Research & Education

Study Path Agent is an AI-powered tutorial builder designed to create structured learning paths for a wide array of topics. Users can generate comprehensive study plans complete with organized chapters, interactive dependency graphs to visualize learning progression, and curated YouTube video recommendations to supplement their studies. This tool aims to streamline the learning process by providing a clear, step-by-step approach to mastering new subjects, making it easier for individuals to acquire knowledge efficiently and effectively. It caters to various learning needs, from technical subjects like Docker & Kubernetes to creative skills like Photography Basics.

albert_zh is an open-source implementation of A Lite Bert for Self-Supervised Learning of Language Representations, specifically optimized for Chinese language processing. Based on the BERT architecture, ALBERT introduces improvements like factorized embedding parameterization and cross-layer parameter sharing, significantly reducing the number of parameters while retaining or even improving accuracy. This leads to faster training and inference times, making it suitable for real-time applications and resource-constrained environments. The repository provides various pre-trained ALBERT models for Chinese, including tiny, small, base, large, and xlarge versions, with options for TensorFlow, PyTorch, and Keras. It includes scripts for pre-training on custom data and fine-tuning on downstream tasks like semantic similarity prediction, with examples provided for the LCQMC dataset.

ASearcher is an open-source framework designed for large-scale online reinforcement learning (RL) training of search agents, aiming to advance Search Intelligence to expert-level performance. It provides model weights, detailed training methodologies, and data synthesis pipelines, making it fully committed to open-source development. Key features include a prompt-based LLM agent for autonomous QA pair generation, a fully asynchronous agentic RL framework that decouples trajectory collection from model training, and the ability to enable long-horizon search with tool calls exceeding 100 rounds. ASearcher achieves cutting-edge performance on challenging QA benchmarks like GAIA, xBench-DeepSearch, and Frames, demonstrating substantial improvements through RL training. It also offers comprehensive guidance for building and training customized agents.

attention_with_linear_biases is a GitHub repository offering the implementation of the Attention with Linear Biases (ALiBi) method for transformer language models. This method, presented in the ICLR 2022 paper 'Train Short, Test Long,' allows models to be trained on shorter input sequences (e.g., 1024 tokens) and then perform inference on significantly longer sequences (e.g., 2048 tokens or more) without requiring fine-tuning. The repository provides code and models for conducting experiments, specifically on the WikiText-103 dataset. ALiBi simplifies the positional encoding process by adding a linear bias to each attention score instead of using traditional position embeddings, which can improve performance even in non-extrapolating scenarios. The implementation details, including removing position embeddings and setting up the relative bias matrix, are clearly outlined.

Picterra is an AI-powered GeoAI analytics platform designed to provide environmental intelligence for monitoring, detection, and protection. It offers a mission control for environmental intelligence, giving sustainability teams visibility, focus, and verifiable proof to drive action and impact. The platform helps users detect risks early, understand critical issues, and respond with confidence, bringing clarity and control to sustainability performance at scale. Key solutions include anticipating production, ensuring EUDR compliance, verifying regenerative agriculture practices, and providing surface intelligence for mining, forestry, and carbon initiatives. Picterra augments existing ESG, supplier, and farm data with near-real-time GeoAI, surfacing land, risk, and compliance insights across global operations.

Awesome-Image-Colorization is a comprehensive, open-source collection of deep learning-based research papers focused on image and video colorization. This GitHub repository serves as a valuable resource for researchers and developers interested in the field, offering direct links to academic papers, their corresponding source code, and demo programs. The collection covers a wide array of colorization methods, including automatic colorization, user-guided colorization (based on scribbles, reference images, palettes, or text), and video colorization. It is continuously updated with new research, making it an essential reference for staying current with advancements in AI-powered colorization.

awesome-relation-extraction is a comprehensive, open-source curated list of resources dedicated to Relation Extraction, a crucial task in Natural Language Processing (NLP). This repository, inspired by other 'awesome' lists, compiles a wide array of research trends, surveys, and papers covering supervised, distant supervision, GNN-based, and language model approaches. It also features knowledge graph-based and few-shot learning methods. Additionally, the resource includes links to relevant datasets, videos, lectures, systems, and frameworks, making it an invaluable tool for researchers and practitioners looking to explore or advance their work in relation extraction.

awesome-text-summarization is a comprehensive Open Source guide designed to help users understand and implement various text summarization techniques. It delves into fundamental approaches such as extractive summarization, which selects key phrases from the original text, and abstractive summarization, which generates new sentences to convey the main ideas. The guide also explores combination approaches and the application of transfer learning in summarization. Beyond methodologies, it offers valuable resources including evaluation metrics, relevant datasets, useful libraries, academic articles, and research papers, making it an invaluable resource for anyone looking to tackle text summarization tasks.

