Research & Education

LLMSys-PaperList is a comprehensive, curated list of academic resources focused on Large Language Model (LLM) systems. This open-source repository provides a valuable collection of papers, articles, tutorials, slides, and projects, covering various aspects of LLM systems. Users can explore topics such as LLM training (pre-training, post-training, fault tolerance), serving (LLM serving, agent systems, multi-modal serving), system efficiency optimization, and LLM frameworks. The list also includes sections on industrial LLM technical reports, ML conferences, ML systems survey papers, LLM benchmarks, and related ML readings. It serves as an essential resource for researchers and practitioners looking to keep abreast of the rapidly evolving LLM research landscape.

VideoCrafter is an open-source video generation and editing toolbox developed by AILab-CVC, designed to overcome data limitations for high-quality video diffusion models. It features both Text2Video and Image2Video capabilities, allowing users to generate video content from text prompts or existing images. The tool has seen significant improvements with VideoCrafter2, offering better motion and concept combination even with limited data. It provides various checkpoints for different resolutions and models, including VideoCrafter1 and VideoCrafter2, available on Hugging Face. Researchers and developers can set up the environment via Anaconda and perform inference for text-to-video or image-to-video generation, or run a local Gradio demo. Technical reports and citations are provided for those interested in the underlying research.

ViTDet offers an unofficial PyTorch implementation for object detection, leveraging plain Vision Transformer backbones. Based on the ECCV'22 paper "Exploring Plain Vision Transformer Backbones for Object Detection," this tool provides researchers and developers with a robust framework to experiment with advanced object detection models. It includes pre-trained weights and logs for various ViT-Base and ViTAE-Base models on MS COCO, supporting both detection and segmentation tasks. The implementation is designed for PyTorch and integrates with mmcv, timm, and einops, making it suitable for those working with modern deep learning architectures in computer vision.

VITS2 is an unofficial implementation of a single-stage text-to-speech model designed to enhance the naturalness, efficiency, and quality of speech synthesis. It addresses limitations of previous models by proposing improved structures and training mechanisms, significantly reducing dependence on phoneme conversion for a fully end-to-end approach. The tool supports both single and multi-speaker TTS using datasets like LJ Speech and VCTK, or custom datasets. It provides installation instructions, environment setup with Conda, and examples for training and inference. VITS2 is a work in progress, with ongoing development to support features like speaker conditioning, high-resolution mel-spectrograms, and various architectural improvements.

VITS (Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech) is an advanced open-source project designed to generate highly natural-sounding audio from text. Unlike traditional two-stage TTS systems, VITS offers single-stage training and parallel sampling, improving efficiency without compromising quality. It incorporates variational inference augmented with normalizing flows and an adversarial training process to enhance generative modeling. A key differentiator is its stochastic duration predictor, which allows for synthesizing speech with diverse rhythms and pitches, reflecting the natural one-to-many relationship between text input and spoken output. This enables the creation of varied speech styles from the same text, making it suitable for a wide range of applications requiring expressive voice generation.

llm-hallucination-survey is an open-source repository offering a comprehensive reading list and survey paper focused on the critical issue of hallucination in large language models (LLMs). It categorizes hallucinations into input-conflicting, context-conflicting, and fact-conflicting types, providing extensive academic references for each. The resource is invaluable for researchers and academics seeking to understand the evaluation, explanation, and mitigation strategies for LLM hallucinations. It highlights how these issues undermine LLM reliability in real-world applications and serves as a central hub for cutting-edge research in this domain.

long-form-factuality is an open-source project from Google DeepMind designed to benchmark the factuality of large language models (LLMs) in long-form responses. The repository provides the official code for their paper "Long-form factuality in large language models." Key components include LongFact, a comprehensive prompt set of 2,280 fact-seeking prompts specifically designed for long-form responses, and the Search-Augmented Factuality Evaluator (SAFE), an automatic system for evaluating model responses. It also features F1@K, an extension of the F1 score for long-form settings, and an experimentation pipeline for benchmarking models like OpenAI and Anthropic using LongFact and SAFE. This tool is essential for researchers and developers focused on improving the factual accuracy of LLMs.

machineLearningDeepLearning is a GitHub repository dedicated to Li Hongyi's 2021 machine learning and deep learning course. It serves as a comprehensive resource for students and enthusiasts, offering lecture notes, presentation slides (PPTs), and homework assignments. The repository is actively maintained and updated, ensuring access to the latest course materials, including code examples in TensorFlow and PyTorch. Users can download the content via Git or directly from the website. It also provides links to course videos on Bilibili and data sets via Baidu Netdisk, making it a valuable self-study resource for those looking to deepen their understanding of machine learning and deep learning concepts.

