Research & Education

ReconX is an innovative AI tool designed for 3D scene reconstruction, particularly effective in scenarios with sparse input views. It addresses the challenge of creating detailed 3D models from insufficient visual data by reframing the reconstruction process as a temporal generation task. The core of ReconX lies in its ability to harness the strong generative prior of large pre-trained video diffusion models. To ensure 3D view consistency, it first constructs a global point cloud from limited input views and encodes it into a contextual space, serving as a 3D structure condition. This condition guides the video diffusion model to synthesize video frames that are both detail-preserved and exhibit high 3D consistency. Finally, ReconX recovers the 3D scene from the generated video using a confidence-aware 3D Gaussian Splatting optimization scheme, outperforming state-of-the-art methods in quality and generalizability on real-world datasets. The code for ReconX is expected to be released soon.

AuditMy offers an AI-powered website auditing tool designed to help businesses quickly identify and resolve critical issues affecting their online presence. This platform provides a comprehensive technical audit covering essential areas such as SEO, security, and website speed, delivering expert-level insights without the need for expensive agency fees. It leverages six concurrent AI engines to deeply scan a website's infrastructure, analyzing hundreds of data points from meta tags and schema markup to SSL certificates and server response times. AuditMy translates complex technical data into a simple, prioritized action plan, empowering users to enhance their website's performance, search engine visibility, and overall security, ultimately contributing to a stronger digital foundation and better user experience.

PreSumm is an open-source project providing code for text summarization with pretrained encoders, based on an EMNLP 2019 paper. It offers capabilities for both abstractive and extractive summarization, allowing users to condense text into shorter versions. The tool supports summarizing raw text input, with specific formatting requirements for sentence boundaries in extractive summarization. It includes pre-trained models for datasets like CNN/DailyMail and XSum, and provides detailed instructions for data preparation, model training, and evaluation. PreSumm is primarily designed for researchers and developers working in natural language processing and text summarization.

LibroMatch is a free AI-powered tool designed to help book lovers discover their next great read. Users can easily find similar books by entering the title and author of a book they already enjoy. The platform aims to provide personalized recommendations, making it simple to explore new titles based on existing preferences. It offers a straightforward interface for quick searches and also includes features like finding a book title by plot and popular books, enhancing the book discovery experience for a wide range of readers.

mml-book.github.io serves as the official companion webpage for the book "Mathematics For Machine Learning" by Marc Peter Deisenroth, A Aldo Faisal, and Cheng Soon Ong. This resource is designed to motivate and equip individuals with the necessary mathematical skills to understand advanced machine learning techniques. The site provides supplementary materials, including exercises for the mathematical foundations section and Jupyter notebooks for the example machine learning algorithms. These notebooks can be run live on Google Colab, offering an interactive learning experience. The book aims to be concise, focusing on core mathematical concepts rather than exhaustive coverage of advanced ML techniques, making this companion site a valuable educational aid.

The Process-Energy-Environmental Systems Engineering (PEESE) Lab, led by Fengqi You at Cornell University, is an interdisciplinary research group dedicated to pushing the boundaries of systems engineering, artificial intelligence, and data science. The lab develops innovative computational models, optimization algorithms, statistical machine learning techniques, and multi-scale systems analytics tools. These methodologies are applied across a variety of domains, including materials informatics, smart manufacturing, digital agriculture, energy systems, and sustainability. PEESE Lab emphasizes the seamless integration of theoretical frameworks, computational methods, and real-world applications, with research featured in prestigious journals like Science Advances and Nature Communications.

SchoolMouv is a comprehensive online academic support platform designed for students from CP (primary school) to Terminale (final year of high school) in France. It offers a vast library of over 16,000 educational resources, including video lessons, clear course summaries, interactive quizzes, exercises, flashcards, and study guides, all meticulously aligned with official French national curricula. The platform emphasizes a pedagogical approach, with 92% of students reporting better understanding of their courses and 9 out of 10 staying more focused due to its engaging and interactive formats. SchoolMouv also provides personalized progress tracking and an AI-powered tutor available via chat for homework help and academic coaching, aiming for concrete results like an average increase of 3 points in grades.

Tetris-deep-Q-learning-pytorch is an open-source Python project that demonstrates the application of Deep Q-learning for training an AI agent to play the classic game Tetris. Developed with PyTorch, this tool serves as a foundational example of reinforcement learning in action. Users can leverage the provided source code to train their own Tetris-playing models from scratch or test pre-trained models. The project includes all necessary scripts for training and testing, making it accessible for those interested in understanding and experimenting with AI agents and deep learning techniques in a practical gaming context. It's an excellent resource for students and developers exploring the basics of reinforcement learning.

