101010.pl is one of the many independent Mastodon servers you can use to participate in the fediverse.
101010.pl czyli najstarszy polski serwer Mastodon. Posiadamy wpisy do 2048 znaków.

Server stats:

493
active users

#hybridai

0 posts0 participants0 posts today
All Things Open<p>🚀 NEW on We ❤️ Open Source 🚀</p><p>Hybrid AI = innovation + security.</p><p>Dr. Ruth Akintunde dives into how open source and enterprise AI can work together to drive progress in this new video.</p><p>🎥 Watch it here: <a href="https://allthingsopen.org/articles/open-source-vs-enterprise-ai-hybrid-ai" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">allthingsopen.org/articles/ope</span><span class="invisible">n-source-vs-enterprise-ai-hybrid-ai</span></a></p><p><a href="https://mastodon.social/tags/WeLoveOpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>WeLoveOpenSource</span></a> <a href="https://mastodon.social/tags/HybridAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HybridAI</span></a> <a href="https://mastodon.social/tags/FOSS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FOSS</span></a> <a href="https://mastodon.social/tags/AIethics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AIethics</span></a> <a href="https://mastodon.social/tags/OpenSourceAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSourceAI</span></a></p>
Harald Sack<p>Interesting new paper: "Graph-constrained Reasoning (GCR)" - Enabling Faithful KG-grounded LLM Reasoning with Zero Hallucination! 🧠 by Linhao Luo, Zicheng Zhao, Chen Gong, Gholamreza Haffari, Shirui Pan</p><p>paper: <a href="https://arxiv.org/pdf/2410.13080" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/pdf/2410.13080</span><span class="invisible"></span></a><br>GCR code on GitHub: <a href="https://github.com/RManLuo/graph-constrained-reasoning" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/RManLuo/graph-const</span><span class="invisible">rained-reasoning</span></a></p><p><a href="https://sigmoid.social/tags/knowledgegraphs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>knowledgegraphs</span></a> <a href="https://sigmoid.social/tags/llms" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llms</span></a> <a href="https://sigmoid.social/tags/semanticweb" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>semanticweb</span></a> <a href="https://sigmoid.social/tags/neurosymbolic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neurosymbolic</span></a> <a href="https://sigmoid.social/tags/hybridaI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>hybridaI</span></a> <a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a></p>
Harald Sack<p>Interesting paper on how to improve LLM-based Question Answering. They present an ontology-based error checker for LLM-generated SPARQL queries and an approach to automatically repair the SPARQL queries:<br>Dean Allemang, Juan Sequeda: Increasing the LLM Accuracy for Question Answering: Ontologies to the Rescue!</p><p><a href="https://arxiv.org/pdf/2404.07198.pdf" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/pdf/2404.07198.pdf</span><span class="invisible"></span></a></p><p><a href="https://sigmoid.social/tags/llms" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llms</span></a> <a href="https://sigmoid.social/tags/sparql" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>sparql</span></a> <a href="https://sigmoid.social/tags/qa" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>qa</span></a> <a href="https://sigmoid.social/tags/knowledgegraphs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>knowledgegraphs</span></a> <a href="https://sigmoid.social/tags/ontologies" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ontologies</span></a> <a href="https://sigmoid.social/tags/hybridai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>hybridai</span></a> <a href="https://sigmoid.social/tags/semanticweb" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>semanticweb</span></a> <a href="https://sigmoid.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <span class="h-card" translate="no"><a href="https://data-folks.masto.host/@juan" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>juan</span></a></span></p>
Harald Sack<p>Calling Knowledge Graphs and Symbolic AI to the rescue! How <a href="https://sigmoid.social/tags/knowledgegraphs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>knowledgegraphs</span></a> can help to improve the performance of large language models and lower the risks of hallucination, we will explain in this section of our free <a href="https://sigmoid.social/tags/kg2023" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>kg2023</span></a> lecture.<br>OpenHPI video: <a href="https://open.hpi.de/courses/knowledgegraphs2023/items/1zeQqWUsn1G7YpSvqAAwMI" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">open.hpi.de/courses/knowledgeg</span><span class="invisible">raphs2023/items/1zeQqWUsn1G7YpSvqAAwMI</span></a><br>youtube video: <a href="https://www.youtube.com/watch?v=5XhaLlQPsrg&amp;list=PLNXdQl4kBgzubTOfY5cbtxZCgg9UTe-uF&amp;index=63" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=5XhaLlQPsr</span><span class="invisible">g&amp;list=PLNXdQl4kBgzubTOfY5cbtxZCgg9UTe-uF&amp;index=63</span></a><br>Slides: <a href="https://zenodo.org/records/10185291" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">zenodo.org/records/10185291</span><span class="invisible"></span></a> <a href="https://sigmoid.social/tags/ccby40" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ccby40</span></a> <br><span class="h-card" translate="no"><a href="https://wisskomm.social/@fiz_karlsruhe" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>fiz_karlsruhe</span></a></span> <span class="h-card" translate="no"><a href="https://sigmoid.social/@fizise" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>fizise</span></a></span> <a href="https://sigmoid.social/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llm</span></a> <a href="https://sigmoid.social/tags/llms" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llms</span></a> <a href="https://sigmoid.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://sigmoid.social/tags/hybridAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>hybridAI</span></a> <a href="https://sigmoid.social/tags/semanticweb" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>semanticweb</span></a> <a href="https://sigmoid.social/tags/deeplearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>deeplearning</span></a></p>