Webscape.ai functions as an AI-powered marketing platform specifically designed for local businesses. It aims to streamline how these businesses manage their online marketing efforts. The tool provides AI-powered assistance, likely for tasks such as content creation, social media management, or customer engagement, though specific features are not detailed on the landing page. By leveraging artificial intelligence, Webscape.ai seeks to enhance productivity and simplify complex marketing processes for its target audience, allowing them to focus on their core business operations. The platform emphasizes ease of use, suggesting it is accessible to users without extensive technical or marketing expertise.

transformers-interpret is a model explainability tool specifically designed to integrate seamlessly with the Hugging Face Transformers package. It enables developers to understand the predictions of their transformer models with minimal effort, requiring only two lines of code to generate explanations. The tool supports explainers for both text and computer vision models, offering insights into how different parts of the input contribute to the model's output. It also provides visualization capabilities, allowing users to view attributions directly in notebooks or save them as PNG and HTML files for easier analysis and sharing. This functionality is crucial for debugging, improving model performance, and ensuring transparency in AI applications.

DeepSearch Labs is an AI-powered intelligence platform designed to help users find answers, quantify trends, and identify growth and risk impacts within their data. The platform supports various data formats, including Excel, PowerPoint, video, audio, JSON, and HTML, enabling comprehensive cross-database research. It assists users in generating insights and creating reports in multiple formats, allowing them to focus on strategic tasks. By fusing structured and unstructured data, DeepSearch Labs aims to transform complex information into actionable insights, providing recommendations for 'winners and losers' based on its analysis.

Conceptile is an AI-powered platform designed for exam preparation, offering a unique approach to learning by breaking down any goal into atomic concepts. It creates a personalized learning path for users, tracking mastery with precision and allowing them to focus on what they don't know. The platform features a dependency graph to ensure concepts are learned in the correct order and a 'Conceptile Score' to measure true mastery based on quizzes, flashcards, and time spent. It supports a wide range of certifications, licenses, and competitive exams globally, including ISTQB, AWS Solutions Architect, PMP, CPA, JEE Advanced, and GMAT. Conceptile offers bite-sized lessons, interactive content, and various question types to prove mastery, aiming to get users certified faster and with confidence.

vixtts-demo is a text-to-speech voice generation tool specifically designed for Vietnamese voice cloning. Built upon the XTTS-v2.0.3 model and utilizing the viVoice dataset, this tool allows users to generate speech in Vietnamese and potentially other languages. While primarily intended for demonstration, it offers an online version via Hugging Face Spaces for immediate use without installation. For local deployment, it supports Ubuntu or WSL2 systems, requiring specific hardware like an Nvidia GPU for optimal performance. The tool also includes features like automatic dependency installation and a Gradio demo link for easy interaction. It's important to note its limitations, such as subpar performance for short Vietnamese sentences and untested effectiveness with non-Vietnamese languages.

FavTutor connects students with top programming and data science tutors for live, one-on-one coding help. The platform offers 24/7 access to expert tutors across a wide range of subjects including Python, Java, C++, Machine Learning, Data Structures, and Web Development. Beyond live tutoring, FavTutor also provides AI-powered tools such as an AI Code Generator, AI Code Debugger, AI Data Analysis tool, and AI Code Converter to assist with coding tasks. Students can choose between written lessons and live sessions, with flexible pricing plans. The service aims to help students with homework, assignments, and interview preparation, ensuring personalized support and guaranteed satisfaction.

Machine-Learning-Zoomcamp offers a comprehensive, free 4-month course designed to teach machine learning engineering from end-to-end. Participants learn to build regression and classification models in Python, work with key algorithms like linear/logistic regression, decision trees, and deep learning, and then deploy them using Docker, FastAPI, Kubernetes, and AWS Lambda. The course provides flexible learning paths, including a live cohort with deadlines, automatic homework scoring, and project peer reviews, or a self-paced option. All materials are freely available, including pre-recorded lectures and homework assignments. It's an ideal resource for individuals looking to gain practical ML engineering skills and build a portfolio.

Textero is an AI-powered writing assistant designed to help students and researchers with academic content creation. It enables users to generate essays, research papers, and other academic texts efficiently, streamlining the writing process. Key features include an anti-plagiarism focus, citation support in various styles (MLA, APA, Chicago), and the ability to upload custom sources or instructions. Textero also offers additional tools like an AI detection remover, PDF summarizer, outline generator, and paraphraser. It supports over 10 languages, making academic success accessible globally, and is trained on academic datasets to ensure an appropriate tone and structure for scholarly work.

