Search AI Products and News

VLM2Vec-V2, a multimodal embedding framework developed by Salesforce Research and other institutions, breaks through the limitations of traditional models. Based on the Qwen2-VL architecture, this framework innovatively unifies image, video, and visual document retrieval tasks. It adds five new evaluation tasks to expand the MMEB dataset. With key technologies such as dynamic resolution and M-RoPE, it achieved an average score of 58.0 across 78 datasets, leading in performance, especially in video tasks. Although its document retrieval is slightly behind ColPali, it

Alibaba's WebSailor, an open-source AI agent framework, excels in BrowseComp-en/zh and SimpleQA tests. Features knowledge graph-based task generation and reinforcement learning with RFT/DUPO. Introduces data obfuscation for enhanced AI training.....

Alibaba opens WebSailor AI agent (32B/72B), outperforming closed-source models. Galaxy Securities highlights AI Agent economy growth, citing firms like Focus Tech and JinCai Tech. Open-source lowers entry barriers, accelerating industry progress.....

A deep dive into how Eureka AI addresses three major pain points in R&D - information overload, innovation bottlenecks, and evaluation difficulties - through core features such as a technical Q&A assistant and TRIZ theory innovation. It provides end-to-end AI support solutions from concept to implementation.

Recently, an open-source RAG (Retrieval-Augmented Generation) engine called RAGFlow has attracted significant attention in the industry. This enterprise-level AI tool, based on deep document understanding, provides companies with a brand-new solution for processing complex documents and achieving precise question answering through its powerful multimodal data processing capabilities and efficient workflows. RAGFlow: The Pioneer of Deep Document Understanding RAGFlow is a fully open-source RAG engine that focuses on deep document understanding, aiming to help businesses and individuals extract valuable information from massive amounts of unstructured data.

According to the latest prediction from Gartner, by 2028, 80% of generative AI business applications will be developed on existing data management platforms. This shift is expected to reduce development complexity and cut delivery time in half. Currently, the development of generative AI business applications mainly relies on combining large language models (LLMs) with corporate internal data, as well as evolving technologies such as vector search, metadata management, prompt design, and embedding techniques. However, without a unified management approach, companies may...

With the rapid advancement of generative AI, Retrieval-Augmented Generation (RAG) systems are becoming crucial for enhancing the accuracy and context relevance of Large Language Models (LLMs). Recently, an innovative RAG enhancement system called NodeRAG has garnered significant attention in the industry, its unique heterogeneous graph structure bringing a revolutionary breakthrough to RAG workflows. NodeRAG: A New Paradigm of Heterogeneous Graph-Driven RAG. NodeRAG is...

Google's NotebookLM has launched a new feature, "Discover Sources," designed to help users easily access relevant information from the web. As a powerful learning tool, NotebookLM allows users to describe a topic of interest, and the system quickly finds and summarizes relevant web content. Users can easily add these sources to their notebooks with a single click for convenient access and future use. This new feature offers a streamlined and user-friendly experience. Users in Noteboo...

In modern scientific research, accessing and discovering relevant literature is crucial for researchers. Therefore, Ai2PaperFinder was created, a powerful tool designed to help users easily find the academic papers they need. The platform brings together over 8 million full-text papers and over 108 million abstracts, offering broad and deep coverage. Ai2PaperFinder's unique strength lies in its powerful literature retrieval capabilities. Users can quickly find relevant research papers by inputting keywords. Whether it's a trending topic or a niche area...

Researchers at the Hebrew University of Jerusalem recently discovered that in Retrieval Augmented Generation (RAG) systems, the number of documents processed significantly impacts language model performance, even when the total text length remains constant. The research team conducted experiments using 2,417 questions from the MuSiQue validation dataset, each linked to 20 Wikipedia paragraphs. Two to four paragraphs contained relevant answer information, with the remaining paragraphs serving as distractors. To study the impact of the number of documents, the team created multiple data partitions, progressively reducing the number of documents from 20 to...

AMD recently announced GAIA, an open-source application designed to provide a highly efficient and localized method for running Large Language Models (LLMs). Currently supporting Windows and optimized for Ryzen AI 300 series processors, GAIA leverages the strengths of these processors for AI tasks. GAIA is a generative AI application enabling private LLM execution on personal computers, ensuring data privacy. Furthermore, GAIA utilizes...

Baidu Research has unveiled BGE-VL, a groundbreaking multimodal vector model poised to revolutionize information retrieval. This advanced model promises significant improvements in search accuracy and efficiency.

On March 6th, the Beijing Academy of Artificial Intelligence (BAAI) announced the open-sourcing of its multimodal vector model, BGE-VL. This achievement marks a significant breakthrough in the field of multimodal retrieval. The BGE-VL model achieves state-of-the-art results on various multimodal retrieval tasks, including image-text retrieval and compositional image retrieval, significantly improving the performance of multimodal retrieval.