awesome-text-to-image-studies is a comprehensive GitHub repository dedicated to summarizing papers and resources related to text-to-image (T2I) generation. This tool organizes academic studies based on various research directions, publication years, and conferences, making it an invaluable resource for researchers and academics. It includes sections on survey papers, conditional T2I generation, personalized T2I generation, and text-guided image editing. The repository also features a list of off-the-shelf T2I generation products and toolkits, along with a detailed 'To-Do Lists' section for future updates, ensuring it remains current with the latest advancements in the field. Users can find links to papers, project pages, and code where available, facilitating deeper exploration of the studies.

wondder develops immersive VR learning methods powered by AI, based on proven scientific research. The platform aims to improve professional skills, reduce bias, and grow mental health within organizations. By leveraging virtual reality, wondder creates engaging and effective training experiences that allow users to practice and develop critical skills in a simulated environment. This AI-powered approach ensures that learning is personalized and impactful, addressing specific needs for professional development and well-being. The focus on scientific research underpins the methodology, ensuring that the training is not only innovative but also evidence-based for optimal results.

Plattform Lernende Systeme is a prominent German AI platform and expert network dedicated to advancing the understanding and responsible application of Artificial Intelligence. It brings together nearly 200 members from scientific research, industry, and civil society to facilitate interdisciplinary exchange and public dialogue on AI topics. The platform's core mission involves developing position papers on the opportunities and challenges presented by AI, as well as formulating recommendations for its ethical and effective deployment. Established in 2017 by the German Federal Ministry of Education and Research, it serves as a crucial hub for national AI strategy, promoting research, innovation, and transfer into practical applications across various sectors. The platform also monitors AI developments in Germany, showcases success stories, and provides educational resources.

Awesome-GPTs is a comprehensive, open-source GitHub repository featuring a vast collection of over 1000 GPTs, categorized into 10 distinct groups. This resource also includes more than 80 leaked prompts, offering valuable insights and examples for users interested in GPT applications. The project aims to provide a centralized hub for discovering and understanding diverse GPT implementations, making it a useful tool for developers, researchers, and AI enthusiasts. Its community-driven nature encourages contributions and continuous expansion of the collection, fostering an environment for shared knowledge and exploration within the AI community.

awesome-graph-classification is a comprehensive collection of graph classification methods, encompassing embedding, deep learning, graph kernel, and factorization papers. This resource provides researchers and practitioners with a curated list of important papers, often accompanied by their reference implementations. It serves as a valuable starting point for exploring various techniques in graph-based machine learning, offering insights into areas like network embedding, graph convolutional networks, and graph attention networks. The repository also links to relevant graph classification benchmark datasets, making it a practical tool for academic research and development in the field.

awesome-uncertainty-deeplearning is an extensive open-source repository dedicated to predictive uncertainty estimation in deep learning models. It compiles a wide range of resources including surveys, academic papers, datasets, and code implementations. The collection covers various methodologies such as Bayesian methods, ensemble techniques, sampling/dropout-based approaches, post-hoc methods, data augmentation, and evidential deep learning. It also addresses applications in classification, regression, object detection, natural language processing, and more. This repository is an invaluable resource for researchers and practitioners looking to explore, understand, and implement uncertainty quantification in their deep learning projects.

Awesome-diffusion-model-for-image-processing is a comprehensive, open-source GitHub repository that serves as a summary of diffusion model-based image processing techniques. It covers a wide array of applications such as image restoration, enhancement, coding, and quality assessment. The repository is continuously updated with new related works and includes detailed sections on image super-resolution, video restoration, inpainting, denoising, dehazing, deblurring, and medical image restoration. It also features benchmarks, datasets, and models for image/video compression and quality assessment, making it an invaluable resource for researchers and practitioners in the field.

Awesome-CV-MasterHub is an open-source repository providing a curated list of recent Computer Vision (CV) papers. It serves as a valuable resource for researchers and practitioners looking to stay abreast of the latest developments in the field. The platform organizes papers by various CV sub-domains such as Image Classification, Object Detection, Semantic Segmentation, Image Generation, and Vision-LLMs. Users can easily browse through the list and find links to papers, with code links provided where available. The repository is actively maintained, with updates to ensure the most recent and relevant articles are included, typically retaining up to 200 papers per area. It encourages community contributions through issues and pull requests for any overlooked papers.

Awesome-LLMs-as-Judges is a dedicated repository for researchers and practitioners interested in the field of Large Language Models (LLMs) as evaluators. It serves as the official companion to the survey paper "LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods," offering a continuously updated collection of relevant academic papers. The repository categorizes papers by functionality (performance evaluation, model enhancement, data collection), methodology (single-LLM, multi-LLM, human-AI collaboration systems), application areas, and meta-evaluation. It also includes a "Daily Papers on LLMs-as-Judges" section, automatically retrieving and updating the latest arXiv papers, making it a one-stop resource for staying current with advancements in this rapidly evolving domain.

