Research & Education

Obsidian PDF++ is an Obsidian.md plugin designed to significantly improve the PDF experience by integrating robust annotation and viewing capabilities directly into the Obsidian environment. It transforms backlinks to PDF files into highlight annotations, allowing users to annotate PDFs simply by linking to text selections. The plugin also supports direct PDF annotation, making highlights visible outside Obsidian, and offers numerous quality-of-life improvements to the built-in PDF viewer. A key differentiator is its approach to sidenotes as pure markdown, ensuring annotations remain accessible even if the plugin is disabled. It also enables Obsidian to function as a standalone PDF annotation tool, facilitating seamless annotation without switching applications.

ExtremeNet is an open-source object detection system that employs a bottom-up approach to identify objects within images. It achieves this by detecting four extreme points (top-most, left-most, bottom-most, right-most) and one center point of objects using a standard keypoint estimation network. These five keypoints are then grouped into a bounding box if they are geometrically aligned. This method transforms object detection into a purely appearance-based keypoint estimation problem, bypassing region classification or implicit feature learning. The project is built upon the CornerNet code and integrates code from Deep Extreme Cut (DEXTR) for instance segmentation, allowing it to generate coarse octagonal masks and further refine them for improved Mask AP. It provides code for training, evaluation, and demo purposes, supporting benchmark evaluation on datasets like MS COCO.

FSDrive is the official implementation for the research paper "FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving," which was recognized as a NeurIPS 2025 spotlight. This tool introduces a novel spatio-temporal Chain-of-Thought (CoT) approach, allowing end-to-end autonomous driving Visual Language Agents (VLA) to visually process and plan trajectories. It uniquely unifies visual generation and understanding with minimal data, marking a significant advancement in applying visual reasoning to autonomous driving. FSDrive provides comprehensive instructions for installation, data preparation, training, inference, evaluation, and visualization, making it a valuable resource for researchers and developers in the autonomous driving domain.

The Knight in the Panther's Skin is a digital edition of Shota Rustaveli's 12th-century Georgian epic poem, Vepkhistkaosani. This interactive platform provides the full text in English (Wardrop 1912 translation) with a parallel Georgian text from the critical edition, allowing for a bilingual reading experience. Users can explore all 47 chapters, access detailed annotations, and view illustrations that bring the allegorical masterpiece to life. The tool enhances engagement with this historically significant work by weaving themes of friendship, love, and devotion into an accessible digital format, making it ideal for students, scholars, and enthusiasts of medieval literature and Georgian culture.

Lyspeak, despite its name suggesting a language learning tool, functions as an affiliate website in Turkish, focusing on online betting and casino bonuses. The site provides lists of current promotions, such as welcome bonuses, free spins, and no-deposit bonuses, from numerous gambling platforms like Roketbet, Betmoney, Milyar, and Fikstürbet. It aims to guide users to reliable and licensed sites offering these bonuses, detailing different types of bonuses like investment bonuses, loss bonuses, and freebet offers. The platform also includes an FAQ section addressing common questions about bonuses, their usage, and terms and conditions, positioning itself as a resource for individuals interested in online gambling promotions.

PyTorch-RL offers a comprehensive PyTorch implementation of various deep reinforcement learning algorithms. This repository is designed for researchers and developers working with reinforcement learning, providing ready-to-use implementations of popular policy gradient methods such as Trust Region Policy Optimization (TRPO), Proximal Policy Optimization (PPO), and Synchronous A3C (A2C). Additionally, it includes Generative Adversarial Imitation Learning (GAIL). A key feature is its fast Fisher vector product calculation and support for multiprocessing, enabling agents to collect samples from multiple environments simultaneously for improved performance. It supports both discrete and continuous action spaces, making it versatile for different reinforcement learning tasks.

Qwen-VL, developed by Alibaba Cloud, is a powerful open-source large vision language model (LVLM) that accepts image, text, and bounding box inputs, and outputs text and bounding boxes. It offers strong performance, significantly surpassing existing open-sourced LVLMs on multiple English evaluation benchmarks. Key features include multi-lingual support for English, Chinese, and multi-lingual conversations, end-to-end recognition of bi-lingual text in images, and multi-image interleaved conversations. It is also the first generalist model to support grounding in Chinese, allowing for bounding box detection through open-domain language expression. The model boasts fine-grained recognition and understanding with a 448x448 resolution, promoting detailed text recognition and document QA.

prettygraph is a Python-based web application developed by @yoheinakajima, designed to demonstrate a new UI pattern for text-to-knowledge graph generation. While it's an experimental project and not intended as a robust framework, it provides a simple yet interactive way to visualize knowledge graphs. The application uses Flask for the backend, LiteLLM for generating predictions that transform text inputs into JSON formatted graph data, and Cytoscape.js for visualization. A key feature is its dynamic UI, where the graph regenerates and updates in real-time with each period insertion in the text input, offering color-coded nodes and edges for better visual distinction. It requires an OpenAI API key for operation.

