Research & Education

Causal_Reading_Group is a GitHub repository dedicated to curating a comprehensive list of academic papers at the intersection of machine learning and causal theory. This resource is primarily utilized internally by research groups such as NExT++ at the National University of Singapore (NUS) and LDS at the University of Science and Technology of China (USTC) for their weekly discussion sessions. The repository encompasses a wide range of materials, including foundational causality papers, machine learning research, relevant survey papers, datasets, and applications within specialized fields like Natural Language Processing (NLP) and computer vision.

qwen3-30b-a3b Research is an AI tool designed for real-time deep research, leveraging the qwen3-30b-a3b model. It helps users get accurate answers to their questions by automatically searching the web for the latest information. Users simply type their question, and the tool finds relevant results and provides comprehensive answers. This makes it suitable for individuals and professionals who require up-to-date and verified information for their work or studies. The tool aims to streamline the research process by automating information retrieval and synthesis.

jsfeat is an open-source JavaScript Computer Vision library designed for developers to explore and implement modern computer vision algorithms using JS/HTML5. The library provides a comprehensive set of features, including custom data structures and essential image processing methods such as grayscale conversion, box blur, Gaussian blur, histogram equalization, Canny edges, and various derivative calculations. It also incorporates a Linear Algebra module for LU, Cholesky, and SVD solvers, along with Eigen Vectors and Values. For advanced applications, jsfeat offers a Multiview module with Affine2D and Homography2D motion kernels, and RANSAC/LMEDS motion estimators. Additionally, it includes feature detectors like Fast Corners, YAPE06, YAPE, and ORB, as well as Lucas-Kanade optical flow and HAAR/BBF object detectors, making it a versatile tool for computer vision development.

2d-gaussian-splatting provides an official implementation for creating geometrically accurate radiance fields using 2D Gaussian Splatting. This open-source project represents scenes with 2D oriented disks and utilizes perspective-correct differentiable rasterization. It includes regularizations to enhance reconstruction quality and offers various meshing approaches for Gaussian splatting, including both bounded and unbounded mesh extraction. The tool supports COLMAP and NeRF Synthetic datasets, and provides scripts for training, rendering, and evaluation of novel view synthesis and geometric reconstruction. It also features integrations with community resources like WebGL/Three.js viewers and offers performance improvements through CUDA operator fusing.

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.

advanced_lane_detection is an open-source project designed for advanced lane detection using computer vision techniques. Developed as part of the Udacity Self-Driving Car Nanodegree, it provides a comprehensive pipeline for identifying lane boundaries in images and video streams. Key steps include camera calibration and distortion correction, creating thresholded binary images using color transforms and gradients, applying perspective transforms for a bird's-eye view, and fitting polynomial curves to detect lane lines. The tool also calculates lane curvature and vehicle position relative to the lane center, and annotates the original image with this information. It's built with Python and relies on libraries like NumPy, OpenCV, Matplotlib, and Pickle.

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.

Algorithmic-trading-python is a comprehensive open-source repository designed to accompany freeCodeCamp's YouTube course on algorithmic trading in Python. It offers practical resources for individuals looking to understand and implement algorithmic trading strategies. The repository guides users through fundamental concepts, API basics, and the development of various trading models. Key sections include building an equal-weight S&P 500 index fund, as well as quantitative momentum and value investing strategies. This resource is ideal for students and developers who want to gain hands-on experience in financial programming and automated trading.

Image Similarity is an AI tool hosted on Hugging Face Spaces by AnnasBlackHat, designed to identify and group images based on their visual similarities. This tool can be particularly useful for tasks requiring the detection of duplicate images or the organization of image datasets into visually coherent clusters. While the live website currently shows a runtime error, suggesting it may not be fully operational at this moment, its intended function is to provide a free and accessible solution for image analysis and content moderation. The tool's availability on Hugging Face indicates a focus on community access and ease of use for those interested in applying AI to image-related challenges.

