Christoph Lange-Bever

This paper provides an #overview of #processing #steps and #evaluation #methods for #channel #charting and proposes a novel dissimilarity metric that takes into account #angular-#domain #information as well as a novel #deep #learning-#based #metric. Furthermore, the authors suggest a method to fuse dissimilarity metrics such that both the time at which channels were measured as well as similarities in channel state information can be taken into consideration while learning a #channel #chart. By applying both classical and deep learning-based manifold learning to a dataset containing #sub-#6 GHz distributed #massive #MIMO #channel #measurements, they show that their metrics outperform previously proposed dissimilarity measures. ----Phillip Stephan, Florian E., @Stephan Ten Brink More details can be found at this link: https://lnkd.in/gZtvsxF3

2

#bibframe #cataloguing #ShareVDE Research Article A Comparative Evaluation of the Share-VDE Search System Authors: Jim Hahn, Head of Metadata Research, University of Pennsylvania Libraries Kayt Ahnberg, Assessment and User Experience Researcher, Princeton University Libraries Liliana Giusti Serra, Research Associate (School of Information Sciences), University of Illinois at Urbana-Champaign Abstract The Share-VDE search system shifts the library discovery paradigm from record-based indexing and retrieval to that of linked data entity exploration. This paper reports results of iterative testing of multiple versions of the Share-VDE interface. The testing included remote user experience (UX) interviews with a total of twenty participants across four rounds of tests spanning two years. The comparison among participants encompassed catalogers, students of all levels, and faculty. Synthesizing IFLA LRM user tasks with interface evaluation methods supported the qualitative inquiry into how linked data systems in general, and BIBFRAME specifically, can support search system objectives. Publication date 2024-07-03 Journal title Cataloging & Classification Quarterly #openaccess ▶ https://lnkd.in/dxbATXHJ

11

Welcome to read the article "Integrated Gradients for Feature Assessment in Point Cloud-Based Data Sets" which is written by Mr. Markus Schwegler, Prof. Christoph Müller and Alexander Reiterer. This excellent article was published in issue 7 in 2023 and has been viewed 1313 times and cited 3 times! Article link: https://lnkd.in/gMCsed5z MDPI Fraunhofer IPM Furtwangen University Albert-Ludwigs-Universität Freiburg (Albert Ludwig University of Freiburg) #pointcloud #neuralnetwork #integratedgradients

2

#EarlyCareer #talk at #IJCAI2024 by🗣️Julia Neidhart, Technische Universität Wien: Transforming Recommender Systems: Balancing Personalization, Fairness, and Human Values ➡️https://lnkd.in/dK3Nieyr Abstract: Recent advancements in recommender systems highlight metrics beyond accuracy, including diversity, serendipity and fairness. This paper examines the integration of Large Language Models into recommender systems, focusing on challenges such as interpretability, bias, and user autonomy. LLMs offer enhanced personalization capabilities but also introduce concerns regarding transparency and ethical implications. This work discusses ongoing research efforts aiming to develop transparent, fair, and contextually aware systems. Our approach seeks to prioritize user wellbeing and inclusivity, contributing to a more equitable and functional digital environment through advanced technologies and interdisciplinary insights. #XAI #LLMs #InclusiveTech #NextGenAI #AI TU Wien Informatics

3

Our next video is out! This is the first of a 2-part video in which Prof. Semih Salihoğlu explains about Resource Description Framework (RDF), a popular data model in graph DBMSs. If you're curious about graph modeling and are intimidated by the terminology used (especially when it comes to RDF), this video has you covered! ✅ Fundamentals of RDF: What are resources, URIs, literals, and (subject, predicate, object) triples, and how do these form a graph? ✅ Advantages of using RDF as a data model for complex and irregular domains and its flexibility in handling irregularities and connections between objects ✅ How RDF allows you to query both data and schema information in a uniform way. In the 2nd video (coming soon!), we will also go over RDF's powerful knowledge representation and reasoning capabilities, and their potential in the age of AI. Stay tuned! https://lnkd.in/gZM79U44

