Research & Education

awesome-ml-model-compression is a comprehensive, open-source curated list of resources dedicated to machine learning model compression and acceleration. This GitHub repository compiles research papers, articles, tutorials, libraries, and tools covering various techniques such as quantization, pruning, distillation, and low-rank approximation. It serves as an invaluable reference for researchers, developers, and students looking to optimize deep neural networks for efficiency, speed, and reduced memory footprint. The repository is actively maintained and welcomes contributions, making it a collaborative effort to advance the field of efficient AI model deployment.

InternUtopia is a comprehensive simulation platform designed for advanced Embodied AI research and development. It addresses the challenges of real-world data collection by offering a robust Sim2Real paradigm. Key features include GRScenes, a dataset of 100k interactive, finely annotated scenes covering 89 diverse categories, and GRResidents, an LLM-driven Non-Player Character system for social interaction and task generation. The platform also provides GRBench, a collection of embodied AI benchmarks for assessing various capabilities like Object Loco-Navigation, Social Loco-Navigation, and Loco-Manipulation. InternUtopia supports diverse robots, policies, and physically accurate interactive object assets, making it an ideal environment for scaling the learning of embodied models.

ecg is an open-source AI tool designed for advanced arrhythmia detection and classification in ambulatory electrocardiograms. Leveraging a deep neural network, it aims to achieve cardiologist-level accuracy in analyzing ECG data. The tool is hosted on GitHub, providing a platform for researchers and developers to access, train, and test models. It includes instructions for setting up a Python environment, installing dependencies with or without GPU support, and training/testing models using configuration files. This makes it a valuable resource for medical diagnosis, research, and the development of AI-powered healthcare solutions.

NRLPapers is a valuable resource for anyone interested in network representation learning (NRL) and network embedding (NE). This GitHub repository, maintained by THUNLP, compiles a list of essential academic papers in the field, categorized for easy navigation. It covers survey papers, various models including basic, attributed, dynamic, heterogeneous information, bipartite, and directed networks, as well as other advanced models. Additionally, it highlights applications in natural language processing, knowledge graphs, social networks, graph clustering, community detection, and recommendation systems. The repository also mentions OpenNE, an open-source toolkit for NE/NRL, providing a standard training and testing framework with implemented models like DeepWalk, LINE, and GCN. This makes NRLPapers an indispensable guide for researchers and students seeking to explore or contribute to the domain of network representation learning.

llm_note is an extensive collection of notes and resources designed for individuals looking to deepen their understanding of large language models (LLMs). It covers fundamental aspects such as LLM inference, the intricate structure of transformer models, and detailed code analysis of various LLM frameworks. Additionally, the resource delves into high-performance computing (HPC) topics, offering insights into Triton and CUDA programming for optimizing LLM operations. The project also features a self-made large model inference framework, built with Triton and PyTorch, emphasizing lightweight design and ease of use. This framework aims to simplify GPU kernel development by leveraging PyTorch-like syntax for Triton operators, bypassing the complexities of direct CUDA programming. It includes support for advanced features like FlashAttention and PageAttention, and demonstrates significant speed improvements over standard libraries for certain LLM models.

LLMForEverybody is a comprehensive resource designed to make large language model (LLM) knowledge accessible to everyone. It features a curated database of LLM interview questions, covering topics from foundational concepts to advanced applications, ideal for job seekers preparing for spring/autumn recruitment drives. The platform also offers a systematic approach to studying LLM research papers, starting from the 2017 Transformer paper and progressing through key technological advancements. Complementing these resources are continuously updated video tutorials available on Bilibili and YouTube, ensuring a multi-modal learning experience. The goal is to equip users with the knowledge to confidently discuss LLMs with interviewers and advance their careers.

SPSSAU is an intelligent online statistical analysis platform designed to make data analysis accessible and efficient. It provides a comprehensive suite of over 500 analytical methods, such as T-tests, ANOVA, regression, correlation, clustering, and factor analysis. The platform features a "drag-and-drop" interface, allowing users to easily select analysis items and generate results with a single click. SPSSAU integrates AI to intelligently analyze data, suggest appropriate analytical options, and automate the generation of standardized analysis reports, including textual interpretations and visualizations. It also offers data processing functions like data labeling, encoding, and variable generation, alongside automatic chart generation. The platform supports both English and Chinese, offers robust security with阿里云 servers and data backup, and provides academic and enterprise-level research report services.