Climate AI Nordics is a collaborative network of researchers dedicated to leveraging AI technologies to tackle the urgent global challenge of climate change. The network focuses on creating and promoting AI solutions that support both climate change mitigation, aiming to reduce its severity, and adaptation, helping societies adjust to its effects. Recognizing the current climate emergency, Climate AI Nordics emphasizes a multifaceted approach, including policy change, limiting activities contributing to climate change, and bolstering societal resilience. The initiative brings together researchers from Nordic countries to accelerate progress in this critical field, facilitating the sharing of expertise and resources to develop impactful AI solutions for a sustainable future.

Squirro is an Enterprise GenAI platform designed for regulated industries, offering secure, private, and accurate AI-driven intelligence at scale. It helps organizations boost productivity, cut costs, and enhance decision-making. The platform features an Enterprise AI Platform Overview, Taxonomy and Ontology Management, a Security and Trust Center, and On-Premises Enterprise AI deployment options. Its core AI engine includes Agentic AI, Knowledge Graphs, AI Guardrails, a Privacy Layer, and a Classifier. Squirro provides solutions for Knowledge Management, Service Intelligence, Enterprise Search & Insights, Risk, Audit and Compliance, and AI Strategy & Roadmap, catering to industries like Banking & Financial Services, Manufacturing & Automotive, Government, Insurance, Healthcare and Life Sciences, and Telecom & Utilities.

awesome-llm-interpretability is a comprehensive, curated list of resources dedicated to understanding and interpreting Large Language Models (LLMs). This open-source GitHub repository serves as a central hub for researchers and practitioners, offering a wide array of tools, academic papers, insightful articles, and community links. It covers various aspects of LLM interpretability, from visualization platforms like The Learning Interpretability Tool and Comgra, to specific research on attention mechanisms, neuron behavior, and factual associations within models. The resource is invaluable for anyone looking to delve into the inner workings of LLMs, debug neural networks, analyze training processes, or explore mechanistic interpretability.

Awesome-LLM-Long-Context-Modeling is a comprehensive, open-source GitHub repository dedicated to curating essential papers and blogs focused on Large Language Model (LLM) based long context modeling. This resource is designed for researchers and practitioners who need to stay abreast of the latest advancements in enabling LLMs to process and understand extended sequences of text. It provides a structured collection of academic papers and insightful blog posts, making it easier to navigate the rapidly evolving landscape of long-context LLMs. The repository is freely available, offering a valuable knowledge base for anyone working on or interested in the challenges and solutions related to long-term memory and context handling in LLMs.

The aws-machine-learning-university-accelerated-cv repository offers comprehensive educational materials for the Machine Learning University (MLU) Computer Vision class. This open-source resource is designed to make machine learning accessible to everyone, providing a structured path to learn about widely used ML techniques and apply them to real-world problems in computer vision. The class includes three lectures covering topics such as Intro to Computer Vision, Neural Networks, Convolutional Neural Networks, Image Datasets, and advanced CNN architectures like VGGNet and ResNet. It also features a final project where students practice working with a real-world computer vision dataset. The repository contains slides, Jupyter notebooks for hands-on practice, and datasets, making it a valuable tool for self-paced learning and experimentation.

BLiTZ is an Open Source Python library designed to facilitate the creation of Bayesian Neural Network layers within PyTorch. It enables users to introduce uncertainty into their models and quantify the complexity cost, adhering to principles from the "Weight Uncertainty in Neural Networks" paper. The library provides core weight sampler classes, allowing for extensibility and integration with various PyTorch layers. BLiTZ aims to simplify the process of implementing Bayesian Deep Learning, making it accessible for tasks like regression with confidence interval estimation, which can be crucial for more reliable decision-making in various applications.

Biomni is a general-purpose biomedical AI agent designed to autonomously execute a wide range of research tasks across diverse biomedical subfields. It integrates cutting-edge large language model (LLM) reasoning with retrieval-augmented planning and code-based execution, enabling scientists to dramatically enhance research productivity and generate testable hypotheses. Biomni supports various LLM providers like Anthropic, OpenAI, Azure OpenAI, Gemini, and Groq, and can be configured via environment variables or a .env file. It features a data lake for biomedical information, a Gradio interface for interactive use, and configuration management for consistent settings. Additionally, Biomni can generate PDF reports of execution traces, supports Model Context Protocol (MCP) for external tool integration, and includes a Know-How Library of best practices. It also offers Biomni-R0, a specialized reasoning model for biology, and Biomni-Eval1, a comprehensive evaluation benchmark.