AI Coder Buddy is an AI-powered coding assistant designed to significantly enhance developer productivity. While specific features are not detailed on the current landing page, the tool aims to provide developers with efficient access to code examples and solutions. It is expected to support a wide array of programming languages and frameworks, helping developers to streamline their workflow, solve coding problems more efficiently, and focus on higher-level tasks. The platform is currently in a 'Launching Soon' phase, indicating future availability for users seeking to leverage AI in their coding endeavors.

WeDLM is an open-source diffusion language model developed by Tencent, designed for high-speed inference. It uniquely reconciles diffusion language models with standard causal attention, enabling native KV cache compatibility with technologies like FlashAttention and PagedAttention. This approach allows for direct initialization from pre-trained autoregressive models such as Qwen2.5 and Qwen3, delivering significant real speedups compared to vLLM-optimized baselines. WeDLM achieves 3-6x speedup on tasks like math reasoning and up to 10x on sequential/counting tasks, while maintaining competitive accuracy. It includes an inference engine, evaluation suite, and a fine-tuning framework, making it a powerful tool for developers and researchers focused on efficient language model deployment.

Bert-Multi-Label-Text-Classification offers a PyTorch implementation of pretrained BERT and XLNET models specifically tailored for multi-label text classification. This open-source repository includes a structured codebase with modules for callbacks, configuration, dataset handling, model architecture, output management, text preprocessing, and training. Developers can fine-tune BERT models, preprocess data, and predict new data using provided scripts. The tool supports various dependencies like PyTorch, transformers, and scikit-learn, making it a robust solution for NLP tasks requiring multi-label classification.

Everyday Daily is a free AI-powered platform designed for daily English practice, offering comprehensive learning across listening, speaking, reading, and writing. The platform provides high-quality data updates and interactive lessons to help users enhance their language proficiency. It features AI feedback, particularly helpful for improving speaking skills, and aims to make English learning engaging and effective. Users can focus on specific areas of improvement, making it a versatile tool for various learning needs. The platform emphasizes bringing English learners together and offers a supportive community.

DashPlayer is a specialized video player crafted for English language learners, aiming to enhance language acquisition through immersive video watching. It offers a suite of features tailored for language study, including dual-language subtitles (English/Chinese), the ability to jump between sentences, and an integrated dictionary for quick word lookups by hovering over text. Users can also leverage AI to generate subtitles for videos lacking them and utilize an AI-powered sentence learning function. The player supports adjustable interface sizes, records playback positions, and can be controlled via Bluetooth remotes. It also includes video download and cutting functionalities, making it a comprehensive tool for self-directed English learning.

Link Whisper is an AI-powered WordPress plugin designed to streamline internal linking for SEO. It intelligently analyzes website content to identify optimal opportunities for internal links, allowing users to build thousands of links quickly. Key features include AI-powered suggestions for relevant links, an orphan page finder to identify content without internal links, and broken link detection. The tool also offers auto-linking, Google Console integration, dynamic visual sitemaps, and monthly link maintenance. It's trusted by over 50,000 WordPress publishers and aims to save significant time by automating the internal linking process, ultimately helping improve search engine rankings.

Feynman Nurse AI is an AI-powered study companion specifically designed for nursing students, available on Android and web, with iOS coming soon. It streamlines the study process by allowing users to record lectures, import PDFs, and even capture content from YouTube or TikTok links. The AI then instantly generates flashcards, practice quizzes, and organized notes tailored to nursing classes like Pharmacology, Med-Surg, and Pathophysiology. A key differentiator is its "Feynman Mode," which challenges students to explain concepts back to an AI mascot, ensuring deep understanding rather than rote memorization. The tool also includes over 150 pharmacology drug cards with spaced repetition and NCLEX-style quizzes, covering the entire nursing journey from fundamentals to NCLEX preparation. It aims to consolidate scattered study tools into one platform, offering a free-to-start model.

Anixo: Cartoon Yourself AI, also known as AniCore, is an iOS mobile application designed to convert any photo into stunning anime and cartoon artwork. Users can choose from over 30 distinct styles, including Kawaii, Shōnen, Pixar 3D, Cyberpunk, and more, to create unique stylized images. Beyond simple filters, the app provides a comprehensive editing suite, allowing users to adjust colors, lighting, detail, and composition to refine their AI-generated artwork. This tool is ideal for anyone looking to transform their photos into creative, high-quality anime and cartoon visuals with extensive customization options.

