Research & Education

Lighting-the-Darkness-in-the-Deep-Learning-Era-Open is an open-source project offering a comprehensive platform and resources for low-light image and video enhancement (LLIE) using deep learning. It features LLIE-Platform, a user-friendly web interface covering 14 popular deep learning-based LLIE methods like Zero-DCE++ and EnlightenGAN, allowing users to produce enhancement results. The project also provides the LLIV-Phone dataset, containing 120 videos (45,148 images) captured by various phone cameras under diverse illumination conditions. Additionally, it collects and categorizes numerous deep learning-based LLIE methods, datasets, and evaluation metrics, making it a valuable resource for researchers and developers in the field.

LLaVA-Med is a Large Language-and-Vision Assistant for Biomedicine, developed by Microsoft, that aims to achieve multimodal GPT-4 level capabilities in the biomedical domain. It leverages visual instruction tuning and is continuously trained using a curriculum learning approach, starting with general-domain LLaVA and then specializing in biomedical concept alignment and instruction-tuning. The tool is open-sourced under the MSR release policy and is intended for research use only, specifically for advancing visual-language processing and visual question answering in biomedicine. It is expressly prohibited for use in clinical care or for any clinical decision-making purposes. LLaVA-Med is built upon the PMC-15M dataset, which comprises 15 million figure-caption pairs from biomedical research articles, covering diverse image types like microscopy, radiography, and histology.

Long-Context is an open-source repository from Abacus.AI designed to provide code and tooling for Large Language Model (LLM) context expansion. It offers a comprehensive suite of evaluation scripts and benchmark tasks specifically tailored to assess a model’s information retrieval capabilities within expanded contexts. The repository details various experimental results, including different positional encoding schemes like linear scaling and fine-tuning approaches, and provides instructions for reproducing and building upon these findings. It also shares weights for best-performing models, such as the scale 16 model, which is expected to perform well up to 16k context lengths. The project includes novel evaluation datasets like an extended LMSys dataset and WikiQA (Free Form QA and Altered Numeric QA) to rigorously test models across varying context lengths and answer locations, addressing potential issues like models answering from pre-trained knowledge rather than provided context.

Arxiv Digest is an AI research tool hosted on Hugging Face Spaces, developed by AutoLLM. It is specifically designed to summarize research papers found on Arxiv, making it easier for users to quickly understand the core content of academic articles. Built with Gradio, the tool aims to streamline the research process for academics, students, and other researchers by providing concise summaries. While the current live website indicates a runtime error, the tool's intent is to offer an accessible way to digest complex scientific literature, enhancing efficiency in academic pursuits.

CampusKnot is an AI-powered teaching assistant designed to enhance the educational experience for both educators and students. It provides tools to foster classroom community, gather valuable feedback, and ensure academic integrity. The platform helps educators engage students more effectively and track their participation, while also identifying learning gaps in real-time. CampusKnot automates rewards to motivate students and aims to create a more impactful and interactive learning environment. Its focus is on streamlining teaching workflows and improving student outcomes through intelligent assistance.

LLPlayer is an Open Source media player specifically designed for language learning, offering a comprehensive suite of features to aid in language acquisition. It supports dual subtitles, allowing users to display two subtitle tracks simultaneously, including both text and bitmap formats. A standout feature is its AI-generated subtitles, powered by OpenAI Whisper, which provides real-time automatic subtitle generation from any video or audio. The tool also offers real-time translation with support for multiple engines like Google, DeepL, Ollama, and OpenAI, alongside context-aware translation using LLMs for higher accuracy. Users can benefit from real-time OCR for bitmap subtitles, a subtitles sidebar for easy navigation and word lookup, and instant word lookup with customizable browser searches. LLPlayer integrates with yt-dlp for playing online videos and supports browser extensions like Yomitan and 10ten, making it a versatile tool for language learners.

Bizzuka offers comprehensive AI training and upskilling programs designed to help businesses maximize AI adoption and efficiency. Their core offerings include the AI Strategy Canvas, a foundational tool for aligning AI initiatives with business objectives, and Scalable Prompt Engineering, which teaches organizations to create consistent and shareable prompts. The AI SkillsBuilder series provides role-oriented training for various departments, ensuring a cohesive AI strategy. Bizzuka focuses on practical, real-world applications, helping companies retain and upskill employees rather than replacing them. Their programs are continuously updated and developed in partnership with leading universities and industry experts.

