Research & Education

gradio_molecule2d is a straightforward and effective tool designed for visualizing chemical molecules. Users can input SMILES (Simplified Molecular Input Line Entry System) strings, and the application will instantly display the corresponding 2D molecular structure. This functionality makes it highly valuable for individuals in chemistry education and research, providing a quick and accessible way to inspect molecular geometries. Hosted on Hugging Face Spaces, it offers a free and easy-to-use interface for anyone needing to convert chemical notation into visual representations without complex software installations.

semantic-segmentation is an open-source PyTorch library designed for state-of-the-art semantic segmentation models. It provides a flexible and customizable framework for computer vision researchers and developers. The library supports a wide array of datasets, making it suitable for various applications requiring precise pixel-level classification. Its focus on ease of use and customizability allows users to adapt models to specific needs, ensuring high accuracy for diverse computer vision projects. This tool is ideal for those looking to implement or experiment with advanced semantic segmentation techniques.

4DGaussians is a research project presented at CVPR 2024, focusing on 4D Gaussian Splatting for real-time dynamic scene rendering. This method allows for very quick convergence and achieves real-time rendering speeds, as demonstrated on D-NeRF and HyperNeRF datasets. The project provides code for environmental setup, data preparation for synthetic and real dynamic scenes (D-NeRF, HyperNeRF, DyNeRF, and multiple views), training, rendering, and evaluation. It also includes helpful scripts for exporting 3D Gaussians, visualizing weights, and merging 4D Gaussians, making it a comprehensive resource for researchers in computer vision and graphics.

ChatGod is described as being associated with Zenith's ZOI satellite, a prototype specifically engineered for scientific experiments conducted in orbit. This satellite is equipped with a pressurized payload compartment, enabling a variety of microgravity experiments. Beyond its experimental capabilities, ChatGod also supports remote sensing and advanced communications technologies. The satellite's mission is designed for a duration of six months in orbit, focusing on data collection and scientific research. The tool's connection to such a specialized satellite suggests its application in highly technical and scientific domains, likely catering to researchers and institutions involved in space science and advanced technological development.

The demo-self-driving project is an interactive Streamlit application designed to showcase the Udacity self-driving-car dataset. It integrates real-time object detection capabilities using the YOLO (You Only Look Once) algorithm, providing a practical example of computer vision in action. The entire application is implemented in less than 300 lines of Python code, highlighting Streamlit's efficiency for building interactive data applications. This tool serves as an excellent resource for developers and data scientists interested in exploring self-driving car datasets and real-time object detection with a user-friendly interface.

Deep-reinforcement-learning-with-pytorch is an open-source GitHub repository that offers PyTorch implementations of classic and state-of-the-art deep reinforcement learning algorithms. The project includes implementations of popular methods such as DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, and TD3. Its primary goal is to provide clear and accessible code, making it easier for individuals to learn and experiment with deep reinforcement learning algorithms. The repository is actively maintained, with plans to add more advanced algorithms and update existing code. It also provides installation instructions and examples for testing the implementations.

New-View-Synthesis is a comprehensive GitHub repository dedicated to collecting and organizing research papers focused on new view synthesis techniques. The repository serves as a valuable resource for researchers and academics, offering direct links to published papers (often via arXiv or PDF) and their corresponding code implementations. It is actively maintained, with daily updates to include the latest advancements and provide more detailed information about each paper. This makes it an essential tool for staying current with the rapidly evolving field of neural radiance fields and other view synthesis methodologies, facilitating research, development, and understanding of these complex topics.

pytorch-pose is an open-source PyTorch toolkit designed for 2D single human pose estimation. It offers a comprehensive pipeline for training, inference, and evaluation, making it a valuable resource for researchers and developers in computer vision. The toolkit includes a robust dataloader with various data augmentation options, compatible with popular human pose databases such as MPII, LSP, and FLIC. Key features include multi-thread data loading, multi-GPU training support, a logger for tracking progress, and visualization of training and testing results. It is compatible with PyTorch 0.4.1/1.0 and provides detailed instructions for installation, data preparation, and usage, including testing with pre-trained models and evaluating PCKh@0.5 scores.

