Research & Education

VideoLLaMA2 is an open-source project designed to significantly advance spatial-temporal modeling and audio understanding within video-Large Language Models (LLMs). It offers a comprehensive framework for researchers and developers to explore and build upon state-of-the-art video analysis capabilities. The tool provides various pre-trained models, including vision-only and audio-visual checkpoints, supporting tasks such as multi-choice video QA, video captioning, open-ended video QA, and audio-visual QA. It includes detailed instructions for installation, running online and offline demos, and quick-start guides for training and evaluating custom VideoLLaMA2 models using datasets like VideoLLaVA. The project emphasizes its top performance on leaderboards like MLVU and VideoMME for ~7B-sized VideoLLMs.

VideoLLM-online is the official implementation of an Online Video Large Language Model for Streaming Video, presented at CVPR 2024. Unlike traditional models that process full videos offline, VideoLLM-online enables real-time interaction within a video stream, allowing it to proactively update responses based on activity changes or assist with next steps. It features a cheap and scalable method for synthesizing streaming data by transforming offline annotations into dialogue data using open-source LLMs. The inference method is parallelized, combining video encoding, LLM forwarding, and response generation asynchronously, achieving high speeds of 10-15 FPS on an A100 GPU for long-form videos up to 10 minutes. The tool is designed for researchers and developers working with streaming video analysis and real-time multimodal AI.

Vibe Voice Custom Voices is an innovative audio & music tool hosted on Hugging Face Spaces, designed for generating audio from text input. It offers robust support for both single and multi-speaker voices, making it versatile for various audio production needs. A key feature is its voice cloning capability, allowing users to upload audio clips for each speaker to replicate their voices accurately. The application provides a generated audio output, enabling creators to produce custom voice content efficiently. This tool is ideal for those looking to experiment with voice synthesis and cloning without complex setups, offering an accessible platform for audio creation.

VideoMamba is an innovative open-source state space model designed for efficient video understanding, specifically addressing the dual challenges of local redundancy and global dependencies in video data. It adapts the Mamba architecture to the video domain, overcoming limitations found in existing 3D convolution neural networks and video transformers. Its linear-complexity operator enables efficient long-term modeling, which is crucial for processing high-resolution and extended video content. The tool demonstrates scalability in the visual domain without requiring extensive dataset pretraining, thanks to a novel self-distillation technique. It also exhibits sensitivity for recognizing fine-grained short-term actions, superiority in long-term video understanding, and compatibility with multi-modal contexts, setting a new benchmark for comprehensive video analysis.

VideoCoF is an AI-powered tool designed for unified video editing, leveraging temporal reasoning to understand and apply changes based on user prompts. Users can upload an input video and specify desired edits through text prompts, and the application will generate a new video incorporating those changes. This capability makes it suitable for various content creation needs, allowing for precise modifications that consider the temporal context of the video. The tool is hosted on Hugging Face Spaces, indicating its accessibility and potential for community-driven development and use.

Thai Sentence Embedding Benchmark is a specialized AI tool designed to evaluate and rank Thai sentence embedding models. It features a comprehensive leaderboard that showcases the performance of different models across a variety of datasets and tasks relevant to the Thai language. Users can access detailed scores for each model, enabling them to compare and select the most suitable embeddings for their specific natural language processing (NLP) applications. This tool is particularly valuable for AI researchers and NLP engineers who require robust benchmarks for developing and optimizing Thai language models.

tts Text To Speech is a powerful text-to-speech (TTS) tool built on Next-gen Kaldi, available as a Hugging Face Space. It allows users to easily convert written text into spoken audio. The application provides options to select from various languages and TTS models, offering flexibility in voice output. Additionally, users can specify a speaker ID and adjust the speaking speed to customize the generated audio. The tool outputs the spoken text as a WAV audio file and also indicates the duration of the generated audio, making it suitable for a range of applications from content creation to research and development.

Video Transcription Smart Summary is an AI-powered tool available on Hugging Face that simplifies the process of extracting information from video content. Users can upload a video file, and the application automatically extracts the spoken audio, converts it into a full text transcription, and then generates a concise summary of the main points. This tool is particularly useful for quickly grasping the essence of video content without needing to watch the entire recording. It supports various applications, from academic research to content creation, by providing both detailed transcripts and easy-to-digest summaries.