Wordia is a mobile application designed to significantly expand your vocabulary in English, Spanish, Korean, and Japanese. It provides daily curated words tailored to your language level, including useful and fun words, internet slang, and local dialects not typically found in textbooks. The app features concise definitions, interesting examples, and helpful translations. A standout feature is its AI-powered pronunciation assessment, which grades your speech and helps you improve. Users can bookmark favorite words, review previous vocabulary, and utilize a home screen widget for consistent learning. Additionally, Wordia integrates with HelloTalk, allowing users to write practice sentences and receive feedback from native speakers, fostering a comprehensive language learning experience.

Archive Intel is an AI-powered platform designed for financial firms to ensure compliance with SEC and FINRA regulations. It offers two core solutions: AI Communications Archiving and AI Marketing Review. The communications archiving solution automatically captures and archives all digital client communications, including text (iMessage, Android SMS, WhatsApp), email, chat (Slack, Teams, Zoom, Bloomberg), social media (LinkedIn, YouTube, X/Twitter, Meta), and web content. This system reduces manual compliance workload by up to 95% and cuts false positives by 99%. A key differentiator is its ability to archive text messages from personal phones without requiring additional apps or devices, supporting BYOD policies. The AI Marketing Review solution simplifies content compliance by scanning documents for high-risk terms and providing compliant suggestions, streamlining approval workflows and ensuring audit readiness. Archive Intel offers instant reporting, full audit trails, and customizable pricing based on users and connectors, with no hidden export fees.

ZeroCostDL4Mic is a free and open-source toolbox designed to democratize deep learning in microscopy. It consists of a collection of self-explanatory Jupyter Notebooks, hosted on Google Colab, which provides the necessary computational resources at no cost. The tool features an easy-to-use graphical user interface, making it accessible for researchers with little or no coding expertise. Its primary goal is to allow users to quickly test, train, and utilize popular Deep-Learning networks for processing microscopy data. This project originated from a collaboration between the Jacquemet and Henriques laboratories and has expanded with global contributions, as acknowledged in their Nature Communications paper.

nn_vis is an open-source project designed for processing and rendering neural networks to visualize their architecture and parameters. Developed as part of a master's thesis, it introduces a novel 3D visualization technique that declutters complex models. The tool estimates attributes for trained neural networks using established optimization methods like batch normalization, fine-tuning, and feature extraction to determine the importance of different network parts. It combines these importance values with techniques such as edge bundling, ray tracing, 3D impostors, and special transparency to create a comprehensive 3D model. nn_vis supports both 2D and VR visualization, allowing users to gain insights into model behavior, especially regarding generalization based on edge proximity. It also provides a GUI for controlling shader parameters and processing settings, enabling customization of the visualization.

Tennis_analysis is an open-source project designed to analyze tennis players and ball movements within video footage. It leverages advanced computer vision techniques, including YOLO v8 for player detection and a fine-tuned YOLO model for tennis ball detection. Additionally, the tool utilizes Convolutional Neural Networks (CNNs) to accurately extract court keypoints, providing a comprehensive understanding of on-court activity. This project is ideal for individuals looking to enhance their machine learning and computer vision skills through a practical, hands-on application. It measures player speed, ball shot speed, and the total number of shots, offering valuable insights for performance analysis.

Mini-SGLang is a compact and high-performance inference framework specifically designed for Large Language Models (LLMs). It serves as a lightweight implementation of SGLang, aiming to simplify the complexities of modern LLM serving systems. With a codebase of approximately 5,000 lines of Python, it functions as both a capable inference engine and a transparent reference for researchers and developers. Key features include advanced optimizations such as Radix Cache for KV cache reuse, Chunked Prefill to reduce peak memory usage, Overlap Scheduling to hide CPU overhead, Tensor Parallelism for multi-GPU scaling, and optimized kernels like FlashAttention and FlashInfer for maximum efficiency. It supports online serving with an OpenAI-compatible API and an interactive shell mode for direct model interaction.

Microsoft Copilot serves as an AI companion designed to inform, entertain, and inspire its users. This versatile tool offers advice, provides feedback, and delivers straightforward answers across various topics. It aims to enhance user interaction by acting as a personal assistant capable of understanding and responding to complex prompts. Copilot is integrated into the Microsoft ecosystem, making it accessible for a broad range of applications and user needs. Its core functionality revolves around providing quick, relevant, and helpful information, making it a valuable asset for anyone seeking to streamline their daily tasks or explore new ideas.

multiagent-competition offers the foundational code for environments detailed in the paper "Emergent Complexity via Multi-agent Competition." This tool is designed for researchers and academics focusing on multi-agent reinforcement learning, providing a platform to simulate and study emergent behaviors in competitive scenarios. It includes agent policies for various environments such as run-to-goal, you-shall-not-pass, sumo, and kick-and-defend tasks. The repository, though archived and read-only, serves as a valuable resource for understanding and replicating the experiments described in the associated paper, allowing for in-depth analysis of complex interactions between AI agents.