Research & Education

Neuronika is a machine learning framework built entirely in Rust, emphasizing ease of use, rapid prototyping, and performance. At its core, Neuronika utilizes reverse-mode automatic differentiation, enabling the creation of dynamically changing neural networks with minimal effort and overhead through a lean, imperative, and define-by-run API. The framework leverages the power of the Rust language to offer an intuitive and efficient interface without the need for Foreign Function Interfaces (FFI). It supports GPU-accelerated primitives via CUDA, serialization with Serde, and transparent BLAS support for optimized matrix multiplication. Neuronika is currently in active development, with breaking changes expected as it evolves.

lagrangian_nns is an open-source project providing implementations of Lagrangian Neural Networks (LNNs). Unlike Hamiltonian Neural Networks, LNNs can parameterize arbitrary Lagrangians using neural networks and do not require canonical coordinates, making them suitable for systems where generalized momentum is difficult to compute, such as the double pendulum. The project includes a core equation of motion for automatic derivation of dynamics from learned Lagrangians, which is compatible with any JAX version. It also offers self-contained tutorials and example notebooks for various applications, including special relativity and the wave equation. The tool was developed with JAX 0.1.55 (2020) and uses pixi for reproducible environment management, ensuring compatibility with the original paper's environment.

KG-LLM-Papers is an open-source repository dedicated to curating a comprehensive list of research papers that explore the integration of knowledge graphs (KGs) and large language models (LLMs). This resource is invaluable for researchers and practitioners seeking to understand the synergies and applications at the intersection of these two advanced AI fields. The repository is actively maintained, with regular updates on new preprints and accepted papers from leading conferences. It categorizes papers into surveys and methods, offering a structured overview of the evolving landscape. The project encourages community contributions through Pull Requests to ensure the list remains current and complete.

NATSpeech is a comprehensive open-source framework for Non-Autoregressive Text-to-Speech (NAR-TTS) research and development. It offers official PyTorch implementations of advanced models like PortaSpeech (NeurIPS 2021) and DiffSpeech (AAAI 2022), facilitating high-quality and portable speech generation. The framework includes robust features such as data processing for NAR-TTS using Montreal Forced Aligner, a scalable training and inference system, and an efficient random-access dataset implementation. It's designed for technical users who want to explore and build upon state-of-the-art speech synthesis technologies, providing the necessary tools and code for experimentation and deployment.

learn-modern-ai-python is an open-source GitHub repository offering comprehensive learning materials for Python courses, specifically tailored for modern AI-assisted development with type hints. It is an integral part of the Panaversity Certified Agentic & Robotic AI Engineer program, providing structured content for individuals looking to master AI-driven Python programming. The repository covers a wide array of topics including Python fundamentals, Linux, Docker, Google Colab, prompt engineering, generative AI, and agentic AI. It's designed to equip learners with practical skills in developing intelligent applications and understanding the nuances of AI integration in Python workflows.

QANDA (Mathpresso) is an AI-powered educational super platform dedicated to making effective education accessible worldwide. It leverages AI technology to provide personalized learning experiences, aiming to democratize education that was previously limited to a select few. The platform supports 7 languages, including Korean, Japanese, Vietnamese, Indonesian, Thai, English, and Spanish, and has processed over 7.2 billion problem searches. With over 97 million users globally, 90% of whom are international, QANDA has established itself as a leading educational service in Asia and beyond. It has attracted significant investment from major players like Google and SoftBank Ventures, and continues to innovate with products like MathGPT and Cramify.

LLM-Agent-Paper-List is a comprehensive repository of academic papers focusing on Large Language Model (LLM) based agents. This resource is specifically curated to accompany the 86-page SCIS cover paper, "The Rise and Potential of Large Language Model Based Agents: A Survey," by Zhiheng Xi et al. It offers researchers and developers a centralized and organized collection of must-read papers in this rapidly evolving field. The list is structured to cover various aspects of LLM-based agents, including their construction (brain, perception, action), practical applications (single-agent, multi-agent, human-agent cooperation), and the emerging concept of agent societies. The repository also includes news updates, project releases like AgentGym, and discussions on key topics and open problems, making it an invaluable tool for staying current with advancements in LLM agent research.

LM-reasoning is a GitHub repository dedicated to curating a collection of papers and resources focused on reasoning in Large Language Models (LLMs). It offers a structured overview of various techniques, including fully supervised finetuning, prompting and in-context learning, and hybrid methods, along with evaluation and analysis papers. The repository is designed to be a valuable resource for researchers, academics, and anyone interested in the advancements and methodologies behind reasoning capabilities in LLMs. It is open-source and encourages contributions from the community to ensure its comprehensiveness and up-to-date nature.

