Presentations/Talks
-
Making Safety Sheets Conversational: A RAG Approach with Docling
I am happy to share my presentation:โ๐๐๐ค๐ข๐ง๐ ๐๐๐๐๐ญ๐ฒ ๐๐ก๐๐๐ญ๐ฌ ๐๐จ๐ง๐ฏ๐๐ซ๐ฌ๐๐ญ๐ข๐จ๐ง๐๐ฅ: ๐ ๐๐๐ ๐๐ฉ๐ฉ๐ซ๐จ๐๐๐ก ๐ฐ๐ข๐ญ๐ก ๐๐จ๐๐ฅ๐ข๐ง๐ โat the ๐๐จ๐๐ฅ๐ข๐ง๐ ๐๐จ๐ฆ๐ฆ๐ฎ๐ง๐ข๐ญ๐ฒ ๐๐๐๐ญ๐ฎ๐ฉ. In this talk, I present a ๐๐๐ญ๐ซ๐ข๐๐ฏ๐๐ฅ-๐๐ฎ๐ ๐ฆ๐๐ง๐ญ๐๐ ๐๐๐ง๐๐ซ๐๐ญ๐ข๐จ๐ง (๐๐๐) pipeline for transforming complex multilingual safety sheets at RINGANA – ๐๐จ๐ ๐ซ๐๐ฌ๐ก ๐๐-๐๐จ๐ฅ๐ฎ๐ญ๐ข๐จ๐ง๐ฌ into an interactive conversational system. The presentation covers:[1.] Hybrid chunking with Docling[2.] ๐๐๐ and image…
-
Tackling the problem of โbadโ explanations with the Human-in-the-Loop principle
Link: https://www.youtube.com/watch?v=FnxgNgYyPws From: Prof. Alexander Jung Youtube channel: https://www.youtube.com/@alexjung111
-
Explainable AI with Layer-wise Relevance Propagation (LRP)
Link: https://www.youtube.com/watch?v=-ED-62oU1WY From: LLMs Explained – Aggregate Intellect – AI.SCIENCE Youtube channel: https://www.youtube.com/@ai-science
-
Kandinsky Patterns for Visual Concept Learning
Link: https://www.youtube.com/watch?v=aHRA1bguMRg From: WeAreDevelopers Congress Vienna 2019
-
“Context Engineering in Practice” at the Vienna AI Engineering Meetup
I am happy to share my presentation “๐๐จ๐ง๐ญ๐๐ฑ๐ญ ๐๐ง๐ ๐ข๐ง๐๐๐ซ๐ข๐ง๐ ๐ข๐ง ๐๐ซ๐๐๐ญ๐ข๐๐ – ๐ ๐ซ๐จ๐ฆ ๐๐จ๐๐ฎ๐ฆ๐๐ง๐ญ๐ฌ ๐ญ๐จ ๐๐ง๐ฌ๐ฐ๐๐ซ๐ฌ ๐ฐ๐ข๐ญ๐ก ๐๐๐๐ญ๐จ๐ซ๐๐๐ฌ (๐๐๐๐ฏ๐ข๐๐ญ๐, ๐๐ข๐ง๐๐๐จ๐ง๐)” at the ๐๐ข๐๐ง๐ง๐ ๐๐ ๐๐ง๐ ๐ข๐ง๐๐๐ซ๐ข๐ง๐ ๐๐๐๐ญ๐ฎ๐ฉ as kindly requested by all those incredible people that initiated all those wonderful discussions. My spirit was annealed from all the challenges they are facing, their genuine interest in…