AI Agents & Automation

Awesome-LLMs-Evaluation-Papers is a comprehensive collection of research papers specifically curated for the evaluation of large language models (LLMs). The papers within this resource are systematically organized, following the structure of a detailed survey on LLM evaluation methodologies. This collection serves as a valuable resource for both researchers and practitioners in the AI field, providing them with essential materials to deepen their understanding of LLM evaluation techniques and to guide their own evaluation processes. It aims to simplify the discovery of relevant academic work in this rapidly evolving domain.

AstraSilica Technologies is a company dedicated to advancing semiconductor technology, with a primary focus on applications in artificial intelligence (AI), the Internet of Things (IoT), and 5G connectivity. The company's mission is to foster innovation and promote sustainable practices within the semiconductor industry. AstraSilica emphasizes pushing the boundaries of current semiconductor capabilities and is committed to cultivating a collaborative environment that unlocks the full potential of its employees.

Persontyle AI serves as a digital transformation partner, concentrating on the design, development, and scaling of human-centered applied artificial intelligence solutions. Their service offerings encompass strategy, design, and talent development, specifically tailored for applied AI, Industrial Internet of Things (IIoT), and enterprise blockchain technology platforms. The core mission of Persontyle AI is to leverage these advanced technologies to significantly enhance human potential.

Neural Tech provides comprehensive AI engineering services, focusing on the development and scaling of custom artificial intelligence solutions for a global clientele. Their offerings encompass strategic consulting to guide organizations through their AI journey, alongside robust technology development to build tailored AI systems. Neural Tech emphasizes flexible business models designed to mitigate risks and expedite the achievement of desired outcomes for their clients.

CoreInsightsAI empowers organizations to transform their business through advanced AI and data solutions. The platform specializes in the implementation of Generative AI, providing full-stack development capabilities to integrate these technologies seamlessly. It offers strategic consulting services to guide businesses in their AI journey and develops custom AI/ML models tailored to specific needs. CoreInsightsAI focuses on helping businesses extract actionable intelligence from their data, enabling data-driven decision-making and innovation.

Awesome_Think_With_Images is a comprehensive repository dedicated to resources and research papers concerning Large Vision Language Models (LVLMs). The primary focus is on exploring and documenting how these models can effectively leverage visual information to perform sophisticated tasks such as complex reasoning, strategic planning, and content generation. This repository serves as a valuable companion to a survey paper on the subject, offering a detailed overview of the current landscape and advancements in the field of LVLMs and their visual capabilities.

Exult Technology Crafts provides comprehensive AI and data innovation services designed to help businesses leverage advanced technologies. Their offerings span AI consulting, where they guide organizations in developing effective AI strategies, to custom AI product development, creating tailored solutions for specific business needs. Additionally, they specialize in data management solutions, ensuring data is properly handled and utilized. Key services include machine learning model development and data engineering, all aimed at empowering businesses with robust AI and data capabilities.

cgcnn is a software package designed to leverage Crystal Graph Convolutional Neural Networks (CGCNN) for the prediction of material properties. The package provides functionalities to train a CGCNN model using a user's customized dataset, enabling tailored predictions based on specific research or application needs. Additionally, it can predict material properties for novel crystal structures by utilizing a pre-trained CGCNN model, offering a powerful tool for materials science research and development. This allows for efficient analysis and discovery of new materials with desired characteristics.

bpemb is a comprehensive collection of pre-trained subword embeddings, leveraging Byte-Pair Encoding (BPE) for efficient representation. It supports an extensive array of 275 languages, making it highly suitable for diverse multilingual applications. The embeddings are meticulously trained on Wikipedia data, ensuring broad coverage and quality. These embeddings are specifically designed to serve as effective input for various neural models within the realm of natural language processing tasks, facilitating advancements in areas like machine translation, text classification, and information retrieval across many languages.

BrowserGym provides a Gym environment specifically designed for automating tasks on the web. It allows developers and researchers to simulate various browser interactions, creating a controlled setting for training artificial intelligence agents. The tool is particularly suited for implementing reinforcement learning approaches to develop AI that can autonomously perform web-based tasks, offering a platform for experimentation and development in web automation.

CodeFuse-CGM is a sophisticated framework that leverages graph-based large language models (LLMs) specifically tailored for real-world software engineering challenges. It uniquely combines the power of code graphs with advanced LLMs to provide a robust platform for various code-related operations. The framework is designed to support critical tasks such as rewriting code, efficiently retrieving relevant code snippets, reranking code based on specific criteria, and comprehensively reading and understanding code within a repository-level context. This integration aims to streamline and improve the accuracy of software development workflows.

