Research & Education

Hands-On Graph Neural Networks Using Python, published by Packt, is a comprehensive resource for machine learning practitioners, data scientists, and students interested in graph neural networks. The book covers fundamental concepts, practical implementation using Python and PyTorch Geometric, and applications ranging from natural language processing to drug discovery. It teaches users how to classify nodes, graphs, and edges, predict graph topologies, combine heterogeneous data sources, and forecast events. The resource includes all necessary code organized into folders, along with detailed instructions for setting up the required software and hardware, including Python, PyTorch, PyTorch Geometric, and optional GPU acceleration with CUDA and cuDNN. It also provides a list of required Python libraries and offers alternative access via Google Colab.

Aithor is an AI-powered writing assistant designed to help students and writers with various academic writing tasks, including essays, literature reviews, case studies, and research papers. It offers an undetectable AI writer feature, ensuring generated content bypasses AI detection. Users can access a vast database of over 10 million academic sources with PDF access, facilitating thorough research. The tool also provides automatic reference list generation in various styles like MLA, APA, and Chicago, and includes grammar and spelling checkers. Aithor helps users structure their writing, refine arguments, and maintain their unique writing style, making it ideal for overcoming writer's block and enhancing academic output.

Graph-fraud-detection-papers is a comprehensive, curated list of Graph/Transformer-based papers and resources specifically focused on fraud, anomaly, and outlier detection. This open-source repository is designed to facilitate deep research in the field by providing an organized collection of academic works. Beyond just a list, it offers an interactive dashboard for viewing, filtering, and searching papers, enhancing accessibility and usability. Additionally, the project includes a local RAG-based LLM chatbot, pre-loaded with 250 publicly accessible papers, which users can deploy for personal use to interactively explore the research landscape. The resource covers a wide range of topics, from LLM and Transformer papers to various deep learning and non-deep-learning graph papers across different years, along with toolboxes, datasets, and survey papers.

gpt-fast is a highly efficient PyTorch-native transformer text generation tool, designed for minimal latency and a compact codebase of under 1000 lines of Python. It supports advanced features like int8/int4 quantization, speculative decoding, and tensor parallelism, making it suitable for high-performance applications. The tool is compatible with both Nvidia and AMD GPUs and is intended to showcase optimal performance achievable with native PyTorch, rather than serving as a comprehensive framework. Developers are encouraged to copy, paste, and fork the codebase for their specific needs, leveraging its efficiency for various LLM inference tasks.

Tella is an all-in-one screen recorder and video editor designed for creating professional product demos, tutorials, and courses. It provides a comprehensive suite of tools for recording screen, camera, and microphone, with instant upload capabilities. The platform features AI-powered video editing, allowing users to edit videos like a document by leveraging transcripts, removing filler words, enhancing audio, and applying dynamic layouts and automatic zoom effects. Tella supports recording in up to 4K resolution and offers various sharing options, including instant shareable links, embed codes, and high-quality downloads. It also includes analytics to track video performance and collaboration features for teams.

Keras-transformer is a Python library designed to facilitate the construction of (Universal) Transformer models within the Keras framework. It offers essential building blocks such as positional encoding, embeddings, attention masking, and memory-compressed attention. The library also supports Adaptive Computation Time (ACT) and provides a general implementation for BERT models, making it highly relevant for Natural Language Processing (NLP) tasks. Developers can flexibly piece together multi-step Transformer models using its Keras layers, or customize existing components like self-attention and activation functions. The repository includes practical examples demonstrating its application in language modeling with BERT and GPT on datasets like WikiText-2.

KaJ Labs is a research organization founded in 2017 by J. King Kasr, dedicated to supporting teams building next-generation internet technologies. The foundation focuses on early Web3 projects, prioritizing innovation in areas like AI and Deep Learning. Key initiatives include Lithosphere (LITHO), a cross-chain network powered by AI; Imagen Network (IMAGE), the first decentralized social network with AI-generated content management; and Colle AI (COLLE), a multi-chain AI NFT platform for creating unique NFTs from prompts. KaJ Labs also develops Lithic, a smart-contract language for AI workflows, and LAX, an adaptive digital currency for the Lithosphere ecosystem.

Clema is an AI-powered platform designed for Institutional Research and Effectiveness teams in higher education. It acts as an AI copilot, enabling users to query complex federal education databases such as IPEDS, College Scorecard, and EADA using natural language. This eliminates the need to navigate intricate interfaces, providing instant access to data insights. Clema supports various copilots for specific data sets like Pell Grant, Cohort Default Rate, DAPIP, and PSEO, streamlining data requests and analysis for university professionals. The tool aims to enhance efficiency in institutional research by offering quick answers to data questions through conversational AI.