30

AI automation based on papers arxiv Recent research on AI automation from arXiv papers highlights several key developments and considerations: ## Enhancing Trust in AI Agents A study explores new challenges in building trust for Large Language Model (LLM)-based AI automation agents[1]. It analyzes existing literature on trust in AI and identifies specific considerations for the latest generation of automation agents. The paper also evaluates how emerging products address these trust issues. ## AutoDev Framework Researchers have introduced AutoDev, a fully automated AI-driven software development framework[2]. This system allows users to define complex software engineering tasks that are then autonomously planned and executed by AI agents. AutoDev enables operations like file editing, building, testing, and git operations within a secure Docker container environment. ## Formal Modeling for AI in Automation A formal model has been proposed to provide clear and structured documentation of AI applications in automation systems[4]. This approach aims to capture information about automation components, AI software, and technical processes, addressing the need for comprehensive documentation in long-lived industrial systems. ## Anthropomorphization and Trust A study investigated how anthropomorphized descriptions of AI systems influence people's trust[5]. Interestingly, the research found that anthropomorphizing language alone did not significantly increase trust. Factors like the type of product and user demographics appeared to have a greater impact on trust levels. These papers demonstrate the ongoing efforts to improve AI automation across various domains, from software development to industrial systems, while addressing critical issues like trust, documentation, and human perception. Citations: [1] [2308.05391] Enhancing Trust in LLM-Based AI Automation Agents https://lnkd.in/dTubDjxN [2] [2403.08299] AutoDev: Automated AI-Driven Development - arXiv https://lnkd.in/gm77JeA2 [3] Artificial Intelligence - arXiv https://lnkd.in/d2qpQdXn [4] A Formal Model for Artificial Intelligence Applications in Automation ... https://lnkd.in/dysGd4V9 [5] "AI" to Probabilistic Automation: How Does Anthropomorphization of ... https://lnkd.in/dBnXgp4n

5

1 Kommentar

Using 𝗣𝗿𝗶𝗻𝗰𝗶𝗽𝗮𝗹 𝗖𝗼𝗺𝗽𝗼𝗻𝗲𝗻𝘁 𝗔𝗻𝗮𝗹𝘆𝘀𝗶𝘀 (𝗣𝗖𝗔), Vansh Jatana demonstrates how to simplify complex datasets by reducing dimensions while retaining essential information. PCA not only aids in visualizing data in 2D/3D but also preserves significant variance. https://lnkd.in/dG_2XDFN #TheDeepHub #DeepInData #DataVisualization #MachineLearning #DataScience

2

This week on the ShareTIGR lab blog (https://lnkd.in/edm5GTad): Why #metadata is important for FAIR data sharing and reuse? Metadata is an important topic in data management. In this post, Nina Profazi reflects on the relevance of descriptive, technical and administrative metadata for interactional linguistics. Later, we will discuss the specific choices to be made at this regard for our conversational data on the LaRS repository. #openscience #openresearchdata #opendata #spokenlanguage #corpuslinguistics #interactionallinguistics

7

🎓:👁👁 ⬇️ 《Have you used our ‘Data in Publications guide’ before? 📚 This step-by-step guide will help you publishing your data in an easy-to-understand pathway with real-life examples and many resources! Read more 👉 europa.eu/!qqJWCk #EUOpenData》 ⬇️ 🗂EU OpenData via X https://lnkd.in/diHVhD86

