BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Practical ChatGPT for Academics: Deep Research\, Code & LaTeX — 
 Live Demo
DTSTART:20251022T140000Z
DTEND:20251022T163000Z
DTSTAMP:20260904T174000Z
UID:indico-event-3156@indico.ijs.si
CONTACT:eurocc@sling.si
DESCRIPTION:Speakers: Janez Perš (UL FE)\, Janez Križaj\n\nDescription: 
 A 2.5 hour live-demo seminar on practical\, high-impact use of ChatGPT in 
 academia: effective prompting and voice tactics\, verified Deep Research\,
  programmatic problem-solving (live code — digital filter design)\, figu
 re creation from text/screenshots\, and LaTeX outputs (Beamer slides & pos
 ters in Overleaf). Hands-on participation optional.\nDetailed description:
  This seminar provides a comprehensive introduction to using ChatGPT as a 
 versatile academic assistant for the entire research workflow. Participant
 s will see\, step by step\, how to use ChatGPT to perform structured liter
 ature reviews\, locate relevant open-source repositories\, and organize re
 search findings efficiently. The emphasis is on verifiable\, citation-bas
 ed outputs and critical interaction with the model rather than passive use
 . Real-world examples will show how Deep Research mode can complement trad
 itional search engines and databases when used responsibly.\nA major part 
 of the seminar focuses on practical code generation and execution. Attende
 es will observe how ChatGPT can design\, implement\, and run small-scale a
 nalytical projects directly inside the chat interface\, including numerica
 l simulations and data visualizations. The demonstration will include a di
 gital filter design example\, highlighting verification strategies\, inter
 pretation of results\, and common pitfalls. This section will also touch o
 n multimodal features such as generating figures from text or screenshots\
 , showing how image understanding and textual reasoning combine to support
  reproducible research workflows.\nFinally\, the seminar will demonstrate 
 how ChatGPT can support academic writing and dissemination. Participants w
 ill learn how to automatically produce Beamer presentations and scientific
  posters directly from LaTeX papers in Overleaf\, ensuring consistency bet
 ween research outputs and presentations. The session concludes with a shor
 t bonus demo of text-driven 3D scene generation to illustrate creative app
 lications of language-to-visual synthesis. Throughout the event\, best pra
 ctices for prompting\, critical review\, and AI literacy will be emphasize
 d to ensure reliable and ethical use of generative models in research and 
 education.\nDate and time: 22. October 2025  from 16.00 - 18.30\nLanguage
 : English\nLevel: Intermediate\nLocation: Virtual (Zoom) - link will only 
 be available to registered participants\nTarget audience: Researchers\, gr
 aduate and undergraduate students\, lecturers\, and technical staff in aca
 demia who want to integrate ChatGPT effectively into research\, coding\, w
 riting\, and presentation workflows.\nMax. number of participants: 300\nPr
 erequisites (optional): \n•    Overleaf account\; •    ChatGPT (
 Plus/Team/Pro)\nWorkflow: Live Zoom session with screen-shared demonstrati
 ons. The seminar begins with prompting and voice tactics\, followed by Dee
 p Research for literature and repository discovery\, live Python code exec
 ution (digital filter example)\, figure generation from text or screenshot
 s\, and creation of Beamer presentations and posters in Overleaf. Conclude
 s with a short bonus demo (text-described 3D scene) and Q&A.\nLearning out
 comes:\n • Effective prompting and voice/dictation for complex academic
  tasks.• Verified literature and code-repository search.• Using ChatGP
 T’s built-in code execution for analysis and visualization.• Generatin
 g publication-quality figures from text or screenshots.• Creating Beamer
  presentations and posters from LaTeX papers in Overleaf.• Minimizing ha
 llucinations and improving response reliability.\n \nOrganizator:\n\n \n
 Lecturers:\n\n\n\nAssoc. prof. dr. Janez Perš\n\n\n\nAssociate professor 
 at the Faculty of Electrical Engineering\, University of Ljubljana\, and a
  member of the Laboratory for Machine Intelligence (LMI). His research and
  teaching span computer vision\, machine intelligence\, and embedded syste
 ms\, with a strong focus on applying artificial intelligence to real-world
  problems such as autonomous vehicles\, robotics\, and precision agricultu
 re. He has been an early and active adopter of AI-assisted tools in resear
 ch\, teaching\, and academic communication\, exploring how systems like Ch
 atGPT can augment productivity\, creativity\, and critical thinking in aca
 demic contexts.\n\n\n\n janez.pers@fe.uni-lj.si \n\n\n\n \n\n\n\nas. dr.
  Janez Križaj\n\n\nDr. Križaj is a postdoctoral researcher at the Labora
 tory for Machine Intelligence\, Faculty of Electrical Engineering\, Univer
 sity of Ljubljana. His research focuses on computer vision\, biometrics\, 
 and deep learning.\n\n\n janez.krizaj@fe.uni-lj.si \n\n\n\n\n\n\n\n\nhttp
 s://indico.ijs.si/event/3156/
IMAGE;VALUE=URI:https://indico.ijs.si/event/3156/logo-84923595.png
LOCATION:Virtual location (ZOOM)
URL:https://indico.ijs.si/event/3156/
END:VEVENT
END:VCALENDAR