HunyuanWorld Viewer is an interactive tool hosted on Hugging Face Spaces, designed for exploring detailed 3D worlds. Users can either select from example images to load pre-existing environments or upload their own 3D models in PLY or DRC file formats. The viewer provides an immersive experience, allowing navigation within the 3D space using standard WASD keys for movement and mouse controls for looking around. This makes it a versatile platform for anyone interested in visualizing and interacting with 3D models, from artists and designers to researchers and enthusiasts. Its accessibility through Hugging Face Spaces ensures ease of use without complex installations.

Jinja Playground is a free, web-based tool hosted on Hugging Face that enables users to experiment with and debug Jinja templates. It provides a straightforward interface where you can input your Jinja template code and corresponding data, then instantly view the rendered HTML output. This functionality is particularly useful for developers and students who are learning Jinja syntax, need to test template logic, or want to visualize how data interacts with their HTML structures without setting up a full development environment. The platform simplifies the process of template customization and ensures that your Jinja code behaves as expected before deployment.

splatviz is a comprehensive, open-source Python-based interactive viewer designed for real-time editing and analysis of 3D Gaussian Splatting scenes. Utilizing the pyimgui GUI library, it enables direct manipulation of Gaussian Python objects just before rendering, offering extensive editing and visualization capabilities. Users can view multiple scenes simultaneously, either side-by-side or in a split-screen view, and evaluate Python expressions on the resulting scene. Key features include an Edit Widget for real-time manipulation of Gaussian parameters, an Eval Widget for debugging and visualizing variables, and a Camera Widget with Orbit and WASD modes for flexible scene navigation. It also supports attaching to running 3DGS training sessions for live inspection and editing.

Awesome-Self-Supervised-Papers is a comprehensive, open-source repository on GitHub dedicated to collecting and organizing research papers in the fields of self-supervised learning and representation learning. It serves as a valuable resource for researchers and practitioners, offering a curated list of academic publications. The repository is regularly updated with new papers, including those focusing on self-supervised learning with distillation and dense prediction. It categorizes papers by areas such as Computer Vision (CV) pretraining, contrastive learning, image transformation, self-supervised learning with knowledge distillation, and various other methods, providing details like conference/journal, ImageNet accuracy, and other performance metrics where applicable. Contributions to the paper bank are welcomed.

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.

Sweet Justice AI is a platform designed to help users find and access OnlyFans Telegram channels. The website boasts a collection of over 150,000 verified creators, providing a wide range of content. Users can browse various categories and get free preview content that is updated daily. The tool aims to offer exclusive access to popular groups and links across different messaging platforms, including Telegram, Discord, WhatsApp, and Messenger. While the name suggests an AI legal assistant, the actual content of the website is focused on adult content discovery, specifically OnlyFans leaks and related groups.

This open-source project provides a Tensorflow 2.x based implementation of state-of-the-art models for single image super-resolution, including Enhanced Deep Residual Networks (EDSR), Wide Activation for Efficient and Accurate Image Super-Resolution (WDSR), and Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (SRGAN). It offers a high-level training API, enabling users to train models as described in the respective papers and fine-tune EDSR and WDSR models within an SRGAN context. The tool includes a DIV2K data provider for automatic dataset downloads and offers pre-trained weights for quick setup. It's ideal for developers and researchers working on image processing and computer vision tasks.

Awesome-VLA-Robotics is a curated, open-source repository offering an extensive collection of resources focused on Vision-Language-Action (VLA) models in robotics. This includes a detailed list of excellent research papers, various VLA models, relevant datasets, and other valuable materials for researchers and practitioners in the field. The repository defines VLA models, outlines their core concepts, and details key components like Vision Encoders, Language Understanding modules, and Action Decoders. It also explores the relationship between VLAs, VLMs, and Embodied AI, tracing the evolution from VLM adaptation to integrated VLA systems. The resource is structured to provide quick glances at key models and datasets, categorized by application area and technical approach, making it an invaluable reference for understanding and advancing VLA robotics.

Websim is an interactive platform designed for creating and sharing games and web pages. It enables users to build various simulations and creative projects, ranging from number blocks playgrounds and interactive color mixers to more complex simulations like fractal zoomers and nuclear war simulators. The platform fosters a community where users can share their creations, view popular projects, and explore new content. Websim appears to cater to a broad audience interested in interactive content creation, offering a space for both casual exploration and more involved project development.

