Research & Education

Jazzberry is a platform designed for building and experimenting with reinforcement learning (RL) environments. It offers tools and resources tailored for researchers and students in the field of artificial intelligence. The platform supports a variety of RL algorithms, enabling users to explore and implement different approaches to model training. A key feature is the ability to customize environments for specific tasks, providing flexibility for diverse research needs. Jazzberry aims to simplify the complex process of developing and testing RL agents, making advanced AI research more accessible and efficient for its users.

Static-to-Dynamic-LLMEval is the official GitHub repository for a paper detailing recent advances in large language model benchmarks, specifically focusing on data contamination. The project conducts an in-depth analysis of existing static-to-dynamic benchmarking methods designed to reduce data contamination risks. It examines methods that enhance static benchmarks, identifies their limitations, and highlights the critical gap in standardized criteria for evaluating dynamic benchmarks. The repository proposes optimal design principles for dynamic benchmarking and analyzes the limitations of current dynamic benchmarks, offering a comprehensive overview of advancements in data contamination research and guiding future efforts.

Technical_Book_DL is a comprehensive technical book on deep learning, offering a pedagogical approach to understanding the three most common neural network architectures: Feedforward, Convolutional, and Recurrent. For each architecture, the book meticulously details its fundamental building blocks. It then proceeds to derive the forward pass and the complete update rules for the backpropagation algorithm, providing a thorough understanding for students and AI enthusiasts. The entire document is available as a downloadable PDF, with all figures and LaTeX source files also provided in the repository for compilation. This resource is particularly valuable for those who prefer detailed, indexed formulas over abstract matrix formulations, ensuring a precise grasp of the underlying mechanics.

system-prompts-and-models-of-ai-tools is a comprehensive open-source GitHub repository that curates system prompts, internal tools, and AI models from a wide array of AI applications. This resource is invaluable for developers, researchers, and AI enthusiasts looking to understand the underlying mechanics and prompt engineering strategies of popular tools like Augment Code, Claude Code, Cursor, Devin AI, NotionAI, Perplexity, and many others. It provides a centralized location to explore how different AI systems are structured and prompted, fostering learning and innovation in the AI development community. The repository also highlights the importance of securing AI systems against prompt injection and extraction risks.

TabM is an official open-source repository for the paper "TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling" (ICLR 2025). It offers a PyTorch-based Python package for implementing the TabM model, along with layers and tools for constructing custom architectures that efficiently ensemble MLP-like models. The tool is designed to improve performance on challenging tabular benchmarks like TabReD and has been successfully applied in Kaggle competitions. TabM is noted for its efficiency, being faster than prior tabular deep learning methods and capable of handling large datasets up to 100M+ objects. It allows for parallel training and weight sharing among MLPs, leading to better runtime, memory efficiency, and task performance.

AIxploria serves as a comprehensive online directory and search engine for artificial intelligence tools, featuring over 9000 listed AI solutions. The platform categorizes tools to facilitate easy discovery, offering a ranking of the best AI tools and a 'Top 10 AI' section that updates in real-time. It aims to bridge the gap between complex AI concepts and practical use cases, providing insights into AI trends and how each AI works through articles. AIxploria also encourages community participation, allowing users to submit new AI tools to keep the directory current and share knowledge. The site is designed for ease of use, offering free access without registration and compatibility across various devices.

stanford_dl_ex is a repository offering programming exercises for the Stanford Unsupervised Feature Learning and Deep Learning Tutorial. It provides starter code designed to help users engage with and practice the concepts taught in the official Stanford tutorial, available at ufldl.stanford.edu/tutorial. This resource is particularly useful for individuals looking to deepen their understanding and practical application of deep learning principles through hands-on coding. The repository includes various modules covering different aspects of deep learning, such as convolutional neural networks (CNN), principal component analysis (PCA), and sparse autoencoders (STL). It serves as a valuable, free educational tool for students and researchers alike.

TrajectoryCrafter is an advanced Content & Design tool designed to redirect camera trajectories in monocular videos using sophisticated diffusion models. This tool, presented at ICCV 2025, allows users to generate high-fidelity novel views from standard monocular video footage, offering precise control over camera pose. It is particularly useful for researchers and developers working with video manipulation and synthesis. The system requires a GPU with at least 28GB VRAM for optimal performance and can be set up using standard Python environments. While powerful, its capabilities are rooted in a pretrained video diffusion model, meaning it performs best with well-defined objects and clear motion, and may face limitations with highly complex scenarios beyond its base model's generation capacity. It provides both command-line inference and a local Gradio demo for ease of use.