GeoChat is an open-source, grounded Large Vision Language Model (LVLM) specifically designed for Remote Sensing (RS) applications. Unlike general-domain models, GeoChat is tailored to handle high-resolution RS imagery and employs region-level reasoning for detailed scene interpretation. It leverages a newly created RS multimodal dataset and is fine-tuned using the LLaVA-1.5 architecture, resulting in robust zero-shot performance across various RS tasks. These tasks include image and region captioning, visual question answering, scene classification, visually grounded conversations, and referring object detection. GeoChat also introduces a novel data generation pipeline to create rich instruction sets for the RS domain, making it a valuable tool for researchers and developers in AI and remote sensing.

ONCETALK is an advanced AI tool engineered for dynamic and intelligent conversations. It leverages real-time internet data to ensure responses are always up-to-date and accurate, making it a reliable source for current information. The platform continuously learns and adapts, improving its conversational capabilities over time. This adaptability makes ONCETALK suitable for a wide array of information retrieval and interactive dialogue tasks across various domains. By offering contextually relevant and evolving insights, ONCETALK significantly enhances user engagement, providing a more intelligent and responsive interaction experience. Its core strength lies in its ability to process and utilize live data, setting it apart in delivering timely and precise information.

Lidar_For_AD_references is a comprehensive, open-source repository offering a curated list of academic papers and resources focused on LiDAR point cloud processing for autonomous driving applications. This tool is invaluable for researchers and engineers working in the autonomous vehicle domain, providing references across various critical tasks. These tasks include LiDAR point cloud clustering, semantic segmentation, plane extraction, object detection and tracking, registration and localization, feature extraction, and mapping. The repository also covers topics like point cloud density and compression, simulated point clouds, and various LiDAR datasets, making it a central hub for relevant academic literature and practical resources.

RoboVerse is an open-source initiative providing a unified platform, dataset, and benchmark specifically designed for scalable and generalizable robot learning. It aims to accelerate research and development in robotics and AI by offering a comprehensive ecosystem for creating, testing, and evaluating robot learning algorithms. The platform integrates various simulation frameworks and renderers, including Isaac Lab, Isaac Gym, MuJoCo, and Blender, alongside data from projects like RLBench and Maniskill. RoboVerse encourages community contributions and provides detailed documentation and tutorials to help users get started. Its focus on a standardized environment and extensive datasets makes it a valuable resource for advancing the field of robot learning.

Awesome-RLHF is a comprehensive, open-source repository dedicated to curating resources for Reinforcement Learning with Human Feedback (RLHF). It serves as a vital hub for researchers and practitioners, offering an up-to-date collection of research papers, associated codebases, and relevant datasets. The repository is meticulously organized by publication year, spanning from 2020 to 2025, and includes detailed explanations of RLHF concepts, advanced techniques like Inverse Reinforcement Learning and Human-in-the-Loop RL, and practical examples across various applications such as game playing, recommendation systems, and robotics. Its continuous updates ensure users have access to the latest advancements in the field.

Awesome-Referring-Image-Segmentation is a curated GitHub repository that compiles a vast collection of academic papers and datasets related to referring image segmentation. This resource is invaluable for researchers and practitioners in the computer vision domain, offering insights into traditional and interactive methods, as well as current challenges in the field. The repository is organized into sections covering datasets, challenges, traditional referring image segmentation, interactive referring image segmentation, referring video object segmentation, 3D referring segmentation, and referring image segmentation in specific domains. It is actively maintained and encourages contributions via pull requests or issue submissions, fostering a collaborative environment for advancing research in this specialized area.

Hyperspectral-Image-Super-Resolution-Benchmark is an open-source collection of resources dedicated to hyperspectral image super-resolution. Curated by Junjun Jiang, this benchmark provides a comprehensive list of techniques and papers for generating high spatial and high spectral resolution images. It covers four main classes of super-resolution: spatiospectral super-resolution (SSSR), spectral super-resolution (SSR), single hyperspectral image super-resolution (SHSR), and multispectral image and hyperspectral image fusion (MHF). The resource includes pioneer work, technique reviews, and recent advancements, often with links to PDF papers and code, making it an invaluable tool for researchers and academics in the field.

awesome-self-driving-car is a comprehensive, open-source curated list of resources dedicated to self-driving car technology. It serves as a valuable hub for developers, researchers, and students interested in autonomous vehicles, offering links to full-stack open-source projects like Apollo and Autoware, as well as essential libraries such as ROS, OpenCV, and TensorFlow. The list also includes academic courses from institutions like Udacity and MIT, alongside a vast collection of papers and blogs covering topics from HD mapping and simulation to localization, perception, planning, and control. Furthermore, it details various systems, hardware components, datasets, and benchmarks crucial for autonomous driving research and development.