Macaw-LLM is an exploratory open-source project that pioneers multi-modal language modeling by seamlessly combining image, video, audio, and text data. Built upon the foundations of CLIP, Whisper, and LLaMA, it offers a unique approach to integrating diverse data types. Key features include simple and fast alignment to LLM embeddings, one-stage instruction fine-tuning, and a newly created multi-modal instruction dataset covering image and video modalities. The architecture leverages CLIP for image/video encoding, Whisper for audio encoding, and LLaMA (or Vicuna/Bloom) as the core language model. This tool is designed for researchers and developers to explore and advance the field of multi-modal AI.

MachineLearningNotes is a GitHub repository containing a comprehensive collection of personal notes on various machine learning topics. These notes are primarily derived from video lectures and are formatted as Markdown files. The repository covers a wide range of subjects, including linear regression, classification, dimension reduction, SVM, exponential family, probabilistic graphical models, EM, GMM, variational inference, MCMC, HMM, LDS, particle filters, CRF, Gaussian networks, Bayesian linear regression, Gaussian processes, RBM, spectral methods, neural networks, partition functions, and approximate inference. Users are advised to download the content and view it locally using Typora for proper rendering of mathematical formulas and graphs, as GitHub's native rendering may not fully support these elements. The project also provides a link to a Bilibili video series as a reference.

The NSF AI Institute for Artificial Intelligence and Fundamental Interactions (IAIFI) is a leading institute dedicated to pioneering interdisciplinary research at the intersection of AI and physics. It aims to advance fundamental physics knowledge, from the smallest building blocks of nature to the largest structures in the Universe, while simultaneously galvanizing AI research innovation. IAIFI focuses on developing AI approaches that incorporate first principles from physics and tackles challenging problems such as precision calculations and gravitational wave detection. Beyond research, IAIFI is committed to empowering the next generation of AI+Physics talent through various educational programs, including fellowships, summer schools, and workshops, and building a dynamic AI+Physics community through events and collaborations.

PreciseRoIPooling is an open-source implementation of the Precise RoI Pooling (PrRoI Pooling) method, as proposed in the ECCV 2018 paper "Acquisition of Localization Confidence for Accurate Object Detection." This tool is designed to improve object detection accuracy by providing an integration-based average pooling method for RoI Pooling, which avoids quantization and offers a continuous gradient on bounding box coordinates. Unlike traditional RoI Pooling or RoI Align, PrRoI Pooling allows for the optimization of RoI coordinates through continuous gradients. The repository provides implementations for PyTorch (versions 1.0+ and 0.4) and TensorFlow (2.2), primarily supporting CUDA. It is a valuable resource for researchers and developers working on advanced object detection models.

T2F is an open-source deep learning project designed for generating realistic human faces from textual descriptions. It leverages a combination of StackGAN and ProGAN architectures to achieve high-quality image synthesis. The project processes textual descriptions through an LSTM network to create a summary vector, which then informs the GAN's generation process. While the original project is not actively maintained, a T2F 2.0 version is planned to utilize MSG-GAN for improved image generation. The tool is implemented using PyTorch and requires specific dependencies for setup and training, making it suitable for researchers and developers interested in generative AI.

T81-558 is a comprehensive GitHub repository containing teaching materials for the T81-558: Keras - Applications of Deep Neural Networks course offered at Washington University in St. Louis. This resource focuses on the Keras/TensorFlow version of the curriculum, covering a wide array of deep learning topics. Students and enthusiasts can explore modules on Python preliminaries, Pandas for machine learning, TensorFlow and Keras fundamentals, training for tabular data, regularization, CNNs for vision, Generative Adversarial Networks (GANs), Kaggle competitions, transfer learning, time series analysis, reinforcement learning, and deploying models with Flask. The repository includes Jupyter notebooks for practical application and a complete textbook available on GitHub, making it an invaluable resource for learning and applying deep neural network concepts.

Teaching-material is a comprehensive open-source repository designed to provide preparatory materials for machine learning and deep learning courses. Developed for use at prestigious institutions like Stanford and Cornell, it focuses on foundational skills in Python and Numpy. The repository includes tutorials essential for students embarking on advanced machine learning studies, covering topics relevant to probabilistic graphical models, deep learning, applied machine learning, and deep generative models. It offers an iPython notebook for interactive learning, which can be followed directly on GitHub or executed locally, making it a flexible resource for both self-study and structured academic environments.