Word Genie is an advanced AI search platform designed to enhance online information discovery. It utilizes sophisticated natural language processing capabilities to deeply interpret user queries, moving beyond simple keyword matching. The platform's primary goal is to deliver highly relevant and contextually accurate results, thereby streamlining the research process. This tool is built to facilitate efficient knowledge acquisition across various domains, making it easier for users to find the precise information they need without extensive manual sifting. It aims to improve the overall efficiency and effectiveness of information retrieval for its users.

Fact Checking rocks! is a fact-checking tool hosted on Hugging Face Spaces, designed to verify claims and identify misinformation. It leverages advanced natural language processing techniques, specifically dense retrieval and textual entailment, to assess the accuracy of statements. The tool utilizes models such as sentence-transformers/msmarco-distilbert-base-tas-b for efficient information retrieval and microsoft/deberta-v2-xlarge-mnli for determining logical relationships between text. This combination allows for a robust baseline in fact-checking, making it valuable for researchers and individuals interested in verifying information.

Machine-Learning-Flappy-Bird is an open-source HTML5 project that showcases the application of machine learning in the classic Flappy Bird game. It leverages neural networks and a genetic algorithm to train a virtual bird to navigate through barriers optimally. The project provides a practical example of neuro-evolution, where an evolutionary algorithm (genetic algorithm) is used to train artificial neural networks. It details the neural network architecture, the main concept of machine learning implemented, and the step-by-step process of population evolution, including selection, crossover, and mutation. This project is ideal for those interested in understanding AI implementation in gaming contexts.

WebGPT is an innovative project demonstrating the capability to run GPT models directly within a web browser, leveraging the power of WebGPU. This implementation, crafted in under 1500 lines of vanilla JavaScript and HTML, functions as both a proof-of-concept and an educational resource for developers interested in on-device AI inference. It has been successfully tested with models up to 500 million parameters, with potential for larger models through further optimization. The project highlights the significant advancement WebGPU brings to web applications, offering near-native access to the GPU and compute shaders. Developers can easily run WebGPT by cloning the repository and using a compatible browser like Chrome Canary or Edge Canary, with options to use included models or import custom ones.

machine-learning-mindmap offers a detailed mindmap summarizing key Machine Learning concepts, ranging from fundamental Data Analysis techniques to advanced Deep Learning methodologies. This resource is designed to provide a clear overview of the field, which involves enabling computers to learn and make predictions without explicit programming. The mindmap is available as a downloadable PDF, with both standard and white-background versions. It covers essential topics such as the data science process, data processing steps, underlying mathematical principles, core ML concepts, and popular models. Additionally, it includes references to influential books and lectures, making it a valuable study aid for anyone looking to grasp the breadth of Machine Learning.

AI Chat - Your AI Friend is a revolutionary mobile application developed by Aiway LLP that offers a convenient and intelligent companion for daily tasks. It leverages artificial intelligence to provide solutions for various challenges, enhancing people's lives. The app is designed to be user-friendly, offering features like quick answers, grammar correction, and language translation. It aims to boost personal productivity and learning through its diverse AI-powered capabilities, making it a smart and accessible tool for everyday use. The app is available in all stores and countries, making it widely accessible to a global audience.

X-modaler is an open-source, high-performance codebase designed for cross-modal analytics, encompassing a wide range of tasks such as image captioning, video captioning, vision-language pre-training, visual question answering, visual commonsense reasoning, and cross-modal retrieval. It offers a unified collection of high-quality modules for state-of-the-art vision-language techniques, organized in a standardized and user-friendly manner. The codebase supports various models including LSTM-A3, Up-Down, Transformer, and TDEN across different tasks, providing baseline results and trained models for research and development. It requires Python 3.6+, PyTorch 1.8+, and other specific libraries, making it suitable for technical users and researchers in AI and machine learning.

The Artificial Intelligence Medical and Engineering Researchers Society (AIMER Society) is a dedicated platform for professionals, academics, and students focused on scientific research in biosciences and medical domains using Artificial Intelligence. The society fosters collaboration among medical doctors, engineers, industry researchers, and academicians. It actively develops novel algorithms for disease detection, advances AI use in healthcare for diagnosis and treatment, and explores AI applications in medical imaging like radiology, pathology, and dermatology. AIMER Society also offers various programs including workshops, internships, and certification courses, and publishes research in areas like "Artificial Intelligence in Medical Domain" and "Artificial Intelligence Trends."