Research in English News is a dedicated platform designed to make the latest academic research accessible to a broader audience. It translates complex scientific papers into concise, easy-to-understand articles, covering a wide range of topics from astrophysics and quantum communication to mental health and computer vision. The website features summaries of groundbreaking studies, highlighting key findings and their implications, such as new AI models for retinal scans, advancements in autonomous system safety, and insights into strange metals. This approach democratizes access to cutting-edge scientific knowledge, allowing individuals to stay informed about significant developments without needing to navigate dense scholarly content.

tf-image-segmentation is an open-source image segmentation framework built upon Tensorflow and the TF-Slim library. Its core purpose is to streamline the process of converting various image segmentation datasets, including general, medical, and other types, into a unified and easy-to-use .tfrecords format for training. The framework includes a robust training routine that supports on-the-fly data augmentation, such as scaling and color distortion, ensuring effective model training. It also provides functionalities for evaluating model accuracy using common metrics like Mean IOU, Mean pixel accuracy, and Pixel accuracy. The framework offers pre-trained model files and definitions for models like FCN-32s, FCN-16s, and FCN-8s, initialized with weights from Image Classification models like VGG, making it a comprehensive solution for researchers and developers working on image segmentation tasks.

Tiny Differentiable Simulator is a header-only C++ and CUDA physics library designed for reinforcement learning and robotics applications. It boasts zero dependencies, making it a lightweight and efficient solution for developers. The library implements various rigid-body dynamics algorithms, including forward and inverse dynamics, alongside contact models based on impulse-level LCP and force-based nonlinear spring-dampers. It also includes actuator models for motors, servos, and Series-Elastic Actuator (SEA) dynamics. The entire codebase is templatized, supporting automatic differentiation scalar types like CppAD, Stan Math fvar, and ceres::Jet, as well as regular float/double precision and fixed-point integer math for cross-platform deterministic computation. It can run thousands of simulations in parallel on a single RTX 2080 CUDA GPU at 50 frames per second and offers OpenGL 3+ and MeshCat visualizers.

Traw AI is designed to enhance efficiency by transforming extensive YouTube video content into easily digestible text summaries. This tool allows users to rapidly extract key information, making it ideal for quick learning and knowledge acquisition. By streamlining the process of consuming online video, Traw saves valuable time for professionals and individuals who need to process large amounts of video data without watching every minute. Its core functionality focuses on providing concise summaries, enabling users to grasp the main points and insights from videos efficiently.

Awesome-holistic-3d is a valuable open-source resource for researchers and academics focused on holistic 3D reconstruction in computer vision. This GitHub repository compiles a comprehensive list of relevant papers, datasets, and code, categorized by scene-level and object-level reconstruction. It includes references to tutorials, workshops, and a wide array of research papers spanning from 2009 to 2020. The resource details various datasets with information on the number of scenes, rooms, frames, and annotated structures, making it an essential reference for anyone working on or studying 3D reconstruction techniques.

Awesome-GUI-Agent is a meticulously curated list of papers, projects, and resources specifically focused on multi-modal Graphical User Interface (GUI) agents. This open-source repository serves as a valuable hub for researchers and developers aiming to build advanced digital assistants capable of interacting with computer screens. It categorizes resources into key areas such as Datasets/Benchmarks, Models/Agents, Surveys, and Projects, making it easy to navigate the vast landscape of GUI agent research. The project is actively maintained and encourages contributions, ensuring its relevance and comprehensiveness. It also features an 'Awesome-Paper-Agent' to automatically format arXiv links, streamlining the process of adding new research to the list. This resource is essential for anyone working on or interested in the development of intelligent agents that can understand and operate graphical user interfaces.

What Word Is That? is a free online word counter tool that provides instant statistics for any text you paste or type. It accurately counts words, characters (including and excluding spaces), sentences, and paragraphs. Additionally, it calculates the estimated reading time based on an average adult reading speed and determines the average word length and the number of unique words. The tool operates entirely within your browser using JavaScript, ensuring that your text never leaves your device and maintaining complete privacy. It's a straightforward and efficient solution for anyone needing quick text analysis without sign-ups or page reloads, making it ideal for academic writing, blog post optimization, social media content creation, and freelance writing tasks.

The Ethical Charter is a valuable resource for anyone interested in the ethical considerations surrounding AI, specifically those outlined by the BigScience organization. This Hugging Face Space allows users to easily access and download the BigScience Ethical Charter. The charter is available in multiple convenient formats, including .txt, .docx, and .html, making it accessible for different uses and preferences. It serves as a foundational document detailing the core values and ethical guidelines that BigScience adheres to, providing transparency and a framework for responsible AI development and research.