMT), built on PyTorch. It provides capabilities for distributed training and optimized inference, powering applications like Amazon Translate. While Sockeye has entered maintenance mode and is no longer adding new features, it remains a valuable resource for researchers and developers in the NMT field. The framework supports PyTorch exclusively in its latest versions, with previous versions offering compatibility with MXNet. It includes tools for converting MXNet models to PyTorch for inference, making it adaptable for existing projects. Comprehensive documentation and developer guidelines are available for users.

unitree_rl_lab is a specialized repository designed for reinforcement learning implementation tailored for Unitree robots. Built upon the IsaacLab framework, it offers comprehensive support for various Unitree models, including Go2, H1, and G1-29dof. This tool provides a robust environment for robotics researchers and reinforcement learning engineers to develop, test, and deploy advanced AI models for Unitree's robotic platforms. It facilitates the creation of sophisticated control algorithms and behaviors, enabling researchers to push the boundaries of robotic autonomy and intelligence through practical, hands-on experimentation with real-world robot models.

EmerNeRF offers a self-supervised approach for spatial-temporal scene decomposition using neural fields. It can effectively separate dynamic objects from a static background and estimate their motion without explicit supervision. The tool also enriches 2D features by lifting and 'denoising' them in 4D space-time, opening new possibilities for advanced scene understanding. EmerNeRF supports the NeRF On-The-Road (NOTR) dataset, derived from the Waymo Open Dataset, and NuScenes, with provisions for custom dataset integration. It is implemented in PyTorch and designed for researchers and developers working on neural radiance fields and 3D scene reconstruction.

VILA is a family of vision language models (VLMs) developed by NVlabs, designed to handle complex multimodal AI tasks. It is optimized for both efficiency and accuracy, making it suitable for a wide range of applications from edge devices to data centers and cloud environments. VILA excels in understanding both video and multi-image inputs, providing robust capabilities for various vision-language challenges. The project is available on GitHub, promoting open-source collaboration and accessibility for developers and researchers looking to integrate advanced VLM functionalities into their projects.

easy-few-shot-learning is a comprehensive open-source GitHub repository designed to simplify few-shot learning for image classification. It provides ready-to-use code and tutorial notebooks, making it accessible for both newcomers to the field and experienced practitioners seeking reliable implementations. The repository features 11 state-of-the-art few-shot learning methods, including Prototypical Networks, SimpleShot, and FEAT, along with tools for data loading tailored for few-shot classification tasks. It also includes scripts to reproduce benchmarks and utilities for research. The project supports various datasets like CU-Birds, tieredImageNet, miniImageNet, and Danish Fungi, with clear instructions for download and usage.

LegislatureAI is a free tool designed to help users browse bills and meetings across various cities and counties in the Bay Area and Hawaii. It serves as a valuable resource for staying informed about local government activities and legislative developments. The platform provides access to essential legislative information, making it easier for citizens, researchers, and other interested parties to track local policy. By centralizing this data, LegislatureAI aims to enhance transparency and engagement with local governance.

AlgorithmicTrading is an open-source repository offering three distinct methods for identifying and exploiting arbitrage opportunities: Dual Listing Arbitrage, Options Arbitrage, and Statistical Arbitrage. Developed in collaboration with Optiver and peer-reviewed by their staff, this resource provides a robust foundation for understanding these complex financial strategies. While the analysis offers valuable insights into how these methods operate, the repository explicitly notes that effective implementation typically requires C++ for speed and a lightning-fast connection, making it less feasible for retail investors. It serves primarily as an educational and research tool for those interested in advanced algorithmic trading concepts.

Reinforcement-Learning-Notebooks offers a comprehensive collection of Reinforcement Learning algorithms, primarily implemented in Python. This resource is based on Sutton and Barto's seminal book and incorporates concepts from various research papers. It serves as an excellent supplementary material for students and researchers studying reinforcement learning, providing practical code examples to accompany theoretical knowledge. The notebooks were developed during a university course and are intended to be used alongside academic texts and lectures. While the code is acknowledged to be somewhat unpolished, it provides functional implementations for understanding complex RL concepts. It's an open-source project, encouraging collaboration and improvements from the community.

PufferLib is a fast and sane open-source reinforcement learning library designed to train tiny, super-human models efficiently. It includes a learning algorithm, hyperparameter tuning, and simulation methods developed through PufferAI's research. The library offers optimized parallel simulation and high-performance environments, making it suitable for both academic research and industrial applications. PufferLib aims to simplify working with complex environments by acting as a compatibility layer. All its tools are free and open source, with documentation hosted at puffer.ai. Support is available via Discord, and the project actively seeks new contributors.

awesome-human-pose-estimation is an open-source GitHub repository serving as a comprehensive collection of resources focused on human pose-related problems. It primarily concentrates on human pose estimation but also covers areas such as mesh representation, flow calculation, (inverse) kinematics, affordance, robotics, and sequence learning. The repository is continuously updated with the latest papers and resources, making it a valuable asset for researchers and students in the field. It provides an organized list of academic papers, categorized by topics like 2D and 3D pose estimation, human mesh, and real-time pose estimation, along with links to popular implementations in PyTorch, TensorFlow, and Torch.

awesome-NeRF-and-3DGS-SLAM is a curated, open-source repository offering a comprehensive list of resources focused on Implicit Representations, Neural Radiance Fields (NeRF), and 3D Gaussian Splatting papers within the SLAM (Simultaneous Localization and Mapping) and Robotics domains. This valuable resource includes direct links to papers, videos, code repositories, and related websites, making it an essential reference for researchers and academics. It covers general NeRF models, survey papers, benchmarks, tutorials, and specific applications in Visual-SLAM, Lidar-SLAM, and Multimodal-SLAM for both NeRF and 3D Gaussian Splatting. The repository also delves into robotics applications such as manipulation, reinforcement learning, planning, navigation, localization, and re-localization, providing a centralized hub for cutting-edge research in these fields.