Trending-Deep-Learning is a GitHub repository that provides a curated list of the top 100 trending deep learning projects. This resource is updated regularly and sorts repositories based on the number of stars they gained on a specific day. It leverages the GitHub search API with a comprehensive query including terms like 'deep-learning', 'CNN', 'RNN', 'convolutional neural network', and 'recurrent neural network'. Repositories with 40,000 stars or more are excluded to focus on emerging trends. This tool is ideal for researchers, developers, and students looking to stay updated on the latest advancements and popular projects within the deep learning community, offering a quick overview of what's gaining traction.

Urban-Sound-Classification is an open-source deep learning project designed for the classification of urban sounds. It offers a comprehensive set of Jupyter notebooks demonstrating various neural network architectures, including feedforward, convolutional, and recurrent neural networks. The project is built using Python 3.5 (or above) and leverages popular libraries such as Tensorflow 2.x, Numpy, Matplotlib, and Librosa. It primarily uses the UrbanSound8k dataset for model training, with Google's AudioSet suggested as an alternative. This tool is ideal for researchers, students, and developers interested in deep learning applications for audio analysis and sound classification, providing a practical foundation for understanding and implementing these techniques.

AI Free Tools is a comprehensive web-based platform offering a variety of AI-powered utilities for content creation and analysis. Users can access tools such as an AI writing tool, AI content detector, humanizer, AI rephraser, and AI text summarizer. The platform also includes specialized tools like an AI Contract Reviewer, AI FAQ Generator, and AI Word Counter. All tools are completely free to use, require no signup, and offer unlimited usage. With a focus on accuracy, the AI detection tool boasts 99% accuracy, making it a reliable resource for identifying AI-generated content. The platform aims to provide accessible and powerful AI solutions for writers, content creators, and businesses.

Top-Deep-Learning is an open-source project that compiles and ranks the top 200 deep learning GitHub repositories. The list is meticulously sorted by the number of stars each repository has received, offering a clear indicator of popularity and community engagement. This resource is invaluable for anyone looking to explore the most influential and actively developed projects within the deep learning domain. It is regularly updated to ensure the information remains current, reflecting the dynamic nature of deep learning research and development. The project's methodology involves querying the GitHub search API using terms like 'deep-learning', 'CNN', 'RNN', 'convolutional neural network', and 'recurrent neural network' to gather comprehensive results.

TensorKart is an open-source project that demonstrates self-driving capabilities within the classic game MarioKart 64, powered by Google's TensorFlow framework. Users can train a deep learning model by recording their own gameplay, which then learns to control the in-game kart. The model can generalize to new tracks even with a relatively small training dataset, as shown by its ability to drive on Royal Raceway after training on other tracks. The project provides scripts for recording gameplay samples, preparing training data, training the model with GPU acceleration (using cuDNN), and playing the game with the trained AI agent. It also includes features for overriding AI control with a joystick and outlines future work like reinforcement learning integration to improve performance based on lap times.

Nomic is a Python client for Nomic Atlas, a powerful platform designed for interacting with massive unstructured datasets. It enables users to explore, label, search, and share data directly within their web browser. Atlas supports datasets ranging from hundreds to tens of millions of data points, accommodating various modalities including text, image, audio, and video. Key capabilities include generating, storing, and retrieving embeddings for unstructured data, finding insights, and sharing data findings. The platform also offers features like semantic search, topic modeling, data clustering, and deduplication for text, images, video, and audio.

Türkçe Yapay Zeka Kaynakları is a comprehensive, open-source repository dedicated to deep learning and machine learning resources available in Turkish. Supported by the Deep Learning Türkiye community, this platform centralizes a wide array of materials including blog posts, video lectures, scientific articles, code examples, and datasets. It serves as an invaluable hub for individuals seeking to learn or conduct research in AI within the Turkish language. The resource is continuously updated and encourages contributions from the community, ensuring a rich and current collection of information across various AI topics, algorithms, frameworks, and applications.

text-generation-webui-colab offers a convenient Gradio web user interface for deploying and interacting with Large Language Models (LLMs) directly within a Google Colab environment. This open-source project supports a wide range of LLMs, including popular models like Llama 2, Vicuna, Falcon, and Mistral, often with GPTQ 4-bit quantization for efficient use. It's particularly useful for researchers, developers, and enthusiasts who want to experiment with different LLMs without extensive local setup. The repository provides numerous Colab notebooks pre-configured for specific models, simplifying the process of getting started with text generation, instruction following, and other LLM-based tasks.