Eyeware provides AI-powered head and eye tracking software that utilizes standard webcams and 3D sensors, eliminating the need for specialized hardware. Its flagship product, Beam Eye Tracker, transforms webcams into gaming eye trackers, enabling immersive gameplay in over 200 PC games and enhancing live streams with eye tracking overlays. The GazeSense Eye Tracking SDK allows developers to build custom eye tracking applications for 2D and 3D environments, with rapid prototyping available for Win/Linux. Eyeware also offers White Label Solutions for brands to integrate custom eye tracking apps and an iOS app for 6DoF head tracking and gaze bubble overlays. The technology is adaptable for various applications including gaming, automotive research, and academic research.

VIBE Image Edit DEMO serves as a demonstration tool for the VIBE-Image-Edit model, hosted on Hugging Face Spaces. This application empowers users to interact with AI-driven image editing by either uploading an existing picture and describing desired modifications or by generating entirely new images from a text prompt. It provides a hands-on experience with the capabilities of the VIBE-Image-Edit model, allowing for creative exploration and practical application of AI in visual content creation. The tool is designed for ease of use, enabling individuals to experiment with advanced image manipulation techniques without requiring deep technical expertise.

Research Topics Generator is an AI-powered tool designed to simplify the process of finding compelling research topics. It aims to inspire users by generating unique ideas that resonate with their interests and contribute significantly to academic discourse. The platform encourages users to reflect on past projects and ideas to identify areas they wish to explore further. Beyond topic generation, the website also offers resources like a Research Questions Generator and a tool to Find Scholarly Journals, making it a comprehensive starting point for academic research.

The NC State Data Science and AI Academy provides comprehensive resources for individuals and organizations looking to enhance their capabilities in data science and artificial intelligence. The academy offers a range of courses designed to build foundational knowledge and advanced skills, alongside consulting services to help apply these concepts in real-world scenarios. It also supports research enablement, fostering innovation and practical application of data science principles. The academy's mission is to empower its participants to think critically and work effectively with data, exploring various applications of data science and AI across different domains.

Enveda is a biotechnology company leveraging AI to revolutionize drug discovery. The platform reads and translates nature's hidden chemistry at unprecedented speed and scale, enabling scientists to access the chemical diversity of the natural world for the first time. By identifying and characterizing molecules found in nature, Enveda aims to discover medicines 4X faster than the industry average. This approach addresses the traditional challenges of purifying, identifying, and characterizing natural molecules, which are often time-consuming and costly. Enveda's mission is to accelerate the discovery of better medicines, offering hope to millions globally by harnessing billions of years of evolutionary intelligence.

DeepTutor is an AI learning companion designed to provide personalized learning assistance by transforming any document into an interactive experience. Users can upload textbooks, papers, and manuals to build AI-powered knowledge repositories, leveraging RAG and knowledge graph integration. The tool features smart problem-solving with a dual-loop reasoning architecture and multi-agent collaboration, delivering step-by-step solutions with precise citations. DeepTutor also generates custom quizzes based on knowledge bases or mimics real exam styles, and offers guided learning with interactive visualizations and adaptive explanations. It supports deep research through systematic topic exploration, web search, paper retrieval, and literature synthesis, alongside AI-assisted brainstorming.

Education AI Tools by AI Skynet serves as a comprehensive directory for artificial intelligence solutions tailored for the academic sector. This platform is designed to assist students, educators, and institutions in discovering and utilizing AI tools that enhance various aspects of learning and teaching. It features a wide array of tools for study assistance, content creation, research, and improving classroom productivity. The directory aims to streamline the process of finding relevant AI technologies, making it easier for users to integrate advanced AI capabilities into their educational workflows and achieve better outcomes.

CelebAMask HQ Face Parsing is an AI-powered tool available on Hugging Face Spaces designed for detailed facial feature identification. Users can upload a portrait photo, and the application will automatically parse and label various facial components such as skin, eyes, hair, and lips. The output includes a color-coded label image, clearly marking each region, and a blended image that combines the original photo with the labels. This tool is particularly useful for tasks requiring precise segmentation of facial elements, offering a straightforward interface for quick analysis. While the core functionality is free to use on Hugging Face Spaces, advanced compute options and enterprise features are available through Hugging Face's broader pricing plans.

ai-agent-papers is an Open Source repository that curates the latest research papers on AI agents, focusing on their applications and architectural technologies. The collection is updated biweekly, specifically adding papers that introduce distinctively new approaches or novel concepts rather than striving for comprehensive coverage. It categorizes papers by agent capabilities like environment, ideation, planning, reasoning, tool use, memory, and self-evolution, as well as by architecture (single-agent, multi-agent) and applications (embodied, digital, research agents). This resource is ideal for researchers and academics looking to stay current with cutting-edge developments in the AI agent field.