BuildPrompt is an AI-powered platform designed for secure document analysis and knowledge retrieval. It allows users to upload various document types, including PDFs and .DOCX files, and query their content using natural language. The tool offers features like Dynamic Data Extraction for processing complex datasets, Intelligent Prompting for accurate answers in multiple languages, and Multimodal Vision Capabilities for visual and textual analysis. BuildPrompt also provides Automated Workflows, data benchmarking, and a Database for semantic insights using natural language and semantic SQL. It emphasizes security and compliance, offering multi-industry support and the ability to connect to existing data environments via REST APIs, making it suitable for organizations needing to extract key information and streamline AI workflows.

Instructgpt-prompts is an open-source project offering a comprehensive collection of instruction-based prompts and strategies specifically designed for GPT-instruct and GPT-3.5 models. It focuses on leveraging the instruction-following capabilities of these language models for various text generation and classification tasks. The project highlights the sensitivity of models to phrasing and position within prompts, providing guidance on how to structure prompts effectively using useful verbs and directional words. It covers common use cases such as classification, generation, transformation, and comparison, offering specific instruction verbs for each. This resource is particularly valuable for understanding prompt engineering principles for base and SFT-only models, aiming to align large language models with human intent.

Big Blue AI specializes in transforming data into actionable insights, fueling strategic business decisions through its AI, Analytics, and Engineering expertise. The company offers customized consulting and training services to help organizations build a thriving, data-driven future. Their solutions combine AI and Analytics technologies with strategic consulting and tailored data skills training to boost efficiency, foster collaboration, and drive sustainable growth. Key offerings include data solutions, strategic consulting, tailored training, and data scientists' recruitment services. Big Blue AI empowers clients to achieve unprecedented success in today's data-driven world, whether implementing AI-powered chatbots, developing dynamic dashboards, or integrating ML algorithms for predictive analytics.

Ilya-sutskever-recommended-reading is a curated list of approximately 30 influential deep learning research papers, compiled from a reading list reportedly given by Ilya Sutskever to John Carmack. This resource is designed for individuals seeking to build a strong foundational understanding of deep learning concepts and methodologies. The list includes seminal works such as "Attention Is All You Need," "ImageNet Classification with Deep Convolutional Neural Networks," and "The Unreasonable Effectiveness of Recurrent Neural Networks." Each entry typically provides links to the paper, PDF, and sometimes associated blogs or code, making it a valuable starting point for in-depth study and research in the field of artificial intelligence and machine learning.

KwaiAgents is an open-source project from KwaiKEG at Kuaishou Technology, offering a generalized information-seeking agent system built with Large Language Models (LLMs). The project includes KAgentSys-Lite, a simplified agent system with core functionalities, and KAgentLMs, a series of LLMs specifically tuned for agent capabilities such as planning, reflection, and tool-use. It also provides KAgentInstruct, a large dataset of agent-related instructions for fine-tuning, and KAgentBench, a comprehensive benchmark for evaluating agent performance across various dimensions. KwaiAgents supports both local and cloud-based LLM usage, making it a versatile platform for researchers and developers in the AI agent space.

Large-Language-Model-Notebooks-Course is an unofficial, open-source repository offering a practical, hands-on course on Large Language Models (LLMs) and their applications. It's designed for engineers, researchers, and developers, providing updated notebooks and new examples beyond its associated book. The course is divided into three sections: Techniques and Libraries, Projects, and Enterprise Solutions, covering topics such as OpenAI API, Hugging Face, vector databases, LangChain, fine-tuning (PEFT, LoRA, QLoRA), and model evaluation. It includes practical projects like building chatbots, NL2SQL translators, RAG systems, moderation systems, and data analyst agents. Most notebooks are hosted on Colab or Kaggle, with accompanying Medium articles for detailed explanations.

LLM-PowerHouse is a comprehensive GitHub repository designed as an ultimate resource for developers, researchers, and enthusiasts looking to leverage Large Language Models (LLMs). It provides a curated guide with tutorials, best practices, and ready-to-use code for custom training and inferencing of LLMs. The resource covers foundational concepts in mathematics, Python, neural networks, and natural language processing, progressing to advanced topics like LLM architecture, instruction dataset building, pretraining, fine-tuning, RLHF, and evaluation. It also includes sections on model compression, inference optimization, open LLMs, and resources for cost analysis. LLM-PowerHouse aims to empower users to build intelligent applications and push the boundaries of natural language understanding.

LLM-Agents-Papers is a GitHub repository that curates a comprehensive list of research papers focused on Large Language Model (LLM) based agents. The repository categorizes papers by various aspects including Survey, Technique For Enhancement, Planning, Memory Mechanism, Feedback & Reflection, RAG, Search, Interaction, Role Playing, Conversation, Game Playing, Human-Agent Interaction, Tool Usage, Simulation, Application (across diverse fields like Math, Chemistry, Biology, Physics, Geography, Art, Medicine, Finance, Software Engineering), Research Automation, Workflow, Automatic Evaluation, Training, Fine-tuning, RL, DPO, Scaling, Single-Agent Framework, Multi-Agent System, Stability, Safety, Bias, Hallucination, Infrastructure, Benchmark & Evaluation, Environment & Platform, Dataset, and Others. It also provides recommendations for other related paper lists, making it an invaluable resource for academic research and development in the LLM agent domain.