TimeSeries_Seq2Seq is a GitHub repository offering a valuable collection of notebooks and code designed to facilitate the understanding and implementation of sequence-to-sequence (seq2seq) neural networks specifically for time series forecasting. The networks within this repository are built using popular deep learning frameworks, Keras and TensorFlow. It serves as a practical resource for data scientists and researchers looking to apply advanced neural network architectures to predict future values based on historical time-dependent data. The repository includes instructions for setting up the environment and working with the provided notebooks, making it accessible for those interested in hands-on learning and application of seq2seq models in time series analysis.

VLog is an innovative open-source tool designed for advanced video-language understanding, presented as a CVPR 2025 project. It introduces a novel, efficient GPT2-based video narrator that leverages a Narration Vocabulary via Generative Retrieval. This system converts video content into a comprehensive textual document, encompassing both visual and audio information. By feeding this document to a Large Language Model (LLM), users can engage in chat-based interactions directly over the video content. VLog aims to redefine how we perceive and interact with video, treating it as a 'long document' for deeper analysis and comprehension.

XuanCe (玄策) is an open-source, comprehensive, and unified deep reinforcement learning (DRL) library designed to provide high-quality and easy-to-understand implementations of DRL algorithms. It aims to address the sensitivity of DRL algorithms to hyper-parameter tuning and unstable training processes by offering a robust and flexible framework. XuanCe is highly modularized, easy to install and use, and supports flexible model combinations. It includes abundant algorithms for various tasks, supporting both DRL and Multi-Agent Reinforcement Learning (MARL) tasks. The library boasts high compatibility across different deep learning backends (PyTorch, TensorFlow2, MindSpore), operating systems (Linux, Windows, MacOS), and hardware (CPU, GPU). Key features include fast running speed with parallel environments, distributed training with multi-GPUs, automatic hyperparameter tuning, and good visualization effects with TensorBoard or Weights & Biases.

ChatGPT for YouTube is a free Chrome Extension designed to provide instant, AI-generated summaries of YouTube videos. This tool eliminates the need for an AI account or API key, making it accessible for all users. It helps you quickly understand the main points of any YouTube video, significantly saving time and enhancing your learning experience. The extension offers a free tier with 7 summary quotas per week, and users can purchase additional quotas or subscribe to a Pro version for unlimited summaries and transcription words. It's an ideal solution for anyone looking to efficiently consume video content.

LingoLooper is an innovative AI-powered language learning application designed to help users achieve fluency through immersive, real-world conversations. It leverages fun AI avatars to simulate diverse conversational scenarios across more than 30 languages and dialects, including English, Spanish, French, German, and Korean. The app focuses on practical speaking skills, allowing users to practice conversations on various everyday topics like work, family, shopping, and fitness. LingoLooper provides immediate feedback on grammar and proficiency, adapting to the user's skill level. Available on iOS and Android, it aims to make language acquisition engaging and effective, offering a dynamic alternative to traditional language learning methods.

Notelo is an AI-powered application designed to enhance personal and professional note-taking. It leverages artificial intelligence to automatically organize, summarize, and facilitate the retrieval of user-generated notes. This tool aims to streamline information management and improve productivity for individuals handling large volumes of textual data. By automating the categorization and summarization of notes, Notelo helps users quickly find relevant information and gain insights from their accumulated knowledge. It is particularly useful for those who need to manage extensive textual data, ensuring that valuable information is always accessible and well-organized.

Tradomate offers AI employees capable of performing a wide range of tasks that a human could, operating 24/7 at a fraction of the cost. These AI agents can manage emails, browse the web for information, organize calendars, and conduct research on various topics. The platform is designed to help businesses build, deploy, and scale their AI workforce, providing AI-powered virtual employees that feel human. Tradomate aims to automate daily operations and enhance productivity by offloading repetitive or time-consuming tasks to intelligent AI agents.

TEACH UP is an AI-powered platform specializing in Adaptive Training®, designed to revolutionize corporate learning and development. It offers an Adaptive Training® Studio, an AI-assisted authoring tool (LXP) for creating innovative training experiences, and an Adaptive Training® Platform, an AI-augmented LCMS for comprehensive course creation, distribution, and tracking. Key features include intuitive content creation with an AI Assistant, personalized learning paths that adapt in real-time, and AI-generated feedback for coached training scenarios. The platform also provides optimized monitoring of engagement and performance, and flexible content distribution. It aims to make training 30 times faster to create and 4.1 times more effective than traditional e-learning, ensuring 100% mastery through adaptive learning principles.