The LLM Training Handbook is an open collection of methodologies designed to assist with the successful training of large language models. It offers highly technical material, including scripts and copy-n-paste commands, specifically tailored for LLM training engineers and operators. The handbook covers crucial topics such as model parallelism, maximizing throughput, tensor precision/data types, training hyper-parameters, model initializations, instabilities, debugging software and hardware failures, and SLURM resource management. This resource is ideal for those seeking practical, hands-on solutions to common LLM training challenges, distinguishing itself from more conceptual overviews by focusing on actionable technical details.

LLMAgentPapers is an open-source repository dedicated to curating a comprehensive list of must-read papers on Large Language Model (LLM) Agents. This resource is designed for researchers and practitioners in the field, offering an organized collection of academic works covering various aspects of LLM agents, including agent personality, memory, planning, tool use, RL training, and multi-agent systems. The repository also features sections on applications, frameworks, and benchmarks, making it a valuable hub for staying informed about the latest advancements and research trends in LLM agents. It provides direct links to paper abstracts, facilitating easy access to the research.

llm-continual-learning-survey is a comprehensive and actively updated survey focusing on Continual Learning of Large Language Models (CL-LLMs). This resource, published in ACM Computing Surveys 2025, serves as a dynamic repository of research papers, categorized by topics such as Continual Pre-Training (CPT), Domain-Adaptive Pre-Training (DAP) across various domains (legal, medical, financial, scientific, code, language), Continual Fine-Tuning (CFT), and more. It is designed to be a living document, with new papers and updates regularly added, and encourages contributions from the research community via pull requests or issues. This makes it an invaluable resource for researchers and academics tracking advancements in CL-LLMs.

ML-notes is an open-source repository offering extensive notes and assignments on machine learning. It covers a wide array of topics including Regression, Classification, CNN, RNN, Explainable AI, Adversarial Attack, Network Compression, Seq2Seq, GAN, Transfer Learning, Meta Learning, Life-long Learning, and Reinforcement Learning. The content is available in multiple formats such as HTML, Markdown, and PDF, making it accessible for different learning preferences. Additionally, it includes practical code examples for concepts like Gradient Descent and Keras implementations. This resource is ideal for individuals looking to deepen their understanding of machine learning through structured notes and practical exercises.

ML-Study-Guide is an open-source resource designed to help individuals get started with machine learning through a structured, minimal study plan. It guides users through essential foundational topics, beginning with core mathematics like multivariable calculus, differential equations, linear algebra, and statistics/probability. The guide then progresses to Python programming, covering both beginner and intermediate levels. It also introduces the ML tech stack, including NumPy, Pandas, and Matplotlib, before recommending comprehensive machine learning courses. The plan emphasizes hands-on practice through Kaggle challenges and encourages specialization in fields like Computer Vision or NLP, along with creating a blog to share learned concepts. It also suggests recommended books for those who prefer learning through reading.

Cruit is an AI-powered career agent designed to streamline the job search and career development process. It acts as a personal career agent, helping users build their professional brand, land their dream job, and grow their career through a simple chat interface. Key features include an AI-optimized resume builder, LinkedIn profile optimization, interview preparation with video feedback, and a job tracker. Cruit aims to replace multiple disparate career tools with one integrated, conversational platform that remembers a user's entire career history and provides ethical, context-aware guidance without fabricating experience.

MLResources is an open-source GitHub repository managed by the DLSU Machine Learning Group, serving as a comprehensive collection of resources for Machine Learning and Deep Learning. It features a curated list of lectures, videos, and books, catering to individuals at all levels of experience, from beginners to advanced practitioners. The repository also includes a section for tools and frameworks, encompassing software for data collection, annotation, and visualization, with plans for further expansion. This resource is continuously updated, making it a valuable hub for anyone looking to learn or deepen their knowledge in the ML/DL domain.

Solomei AI is a research team dedicated to the exploration and integration of human creativity with artificial intelligence. The team comprises researchers from diverse fields including mathematics, engineering, philosophy, and the arts, fostering a multidisciplinary approach to AI development. Their core focus is on innovation that not only advances AI capabilities but also profoundly honors human values, ensuring that technological progress serves humanity's best interests. While specific tools or platforms are not detailed, the emphasis is on foundational research and ethical considerations within the AI landscape, suggesting a focus on theoretical and applied research rather than a direct end-user product.