MachineLearning_notes is a GitHub repository serving as a centralized hub for machine learning and deep learning resources. It curates an extensive collection of materials, including cheat sheets, awesome lists for deep learning, Keras, TensorFlow, PyTorch, JAX, Graph Neural Networks, and Transformers. The repository also features links to influential books, courses, tutorials, videos, and papers across various ML/DL domains, including genomics, audio, image, and language models. It encourages community contributions, making it a dynamic and evolving resource for anyone interested in these fields.

Machine-Learning-Notebooks is a comprehensive GitHub repository offering a curated collection of Jupyter notebooks for individuals looking to refresh or learn machine learning and deep learning concepts. The notebooks cover a wide array of topics, including fundamental NumPy operations, various data preprocessing techniques, different regression and classification algorithms, clustering methods, model evaluation metrics, and advanced areas like reinforcement learning, natural language processing, and neural networks. It also includes specialized notebooks on dimensionality reduction and model selection. The resource is compiled from various online sources, making it a valuable, centralized hub for structured learning and practical application of ML/DL concepts.

MachineLearning-QandAI-book is an open-source GitHub repository offering supplementary materials for Sebastian Raschka's "Machine Learning Q and AI" book. It's designed for individuals who have a foundational understanding of machine learning and AI but wish to deepen their knowledge and address specific gaps. The repository includes practical code examples and detailed explanations across various topics, such as multi-GPU training, finetuning transformers, generative AI models, and confidence intervals for ML. Users can find discussions and code for concepts like embeddings, self-supervised learning, few-shot learning, and different types of neural networks. The resource is ideal for those looking to stay current with the latest technologies and implement advanced machine learning techniques in their work.

MLQuestions offers a comprehensive collection of technical interview questions specifically curated for Machine Learning and Computer Vision Engineer roles. The resource covers a wide array of topics, including Natural Language Processing (NLP), bias-variance trade-off, gradient descent, overfitting/underfitting, regularization, PCA, and various neural network concepts like ReLU, convolutions, and batch normalization. It also provides practical implementation questions for algorithms and data structures. Beyond questions, MLQuestions includes preparation resources such as an ML Engineer Interview Course and recommendations for foundational textbooks, making it an invaluable resource for job seekers in the AI/ML domain.

ml-class is a comprehensive resource offering machine learning lessons and teaching projects specifically designed for engineers. It features bite-sized projects that enable users to learn various aspects of deep learning from the ground up. Each project comes with an associated video, typically around 10 minutes long, guiding users through the concepts. The curriculum is structured to progress from beginner to more advanced topics, though users are free to explore projects out of order. While it assumes some proficiency in Python, no prior machine learning background is required, making it accessible for engineers looking to enter the field. The platform also includes additional benchmark projects for further learning and contribution.

nlp-journey is an open-source GitHub repository offering a comprehensive collection of resources for Natural Language Processing (NLP). It includes a wide array of documents, academic papers, and code examples covering key NLP areas such as Topic Models, Word Embeddings, Named Entity Recognition, Text Classification, Text Generation, Text Similarity, and Machine Translation. The repository is structured to provide easy access to foundational and advanced research, making it an invaluable resource for students, researchers, and practitioners in the field of NLP. It serves as a central hub for exploring the latest advancements and understanding the underlying principles of various NLP techniques.

Alelo is a leading AI-powered simulation training platform that leverages generative AI avatars to provide personalized and scalable learning experiences. Learners engage in challenging conversations with socially intelligent avatars in realistic scenarios, receiving immediate feedback to improve their skills. This approach has been shown to accelerate learning significantly compared to conventional methods. Alelo offers solutions for individuals, employee upskilling and reskilling, student education, and government personnel training, including culture and language training for overseas deployments. The platform also features AI-powered Content Navigators for content discovery and Resource Navigators for patient education, reducing the burden on care teams and guarding against misinformation.

pdftochat is an AI-powered tool designed to facilitate interactive conversations with PDF documents. Users can upload their PDFs and engage in a chat-like interface to ask questions, summarize content, and extract information quickly. The tool leverages a robust tech stack including Next.js for the framework, Mixtral through Together AI for the large language model, and Chroma Cloud for hybrid vector search, ensuring efficient information retrieval. LangChain.js is utilized for the RAG (Retrieval Augmented Generation) code, while Bytescale handles PDF storage and Vercel provides hosting. Clerk manages user authentication, making it a comprehensive solution for anyone needing to interact with their documents more dynamically. It's built for rapid deployment and offers a clear path for self-hosting.