1

LLM agents can automate complex tasks via self-planning and tool calling💪 But how effective are they for Knowledge Graph QA 🤔? Our #ACL2024NLP findings paper introduces #DARA, a fine-tuned LLM agent for KGQA! 📰 https://lnkd.in/ensbEP47 ⌚ Findings Poster Session 4, Wed, Aug 14, 12:15 ICT Previous work on semantic parsing with LLMs includes: ⚙️ external tools to interact with knowledge graphs (KGs) 🗺️ guidance via In-context learning ICL-based agents are easy to use and don’t need training 🤗 BUT they have obvious drawbacks 😟: 🔴 poor performance  💰 expensive and slow API calls  🔒 privacy and flexibility issues DARA addresses these issues with a hierarchical structure:  1️⃣ high-level decomposition: from abstract to concrete tasks 2️⃣ lower-level grounding: deriving executable logical forms Introducing a method to scan promising relations and read descriptions for final selection! We broaden the range of queries that an agent can handle!  How?  🔵 With a semantic retriever to reduce the size of candidate relations 🔵 By introducing actions to get relevant relations and classes for questions that do not include entities Fine-tuned on 768 human-verified trajectories, DARA 🏆 outperforms competing methods  🏆 consistent across different back-end LLMs (CodeLlama (7B), Llama-2 (7B/13B), Mistral-7B) Fine-tuning on thousands of unverified GPT4-generated trajectories is no match for the results obtained with 768 verified trajectories! 😰 Improving LLM-generated trajectories for LLM agents is an exciting direction for future work! We provide open access to our code and results: 📄 Paper: https://lnkd.in/ensbEP47 💻 Code: https://lnkd.in/eGsE8heZ 🤗 Dataset: https://lnkd.in/eNFBkzZY And consider following the authors Haishuo Fang, Xiaodan Zhu and Iryna Gurevych (Ubiquitous Knowledge Processing (UKP) Lab | Queen's University | Ingenuity Labs Research Institute | hessian.AI), if you are interested in more information or an exchange of ideas. See you this week in Bangkok at #ACL2024! #NLProc

14

1 Kommentar

We have published a Commentary from Isaac Wink! 💬 Back to Basics: Considering Categories of Data Services Consults https://lnkd.in/egRbrNfr "Consultations are fundamental to data librarianship, serving as a vital means of one-on-one support for researchers. However, the topics and forms of support unique to data services consults are not always carefully considered. This commentary addresses five common services offered by data librarians...and considers strategies for successful patron support within the boundaries of a consultation." #DataLibs #DataServices #Consultations

2

📈 Dataframe libraries evolving faster than you can keep up? Marco Gorelli's Data Umbrella webinar is your cheat code! Learn Polars expressions and how to build library-agnostic data tools. 👀 Watch now: https://lnkd.in/dpMGfx4a #DataScience #TechTips

7

1 Kommentar

#IJCAIchallenge OPEN CHALLENGE ⏰🏁 Financial Challenges in Large Language Models - FinLLM at #IJCAI2024 ➡️https://lnkd.in/d7StmYwx With the advent of LLM in finance, financial text analysis, generation, and decision-making tasks have received growing attention, including financial classification, financial text summarization, and single stock trading. For instance, 1) The financial classification task aims to categorize sentences as claims or premises effectively. 2) Financial text summarization task for abstracting financial texts into concise summaries. 3) The single stock trading task aims to make a predictable decision regarding stock trading. Although several approaches have achieved remarkable performance with LLMs, their capabilities of comprehensive analysis and decision-making for finance remain largely unexplored. We plan to explore the ability of LLMs from these facets. We prepared a Large Language Model-based financial shared task, FinLLM, which contains three subtasks to address diverse financial challenges effectively and holistically.  

1

Federated Evaluation made easy with Flower 🌸 We dived into this topic with new docs and code on the 2️⃣ main approaches to evaluate models in FL systems: centralized (or server-side) evaluation ➕ federated (or client-side) evaluation 💻🔥 🧭 Explore how to implement both approaches: https://buff.ly/3UIZ4m4 👩🏽‍💻 Find code example here: https://buff.ly/3rBo7fv Do you need any clarification? Want to share your knowledge? Join the 🌼 Flower community today: https://buff.ly/3YONpTy or 👤 Log in to Flower Discuss: https://buff.ly/3ThujmD

22

#ICYMI From data-oriented to domain-centric: explore the spectrum of #Java persistence patterns with Otavio Santana’s #InfoQ article: https://bit.ly/48he8vI Delve into Driver, Mapper, DAO, Active Record, and Repository for robust architectural foundations. #SoftwareDevelopment #SoftwareArchitecture #Frameworks

9