BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//euroscipy-2025//speaker//3U3KUU
BEGIN:VTIMEZONE
TZID:Europe/Warsaw
BEGIN:DAYLIGHT
DTSTART:20240818T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241027T030000
RDATE:20251026T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T030000
RDATE:20260329T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Guardians of Science: A Python Tutorial on a RAG-Powered Complianc
 e Plug-In and Ethical AI tools - Anuradha Kar\, PhD\, Anuradha KAR\, Likhi
 ta Yerra
DTSTART;TZID=Europe/Warsaw:20250818T083000
DTEND;TZID=Europe/Warsaw:20250818T100000
DTSTAMP:20260908T130435Z
UID:pretalx-euroscipy-2025-Q3FERF@pretalx.com
DESCRIPTION:As AI adoption accelerates across industries\, ensuring ethica
 l integrity and reproducibility has become increasingly critical for enter
 prises and developers. This tutorial presents a Retrieval-Augmented Genera
 tion (RAG)-based compliance plug-in designed to promote responsible AI pra
 ctices. Through a hands-on session\, participants will learn how to integr
 ate external compliance knowledge bases with generative models to automate
  ethical checks\, document decision-making processes\, and enhance the rep
 roducibility of AI outputs. The session will cover system architecture\, i
 mplementation using popular frameworks\, and practical use cases\, equippi
 ng attendees with tools to embed trust and accountability into AI workflow
 s from the outset.\nOver the course of 90 minutes\, we will introduce the 
 core concepts behind the Python-based plug-in\, including RAG architecture
  and vector-based retrieval techniques. Participants will engage with live
  demonstrations on querying regulatory standards such as the European Unio
 n Artificial Intelligence Act and FAIR (Findable\, Accessible\, Interopera
 ble\, Reusable) principles. The tutorial will also showcase bias auditing 
 and model transparency features\, using a healthcare case study to illustr
 ate real-world application and highlight model tracking and reproducibilit
 y capabilities.
LOCATION:Room 1.38 (Ground Floor)
URL:https://pretalx.com/euroscipy-2025/talk/Q3FERF/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Automated Chess Analysis: Real-Time Move Detection and Game Narrat
 ion Using Computer Vision and Large Language Models - Anuradha Kar\, PhD\,
  Anuradha KAR\, Likhita Yerra
DTSTART;TZID=Europe/Warsaw:20250821T163000
DTEND;TZID=Europe/Warsaw:20250821T165000
DTSTAMP:20260908T130435Z
UID:pretalx-euroscipy-2025-MLCQQL@pretalx.com
DESCRIPTION:This talk presents a python-Streamlit application which has be
 en developed based on integration of deep learning based automatic chess m
 ove detection and LLM-generated chess game commentary and is designed to b
 e a powerful tool for enhancing chess learning and viewer engagement. Auto
 matic move detection based on a high accuracy computer vision model allows
  chess players\, learners and general viewers to accurately track the game
 s\, identify mistakes\, and review tactics without the need for manual not
 ation. Beginners gain a clearer understanding of gameplay flow\, while ent
 husiasts can easily annotate and revisit key moments. By combining move de
 tection with real-time\, LLM-driven commentary\, the system provides conte
 xt-aware explanations that highlight strategic ideas\, tactical patterns\,
  and player intentions. This creates an interactive and educational experi
 ence that enriches both learning and viewing.
LOCATION:Room 1.38 (Ground Floor)
URL:https://pretalx.com/euroscipy-2025/talk/MLCQQL/
END:VEVENT
END:VCALENDAR