Mario-AI is an open-source project available on GitHub that focuses on training an AI model to autonomously play the first level of Super Mario World. The system employs deep reinforcement learning, specifically deep Q-learning, and processes raw pixel input without relying on hand-engineered features. A key component is the integration of a Spatial Transformer, which helps the model make in-depth decisions based on the current game state. The methodology includes a replay memory for training, a unique reward function that accounts for movement and level progression, and an epsilon-greedy policy for action selection. The project details the model architecture, including branches for action history, screenshot history, and the last screenshot, and outlines the specific hardware and software requirements for installation and training, such as an NVIDIA GPU with CUDA and CUDNN, and Lua 5.1.

MiniGPT4-video offers official code for the Goldfish model, designed for understanding arbitrarily long videos, and MiniGPT4-video itself, tailored for short video understanding. This tool advances multimodal Large Language Models (LLMs) by integrating visual and textual tokens for comprehensive video analysis. Goldfish addresses challenges in long video processing through an efficient retrieval mechanism that identifies relevant video clips, making it suitable for applications like movies or TV series. MiniGPT4-video generates detailed descriptions for video clips, facilitating the retrieval process for Goldfish. The project also introduces the TVQA-long benchmark for evaluating long video comprehension and demonstrates significant performance improvements over existing state-of-the-art methods in both long and short video understanding.

ml-cvnets is a comprehensive computer vision toolkit developed by Apple, designed for researchers and engineers to efficiently train a wide array of computer vision models. It supports both standard and novel mobile- and non-mobile architectures for tasks such as object classification, object detection, semantic segmentation, and foundation models like CLIP. The library is built on Python 3.10+ and PyTorch, offering features like automatic data augmentation (RangeAugment, AutoAugment, RandAugment) and enhanced distillation support. It includes a model zoo with various CNNs (MobileNet, EfficientNet, ResNet) and Transformers (Vision Transformer, MobileViT, SwinTransformer), making it a versatile platform for advanced computer vision research and development.

mlimpl is an open-source repository collecting implementations of commonly used machine learning algorithms. It encompasses various domains including statistical learning, deep learning, and reinforcement learning. The implementations are primarily built using popular Python libraries such as NumPy, Pandas, and PyTorch, with some TensorFlow and MATLAB examples. This resource is designed to help users deepen their understanding of machine learning models and algorithms, offering well-documented code and guidance for challenging parts. Users can also modify the code to suit their specific needs, making it a flexible tool for both learning and practical application.

Node provides a supplementary code for Neural Oblivious Decision Ensembles, designed for deep learning on tabular data. This tool specializes in learning deep ensembles of oblivious differentiable decision trees, offering a robust approach to data analysis. While it can run on CPU, optimal performance is achieved with a GPU, which significantly reduces processing time. The implementation is noted to be memory inefficient, potentially requiring substantial GPU memory. It is compatible with popular Linux x64 distributions and MacOS, with Docker recommended for other systems. Users need Python (Anaconda recommended) and specific Torch versions to run the provided notebooks, which showcase classification and regression scenarios.

AI Manga Translator is an online platform designed to translate manga and comic images into multiple languages while preserving the original artwork and layout. Users can upload manga images and translate them with one click, choosing from preferred translation engines like DeepL, GPT, and Gemini. The tool supports vertical text and images, making it suitable for various comic formats. It offers a free plan with limited translations and paid options for more extensive use, including API access for high-volume needs. The platform also provides a Chrome extension for a more immersive reading experience on popular manga sites.

AI Singapore is a national program launched in May 2017, dedicated to fostering advanced AI capabilities within Singapore. It serves as a nexus for Singapore-based research institutions, AI startups, and established companies, facilitating collaborative efforts in use-inspired research, knowledge creation, tool development, and talent cultivation. The initiative focuses on key areas such as AI Research, Governance, Technology, Innovation, and Products, aiming to generate significant social and economic impact. It also offers various talent development programs, including the AI Apprenticeship Programme (AIAP) and LearnAI, to equip professionals and students with essential AI skills.

apic.ai is a leading specialist in automated pollinator monitoring, leveraging artificial intelligence and edge computing to provide reliable and fully automated behavioral assessments of bees and bumblebees. Their minimal-invasive camera system, installed at hive entrances, visually detects all movement in and out of the colony. The collected video footage is analyzed using AI algorithms, providing real-time data on activity, foraging behavior, pollen diversity, mortality, and individual size. This technology helps manufacturers and testers of plant protection products improve risk assessment, enables seed producers to develop practices that enhance crop pollination, and supports companies in designing pollinator-friendly habitats. The scientific approach ensures validated methods and verifiable results, making even subtle effects of substances and environmental factors visible.

