Citegeist is a free tool that helps you find articles related to a topic you are interested in. You need to seed it by entering the abstract of a relevant article or by uploading a relevant article. Citegeist not only finds related articles, but it generates a short report with info from the related articles also!
Citegeist works by using RAG info retrieval on the arxiv corpus of research papers.
#research #science #2ndOrderSearch
#Citegeist #arxivTools #RAG
Harvard ADS search engine has a very interesting search facet called "co-reads", that refers to articles or pages that other users have commonly viewed alongside the content you're looking at. In this case, the search engine is algorithmically inferring what the co-reads are as the article that I selected (listed at the top) was just published.
https://ui.adsabs.harvard.edu/abs/2025arXiv250208826M/coreads
Large Language Models (LLMs) struggle with hallucinations and outdated knowledge due to their reliance on static training data. Retrieval-Augmented Generation (RAG) mitigates these issues by integrating external dynamic information enhancing factual and updated grounding. Recent advances in multimodal learning have led to the development of Multimodal RAG, incorporating multiple modalities such as text, images, audio, and video to enhance the generated outputs. However, cross-modal alignment and reasoning introduce unique challenges to Multimodal RAG, distinguishing it from traditional unimodal RAG. This survey offers a structured and comprehensive analysis of Multimodal RAG systems, covering datasets, metrics, benchmarks, evaluation, methodologies, and innovations in retrieval, fusion, augmentation, and generation. We precisely review training strategies, robustness enhancements, and loss functions, while also exploring the diverse Multimodal RAG scenarios. Furthermore, we discuss open challenges and future research directions to support advancements in this evolving field. This survey lays the foundation for developing more capable and reliable AI systems that effectively leverage multimodal dynamic external knowledge bases. Resources are available at https://github.com/llm-lab-org/Multimodal-RAG-Survey.
TechRxiv is a very useful tool for exploratory search or idea generation type of activity. The wealth of subject headings that it shows for articles can be used for those types of activities, as shown in the screenshot of this example article. You need to create a free login account to use this service.
https://www.techrxiv.org/doi/full/10.36227/techrxiv.16444611.v2
#research $TechRxiv #AI #ML #computerScience #exploratorySearch #2ndOrderSearch
Scholar Inbox
This free AI tool is much better than RSS for automatically emailing you updates on a research field that you want to track. You do not want to share your weblink of the emails you are receiving from it as it contains your secret key for the tool.
MottG