Singa is an open-source distributed deep learning platform developed by Apache. It provides a flexible architecture for training deep learning models across various devices and distributed environments. The platform supports a wide range of deep learning models and offers tools for efficient computation and data management. Singa is particularly well-suited for researchers and developers who require a robust and scalable solution for their large-scale AI projects, enabling them to build, train, and deploy complex neural networks. Its open-source nature fosters community contributions and allows for extensive customization to meet specific project requirements.

prml is an open-source GitHub repository dedicated to Christopher Bishop's seminal work, "Pattern Recognition and Machine Learning." It provides a comprehensive collection of Jupyter notebooks and Python code that implement many of the algorithms and replicate numerous graphs presented in the book. This resource is invaluable for students, professors, and researchers looking to understand and apply machine learning concepts through practical examples. The repository covers a wide range of topics, from basic probability distributions and linear models to more advanced subjects like neural networks, Gaussian processes, and hidden Markov models, making it a robust companion for academic study and practical implementation in the field of pattern recognition and machine learning.

VisionScope-R2 is a demonstration of a multimodal Vision Language Model (VLM) collection, designed to process images in conjunction with user-provided text instructions. Users can upload a picture and type a question or instruction, and the application will generate a clear, written response. This includes functionalities such as generating descriptive captions, performing Optical Character Recognition (OCR) to extract text from images, or providing direct answers to specific questions about the image content. The tool is built on Hugging Face Spaces, showcasing various AI models like DeepCaption, SkyCaptioner, SpaceThinker, Core, and SpaceOm, making it suitable for exploring and testing diverse multimodal AI capabilities.

tree-of-thought-llm is the official open-source implementation of the Tree of Thoughts (ToT) framework, designed for deliberate problem-solving with large language models. This repository, published after the NeurIPS 2023 paper, includes the core code, example prompts, and model outputs, enabling researchers and developers to explore and replicate the ToT methodology. It supports various problem-solving tasks like the game of 24, text generation, and crosswords, offering different thought generation and state evaluation methods. Users can easily set up new tasks and customize prompts, making it a flexible tool for advancing research in LLM reasoning and problem-solving.

InterStand is an AI-powered tool focused on improving reading comprehension and learning by leveraging translation and analysis capabilities. It is designed to help users understand and interpret various texts more effectively. The tool aims to facilitate language learning and support educational research, making it suitable for a diverse audience including students, educators, and researchers. By providing AI-driven assistance, InterStand seeks to simplify complex texts and bridge language barriers, ultimately enhancing the learning experience and promoting deeper understanding of content.

vstar is an open-source project offering a PyTorch implementation of the research paper "V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs." This tool is designed for researchers and developers working with multimodal large language models, specifically focusing on enhancing visual search capabilities. It includes pre-trained models for both VQA LLM and visual search, along with comprehensive training datasets derived from LAION-CC-SBU, COCO, and GQA. Users can set up a local Gradio demo for interactive use and evaluate models using the V*Bench benchmark. The project also provides detailed instructions for pre-training and instruction tuning of the VQA LLM, making it a valuable resource for advancing research in guided visual search within LLMs.

XVerse is an online demonstration of an AI image generation tool developed by ByteDance. Users can generate images by providing a textual prompt and up to four reference images, enhancing creative control. The application also offers practical features such as auto-captioning for descriptions and face cropping, which can be useful for refining generated images or preparing them for specific uses. Hosted on Hugging Face Spaces, XVerse provides a platform for exploring advanced image synthesis capabilities.

Yet Another LLM Leaderboard is a tool designed for comparing and ranking various large language models (LLMs). It aims to provide a platform for users to track and assess the performance of different models. The tool is hosted on Hugging Face Spaces, indicating its accessibility and potential for community contributions. However, the current live status shows a runtime error, preventing immediate use or detailed feature exploration. Despite this, its core purpose is to offer insights into LLM capabilities, which is valuable for researchers, developers, and anyone interested in the evolving landscape of AI models.

WizardLM 1.0 Uncensored Llama2 13b GGML is an AI chatbot tool designed for generating text responses to user prompts. Users can input any question or request, and the application aims to provide detailed and helpful answers. While the tool's description highlights its text generation capabilities, the current live website indicates a runtime error preventing its operation. This suggests that the model or its associated files are currently inaccessible or improperly configured, leading to a 'Repository Not Found' error. The tool is hosted on Hugging Face Spaces and is intended for AI model experimentation and chatbot development, potentially for educational purposes and research.

SuppCheck is an AI-powered supplement decision assistant designed to help users make informed choices about dietary supplements. The tool evaluates supplements through a science-based lens, linking claims to real evidence and highlighting what an ingredient can and cannot do. It aims to cut through influencer hype by providing clear, evidence-backed reasoning. SuppCheck tailors answers to a user's personal context, ensuring relevance and accuracy for confident supplement decisions. This approach helps users understand the efficacy and potential benefits of various supplements based on scientific data.