Code-act is a specialized tool designed for the development of Large Language Model (LLM) agents. Its core functionality revolves around enabling these agents to utilize executable code actions, thereby expanding their capabilities. The tool's primary goal is to consolidate various agent actions into a single, unified action space, which is intended to enhance the overall performance and efficiency of LLM agents. This approach is backed by research, as indicated by its association with a paper presented at ICML 2024.

Impleko AI specializes in providing comprehensive AI services to businesses looking to innovate and grow. The company focuses on taking initial concepts and developing them into fully functional, market-ready AI products. Key offerings include AI-powered product development, intelligent automation solutions to streamline workflows, and seamless AI integrations into existing systems. Impleko AI caters to a diverse range of sectors, including healthcare, eCommerce, finance, and education, aiming to help clients optimize their operations and enhance customer interactions through advanced AI technologies.

Coconut is a specialized codebase developed for training large language models. Its core functionality revolves around enabling reasoning within a continuous latent space, a key feature for advanced AI research. This tool serves as the official implementation of a research paper, indicating its foundation in academic rigor and cutting-edge methodology. It is specifically tailored for professionals in the AI field, including AI researchers and NLP engineers who are actively involved in developing and refining sophisticated language models.

Chidori is a reactive runtime specifically engineered for the development of durable AI agents. This tool empowers developers to construct persistent and reactive AI workflows, ensuring that agents can respond dynamically to various events and effectively maintain their state across interactions. It focuses on the orchestration of AI agents, providing the necessary infrastructure to build robust and reliable AI systems that can operate consistently over extended periods. Chidori aims to simplify the creation of AI applications that require long-term memory and event-driven responses.

Jithasoft Solutions is a technology company focused on digital transformation. They provide specialized expertise in key areas such as data automation, generative AI, and MLOps. The company collaborates with organizations across diverse sectors, aiming to help them succeed in the digital era by implementing innovative and effective technology solutions.

Nyun AI is a specialized platform for optimizing AI models, aiming to significantly enhance their efficiency. It achieves this by reducing computing costs and accelerating inference speeds, making AI deployments more economical and responsive. A key capability is enabling the deployment of large, complex models on devices with more limited computational resources. The platform employs advanced techniques such as pruning, quantization, and distillation to create highly efficient deep-learning models.

PlomX Tech is an IT services and consulting firm dedicated to delivering comprehensive software solutions. Their expertise spans a wide range of technologies, including custom web and mobile application development. A core focus is on advanced technologies such as blockchain development and artificial intelligence (AI) applications. PlomX Tech aims to partner with businesses globally to conceptualize, develop, and deploy digital experiences that meet specific operational and strategic needs.

Pong AI is a platform focused on improving artificial intelligence by providing federated context data services. It facilitates collaboration and governance around AI models, specifically addressing the 'AI context deficit.' The platform achieves this by integrating real-time situational awareness directly into the AI model development and inference processes. Its primary goal is to optimize AI/ML operations through a deeper contextual understanding and robust governance frameworks.

Quantech Saudi is a technology company focused on delivering software and artificial intelligence solutions. Their core expertise lies in developing scalable and user-centered applications tailored for diverse industries. This includes the creation of custom web and mobile applications, as well as the integration of advanced artificial intelligence capabilities into their solutions. Quantech aims to provide innovative technological advancements to meet specific business needs.

Seldon provides a comprehensive platform designed for enterprises to streamline their machine learning operations. It enables the deployment, management, and scaling of ML models with a focus on real-time capabilities. Key aspects include enhanced observability into model performance and cost-efficient modularity, allowing organizations to optimize their ML infrastructure. Seldon Core 2 emphasizes a data-centric approach, promoting standardization and interoperability across various deployment infrastructures.

TreviAI GmbH provides comprehensive AI consulting services, guiding businesses through the integration and management of artificial intelligence models. Their platform is designed to facilitate the optimization and transformation of business processes by leveraging AI solutions. A key feature of TreviAI's offering is its ability to combine diverse data sources and various use cases within a unified environment. The company also develops intelligent agents specifically engineered to enhance workflow efficiency and streamline operations for their clients.

Trust Ray Robotics specializes in the manufacturing of industrial robots and the provision of related industrial services. The company leverages a combination of advanced engineering knowledge and AI-based software to design, develop, and operate its robotic solutions. Its core mission is to facilitate industrial transformation and enhance production environments for its clients. By integrating sophisticated robotics and AI, Trust Ray Robotics aims to help manufacturers significantly reduce their operational costs and improve the overall integration of their production processes.

Servera is a no-code platform designed to empower users to build software applications without writing any code. It provides instant APIs and integrates AI capabilities, streamlining the development process. Key features include database integration and the ability to export AI builder routes. The platform aims to simplify the underlying infrastructure, making application development more accessible and efficient for its users.