Semantic Segmentation Editor is an open-source, web-based labeling tool designed for creating AI training datasets from both 2D bitmap images and 3D point clouds. Developed by Hitachi Automotive And Industry Lab, it is particularly useful for autonomous driving research. The tool supports various image formats like JPG and PNG, and point cloud formats including ASCII, Binary, and Binary compressed. It offers a comprehensive set of tools for polygon drawing, magic tool for contrast detection, manipulation, cutting/expanding, and contiguous polygon creation for bitmap images. For point clouds, it provides functionalities for rotation, zooming, and point selection. The editor is built using Meteor, React, Paper.js, and three.js, and can be run via Docker Compose or from source.

Awesome-DLMs is the official GitHub repository for the survey paper "A Survey on Diffusion Language Models." It serves as a highly-starred, comprehensive, and up-to-date collection of research papers, code, and resources related to Diffusion Language Models. The repository categorizes DLMs into continuous, discrete, and multimodal types, highlighting key milestones in their development. It includes sections for must-read papers, surveys, foundational concepts, training strategies, inference optimization, training frameworks, benchmarks, and applications. This resource is invaluable for researchers, students, and practitioners looking to explore the latest advancements and foundational knowledge in the field of Diffusion Language Models.

LASR Labs provides a 13-week intensive research program focused on technical AI safety, aiming to reduce risks from advanced AI. Participants form small teams, typically three to four individuals, and are supervised by experienced AI safety researchers. The program emphasizes a "learn by doing" approach, guiding participants through the entire research process from proposal to publication of an academic-style paper and accompanying blog post. It is designed for individuals looking to join technical AI safety teams or pursue PhDs in the field, with alumni working at organizations like UK AISI and Open Philanthropy. The program offers an £11,000 stipend, office space, food, and travel support.

Awesome-BEV-Perception-Multi-Cameras is a valuable resource for researchers and engineers focused on multi-camera 3D object detection and segmentation within the Bird's-Eye-View (BEV) paradigm. This curated list compiles significant academic papers, including influential works like DETR3D, BEVDet, BEVFormer, BEVDepth, and UniAD. It categorizes papers by key themes such as Longterm BEV, BEV + Stereo, End to End BEV Perception, BEV + Distillation, Robust BEV, Fast BEV, HD Map Construction, Multi-sensor fusion, Survey, Occupancy Network, and Pre-training. Each entry typically includes a link to the paper and its corresponding GitHub repository, making it easy for users to access the research and associated codebases. This tool is essential for staying updated with the latest advancements in vision-centric autonomous driving perception.

SphereFace offers a comprehensive open-source implementation of the SphereFace algorithm, a deep hypersphere embedding method for face recognition. This tool provides a full pipeline covering face detection, alignment, and recognition, making it valuable for researchers and developers in computer vision. It includes detailed instructions for installation and usage, demonstrating how to train models on datasets like CASIA-WebFace and evaluate performance on LFW. The repository also features various network architectures, including SphereFace-20, and highlights its state-of-the-art verification performance in challenges like MegaFace. Additionally, it provides insights into the underlying mathematical concepts and practical considerations for training, such as gradient normalization and convergence difficulties, along with links to third-party re-implementations and related angular margin learning resources.

SSL4MIS (Semi Supervised Learning for Medical Image Segmentation) is a comprehensive resource for researchers and developers focusing on medical image analysis. It offers a curated collection of literature reviews and practical code implementations for semi-supervised learning techniques. The repository includes re-implementations of various semi-supervised methods such as Mean Teacher, Entropy Minimization, and FixMatch, adapted for medical image segmentation. Additionally, it supports a range of 2D and 3D backbone networks like UNet, nnUNet, and Swin-UNet. This project aims to establish a benchmark for semi-supervised medical image segmentation, fostering easier evaluation and fair comparison within the medical image computing community. It also covers active learning and source-free domain adaptation for medical image analysis.