PyGCL is a PyTorch-based open-source library specifically designed for Graph Contrastive Learning (GCL). It provides a comprehensive framework for researchers and developers to implement and experiment with various GCL algorithms. The library features modularized GCL components, including graph augmentation techniques like Edge Adding, Feature Masking, and Node Dropping, as well as different contrasting architectures and modes (single-branch, dual-branch, bootstrapped, within-embedding). PyGCL also implements a variety of contrastive objectives such as InfoNCE, JSD, and Barlow Twins, alongside negative sampling strategies. It supports standardized evaluation with evaluators like Logistic Regression and SVM, and offers utilities for managing experiments, making it a valuable tool for advancing graph representation learning.

Nitrain (formerly torchsample) is a framework-agnostic Python library designed for medical image analysis, enabling efficient training of AI models. It provides robust functionalities for sampling and augmenting medical images, supporting various frameworks like PyTorch, TensorFlow, and Keras. The library simplifies model training by offering reasonable defaults and a high level of abstraction. Users can visualize results within a medical imaging context, making it a comprehensive tool for medical imaging AI development. Full examples for segmentation, classification, and registration tasks are available, and it integrates with the ANTsPy package for advanced medical image processing.

YOLOv11-RGBT offers a comprehensive single-stage multispectral object detection framework, extending the capabilities of YOLO models (from YOLOv3 to YOLOv13) and RTDETR to handle RGBT (Red, Green, Blue, Thermal) data. This project simplifies the configuration of visible and infrared datasets for multimodal object detection tasks, providing three distinct configuration methods. It supports multi-spectral object detection, keypoint detection, and instance segmentation. The framework is adaptable to various pixel-aligned images, including depth maps and SAR images, not just multispectral. Key features include support for TIFF images, 16-bit multi-spectral datasets with arbitrary channels, and various image formats like Gray, BGR, RGBT, and Multispectral with flexible channel configurations.

Gaussian-SLAM is an open-source project available on GitHub, designed for photo-realistic dense Simultaneous Localization and Mapping (SLAM). It leverages Gaussian splatting to achieve high-quality 3D reconstruction, offering a robust solution for researchers and engineers in computer vision and robotics. The tool supports various datasets including Replica, TUM_RGBD, ScanNet, and ScanNet++, and provides scripts for easy setup and data downloading. Users can configure and run SLAM experiments, reproduce results, and even generate fly-through videos based on reconstructed scenes. It's tested on powerful GPUs like RTX3090 and RTX A6000, ensuring performance for demanding tasks.

PaddleDetection is an end-to-end object detection development toolkit built on PaddlePaddle, offering a rich set of model components and benchmarks. It focuses on industrial applications by providing specialized models and tools, along with practical application examples. This toolkit helps developers streamline the entire process from data preparation and model selection to training and deployment. It supports various tasks including 2D/3D object detection, instance segmentation, face detection, keypoint detection, multi-object tracking, and semi-supervised learning. PaddleDetection also features low-code full-process development capabilities and a modular design for easy model construction.

pgmpy is an open-source Python library designed for causal and probabilistic reasoning through graphical models. It offers comprehensive implementations of data structures for various models including DAGs, PDAGs, MAGs, PAGs, Bayesian Networks, Dynamic Bayesian Networks, and Structural Equation Models. The toolkit includes algorithms for key tasks such as causal discovery, causal identification, causal and probabilistic inference, model validation, parameter estimation, and simulations. Its modular and extensible API ensures compatibility with scikit-learn, allowing direct use, integration into sklearn pipelines, or building higher-level tools. pgmpy supports both discrete and linear Gaussian data, as well as mixture data with arbitrary relationships.