PromptVisor is an advanced AI prompting tool designed to supercharge your experience with artificial intelligence. It offers access to leading AI models from Google, OpenAI, and Anthropic, enabling users to explore, experiment, and learn about AI and prompting techniques. The platform features dynamic prompting capabilities to enhance interaction and output quality. PromptVisor provides flexible pricing options, including pay-per-prompt or subscription models, and even offers free usage through referrals, making it accessible for various user needs.

awesome-neural-geometry is a comprehensive, curated collection of resources and research focused on the geometry of representations within the brain, deep neural networks, and related fields. This open-source repository, collaboratively generated on the Symmetry and Geometry in Neural Representations Slack Workspace, includes educational materials like textbooks, notes, courses, and videos covering topics such as Abstract Algebra, Differential Geometry, Information Geometry, Dynamics, Topology, and Geometric Machine Learning. It also lists computational neuroscience resources, datasets, software libraries like Geomstats and E3NN, and relevant conferences and workshops. The project is a work-in-progress and actively encourages contributions via pull requests.

Conversation Design Institute (CDI) is the world's leading training and certification institute for Conversational AI, offering comprehensive programs for individuals and businesses. CDI provides courses and certifications in areas like AI Ethics, AI Trainer, CDI Method Foundation, and Conversation Designer, equipping professionals with the skills to build human-centric and goal-oriented AI Assistants. Beyond individual training, CDI offers business solutions including assessment, consulting, team training, and workshops to help organizations deploy AI assistants at scale. Their CDI Standards Framework provides a systematic approach to developing conversational AI capabilities, ensuring alignment across mindset, skillset, culture, and systems. CDI also offers resources like free courses, webinars, and case studies, demonstrating their expertise with clients like HP, Vodafone, and Vandebron.

Courtroom5 is an award-winning legal platform designed to empower self-represented litigants in U.S. state and federal civil courts. It offers the LAW Accelerator™, a comprehensive program that provides case management, guidance, and custom document creation. The platform utilizes AI-powered tools to explain legal documents, analyze case facts, research relevant law, build arguments, and generate court filings. Users receive procedural guidance at every stage, enabling them to make informed strategic decisions. Courtroom5 also fosters a supportive community with workshops, office hours, and peer support, helping members succeed without a lawyer.

Playground is an open-source platform dedicated to AI research in multi-agent learning, primarily through the game Pommerman, a clone of Bomberman. Researchers and AI enthusiasts can submit agents they have trained to compete in regular competitions across three variants: Free For All (FFA), Team (2v2 with partial observability), and Team Radio (2v2 with limited communication). The platform aims to provide approachable benchmarks for multi-agent learning, foster contributions to multi-agent and communication research, and offer a competitive environment for AI development. It supports training agents with popular libraries like TensorForce and provides an example training script. Submissions are handled via Docker containers, ensuring agent safety and fair play.

PocketFlow-Tutorial-Codebase-Knowledge is an AI agent that analyzes GitHub repositories and local codebases to generate beginner-friendly tutorials. Built as a tutorial project for Pocket Flow, a 100-line LLM framework, it identifies core abstractions and their interactions within complex code. The tool then transforms this information into easy-to-understand explanations, often with visualizations. Users can specify GitHub repository URLs or local directory paths, include/exclude specific files, and set a maximum file size. It supports various LLM providers and can generate tutorials in different languages, making complex code accessible to a wider audience.

pytorch-pruning is an open-source PyTorch implementation of the paper "Pruning Convolutional Neural Networks for Resource Efficient Inference." This tool is designed to optimize deep learning models by reducing their size and improving inference speed. It achieves this by systematically removing filters from convolutional layers. The project demonstrates its effectiveness by pruning a VGG16-based classifier on a small dog/cat dataset, resulting in a significant 3x reduction in CPU runtime and a 4x reduction in model size. While currently pruning filters sequentially, the project notes that future improvements could include a single-pass pruning mechanism for greater efficiency. It also aims to support additional architectures beyond VGG, such as VGG with batch normalization.

prm800k is an open-source dataset and accompanying tools, released by OpenAI, that provides 800,000 step-level correctness labels for large language model (LLM) solutions to mathematical problems from the MATH dataset. This resource is crucial for researchers and developers aiming to enhance the mathematical reasoning capabilities of AI models through process supervision. The repository includes raw labels, instructions for labelers, Python grading logic for answer correctness, and non-standard MATH train/test splits. It also contains scored samples used to evaluate large-scale ORM and PRM models, making it a comprehensive resource for advancing AI in mathematics.

SAMv2 Mask Generator is an AI-powered tool available as a Hugging Face Space by lightly-ai, designed for image segmentation tasks. Users can upload any image and interactively define objects of interest by drawing bounding boxes around them. The tool then automatically generates precise segmentation masks, highlighting the selected objects within the image. This functionality is particularly useful for various computer vision applications, including object detection, image analysis, and data labeling, providing a straightforward method to isolate and analyze specific elements within visual data. It offers a practical solution for researchers, developers, and data annotators working with image datasets.