Machine-learning-notes offers a comprehensive collection of educational materials for Machine Learning, Probabilistic Models, and Deep Learning. This open-source resource features over 2000 slides, detailed notes, and video links, continuously updated to reflect the latest research and concepts. It covers foundational mathematics, intermediate topics like Expectation Maximization and Markov Chain Monte Carlo, and advanced deep learning research areas such as Generative AI, Neural ODE, and Optimization Methods. The platform also hosts live online classes and seminars, providing in-depth explanations and practical demonstrations for a wide range of machine learning topics.

Synboli revolutionizes material science by integrating cutting-edge AI with groundbreaking, patented chemistry to accelerate the discovery and development of high-performance polymers. The platform leverages proprietary synthesis technology to quickly produce and test polymer samples, enabling access to new, never-before-seen structures. Its AI-powered platform utilizes specialized models to rapidly design novel polymer structures and accurately predict their properties. By combining in-silico and in-laboratory evaluation, Synboli dramatically reduces polymer development time from years to mere months. This innovative approach allows for the creation of unprecedented materials with unique and tailored properties, addressing key needs in industries such as cosmetics, pharma, transportation, defense, construction, and electronics.

Materiais de estudos sobre Data Science e Machine Learning is a comprehensive, open-source guide designed for individuals beginning their journey in Artificial Intelligence, Data Science, and Machine Learning. Hosted on GitHub, this repository organizes a wealth of study materials, predominantly free and in Portuguese. Users can find structured learning paths, recommendations for YouTube channels, online courses (from platforms like Udemy, Udacity, Coursera), and a curated list of books. It also includes sections on foundational mathematics, programming languages like Python and R, and specific libraries such as TensorFlow and Pandas. The guide aims to help beginners navigate the vast landscape of AI education, offering resources for different stages of learning and practical application.

Mathematics for Machine Learning and Data Science Specialization is a beginner-friendly online program created by DeepLearning.AI and taught by Luis Serrano. It aims to equip learners with the essential mathematical foundations required for machine learning and data science, including calculus, linear algebra, statistics, and probability. The specialization uses innovative pedagogy with easy-to-follow plugins and visualizations to make complex mathematical concepts intuitive. It is designed for individuals with at least high school mathematics knowledge and basic familiarity with Python, as labs demonstrate learning objectives using Python. The curriculum includes applied learning projects to help users represent data, apply vector and matrix operations, optimize functions, and assess model performance.

Saturdays.AI Guayaquil is part of the global Saturdays.AI community, dedicated to making AI accessible to everyone. The platform focuses on learning AI by doing, specifically through developing social impact projects that address issues like climate change, education, and disease diagnosis. They offer a flagship AI Saturdays program suitable for beginners, along with numerous free online courses covering topics like Python for AI and Data Science Fundamentals. The community emphasizes diversity, mentor support, and collaborative learning, connecting students globally. Saturdays.AI aims to empower individuals to use AI for the betterment of the world, fostering careers in leading AI organizations or supporting AI entrepreneurship.

Mr. Ranedeer AI Tutor is an innovative tool designed to unlock the full potential of GPT-4 for personalized learning. It offers a highly customizable prompt that allows users to adjust various aspects of their learning experience, including depth of knowledge (from elementary to Ph.D. level), learning style (visual, verbal, active, etc.), communication format (textbook, storytelling, Socratic), and tone. This flexibility enables the creation of a truly tailored AI tutor to suit diverse needs and interests. The tool supports multiple languages and includes commands for testing knowledge, configuring preferences, planning lessons, and continuing outputs. While it works on GPT-3.5 and Claude-100k, it is recommended for ChatGPT Plus with GPT-4 Code Interpreter for optimal effectiveness.

nn-zero-to-hero offers a detailed course on neural networks, guiding learners from foundational concepts to advanced topics. The curriculum is delivered through a series of YouTube video lectures, where participants code and train neural networks alongside the instructor. Each lecture is complemented by Jupyter notebooks, which capture the code built during the videos, and includes exercises to reinforce learning. The course covers essential topics such as backpropagation, language modeling, building multilayer perceptrons (MLPs), understanding activations and gradients, and implementing modern architectures like GPT. It is designed for individuals with basic Python knowledge and a general understanding of calculus, aiming to build competence and intuition in neural network development.

transcribe4u provides an AI-powered solution for converting audio and video files into text. The service emphasizes speed, accuracy, and affordability, allowing users to transcribe large files instantly without the need for subscriptions, accounts, or credits. It operates on a pay-as-you-go model, ensuring users only pay for the transcription services they utilize. The platform is designed for ease of use, offering a straightforward process to get speech-to-text conversions quickly and securely. This makes it a convenient option for individuals and professionals who require efficient transcription without long-term commitments.