AAAI-2024-Papers is an open-source GitHub repository offering a comprehensive collection of research papers presented at the AAAI 2024 conference, one of the premier artificial intelligence conferences. This resource allows users to explore innovative research and provides opportunities to integrate code implementations for a deeper understanding of the presented work. The repository is actively maintained and encourages contributions from the community to ensure completeness and accuracy. It serves as a valuable resource for academics, researchers, and students to stay updated on the latest advancements across various AI domains, including computer vision, natural language processing, machine learning, and more.

applied-ml is a comprehensive curated collection of papers, articles, and tech blogs focusing on data science and machine learning in production. This resource is designed to help individuals understand how various organizations frame problems, implement machine learning techniques, and achieve tangible results. It covers a wide range of topics including Data Quality, Data Engineering, Feature Stores, Classification, Regression, Forecasting, Recommendation, Search & Ranking, Embeddings, Natural Language Processing, Computer Vision, Reinforcement Learning, MLOps, and more. Users can learn from real-world applications, research, and literature to better assess the ROI of ML projects and gain insights into what techniques work and why.

KI Park is a European innovation ecosystem dedicated to fostering the rapid development, testing, and application of Artificial Intelligence. It brings together innovative companies, startups, research institutions, and political and societal actors to combine their strengths. Members benefit from a neutral platform for cross-organizational and cross-sector collaboration, gaining access to cutting-edge infrastructure like HPC, data platforms, and private 5G for accelerated AI development and Proof of Concepts. The ecosystem offers various formats for knowledge exchange, community building, and innovation scouting, including challenges and a connect program to find suitable AI solutions. KI Park also hosts events and an AI Innovation Award to highlight impactful AI projects.

Awesome-System2-Reasoning-LLM is a meticulously curated open-source repository dedicated to tracking the latest advancements in System 2 reasoning within Large Language Models (LLMs). It serves as a vital resource for researchers and practitioners, offering a comprehensive collection of survey papers, research articles, and related projects. The repository is structured to cover various aspects of System 2 reasoning, including O1 replication, process reward models, reinforcement learning, MCTS/tree search, self-training, reflection, and benchmarks. It highlights the progression of AI systems from intuitive to deliberate reasoning models, providing insights into foundational technologies and future directions in this rapidly evolving field.

awesome-vector-search is a comprehensive, curated list of resources dedicated to vector search technologies. This open-source project compiles various vector search frameworks, engines, libraries, and cloud services, alongside relevant research papers. It serves as a valuable hub for anyone interested in vector similarity search, offering insights into standalone services like Qdrant and Milvus, and libraries such as Faiss and Annoy. The collection also highlights cloud services like Pinecone and Zilliz Cloud, making it an essential reference for understanding the evolving landscape of vector search. It's particularly useful for data scientists, machine learning engineers, and software developers looking to implement or explore vector embeddings in their applications.

Heuristica is an AI-powered learning platform designed to accelerate learning through a variety of interactive tools. Users can create visual concept maps to organize complex topics, which can then be instantly converted into flashcards, quizzes, study notes, or essays. The platform supports importing knowledge from diverse sources including PDFs, YouTube videos, websites, and academic databases like PubMed and arXiv, generating transcripts, summaries, and key takeaways. It also features an AI chat with models like Gemini, Claude, ChatGPT, and DeepSeek, allowing users to ask questions and turn conversations into study materials. Heuristica emphasizes non-linear and visual learning, making it ideal for students, researchers, and teachers.

DeepXDE is a comprehensive open-source library designed for scientific machine learning and physics-informed learning. It offers a wide array of algorithms, including physics-informed neural networks (PINN) for solving various types of differential equations (ODEs, PDEs, IDEs, fPDEs, sPDEs), and deep operator networks (DeepONet) for learning operators. The library supports five tensor libraries as backends: TensorFlow 1.x, TensorFlow 2.x, PyTorch, JAX, and PaddlePaddle. DeepXDE is highly configurable, allowing users to define complex domain geometries, various boundary conditions, and different neural network architectures. It also includes features like adaptive sampling, gradient-enhanced PINNs, and multifidelity learning, making it a versatile tool for researchers and engineers in scientific computing.