Vista is an open-source project from OpenDriveLab, presented at NeurIPS 2024, offering a generalizable world model specifically designed for autonomous driving. This tool allows for the prediction of high-fidelity futures across a wide range of driving scenarios, extending these predictions to continuous and long horizons. A key feature is its ability to execute multi-modal actions, including steering angles, speeds, commands, trajectories, and goal points. Furthermore, Vista can provide rewards for different actions without requiring access to ground truth actions, making it a valuable resource for researchers and developers in the autonomous driving field. The implementation is based on generative-models from Stability AI, and the project includes installation, training, and sampling scripts, along with model weights available on Hugging Face and Google Drive.

Market Price Simulator is a browser-based trading sandbox designed for exploring financial market dynamics. Users can create multiple traders, place buy and sell orders, and observe how trades are automatically matched and prices evolve in real time. This simulator provides a visible order book and a history of trades, making it an ideal platform for understanding price formation, supply and demand, and order volume without financial risk. It's a valuable resource for students, researchers, and anyone interested in the mechanics of financial markets.

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.

ROS-Academy-for-Beginners is an open-source collection of code examples specifically designed for the 'Robot Operating System Introduction' course on Chinese University MOOC. This repository offers a comprehensive set of ROS packages, including robot simulation programs, various communication examples (topic, service, action, param), and demonstrations of advanced functionalities like navigation and Simultaneous Localization and Mapping (SLAM). It supports both C++ and Python implementations for many examples, making it versatile for different programming preferences. The project is actively maintained and updated, providing a valuable resource for students and developers looking to learn and implement ROS concepts. It also includes instructions for downloading, compiling, and running the examples, with specific recommendations for the operating environment.

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.

SERL (Software Suite for Sample-Efficient Robotic Reinforcement Learning) is a comprehensive toolkit designed to facilitate the training of RL policies for robotic manipulation. It includes a set of libraries, environment wrappers, and practical examples, enabling users to develop and deploy reinforcement learning solutions for robots. The suite is structured with an asynchronous actor and learner node architecture, allowing for parallel training and inference, with data exchange via agentlace. While providing tools for simulation with Franka robots, it also supports deployment on real Franka arms. SERL is currently being deprecated in favor of HIL-SERL, and users are encouraged to explore the new project for future developments.

The variational-autoencoder project offers a foundational reference implementation for variational autoencoders (VAEs) in both TensorFlow and PyTorch. This open-source tool is designed to assist developers and researchers in understanding, implementing, and experimenting with VAEs for various generative modeling tasks. It also features an example of an inverse autoregressive flow, providing insights into advanced generative techniques. The project is hosted on GitHub, indicating a collaborative and community-driven development approach, making it a valuable resource for those looking to integrate or study VAEs in their AI projects.

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.

Webots is an open-source robot simulator designed to provide a comprehensive development environment for modeling, programming, and simulating a wide range of robotic systems, including robots, vehicles, and other mechanical systems. Originally developed at EPFL for mobile robotics research, it was later commercialized by Cyberbotics and open-sourced in 2018. The platform is beginner-friendly, making it an excellent tool for introducing newcomers to the field of robotics. It offers pre-compiled binaries for easy installation and detailed tutorials to guide users through the simulation process. Webots supports continuous integration, nightly tests, and provides resources for building from source, updating, and reporting bugs, fostering an active development community.

Visual Pushing and Grasping (VPG) is a method for training robotic agents to learn how to plan complementary pushing and grasping actions for manipulation, particularly useful in unstructured pick-and-place applications. This framework operates directly on visual observations, utilizing RGB-D images, and learns through a process of trial and error. It trains quickly and demonstrates generalization to new objects and scenarios. The provided repository offers PyTorch code for training and testing VPG policies with deep reinforcement learning in both simulation and real-world environments, specifically on a UR5 robot arm. The system is designed to discover and learn synergies between non-prehensile (pushing) and prehensile (grasping) actions from scratch, using two fully convolutional networks trained jointly in a Q-learning framework.