Keynote Speaker
Mauro Martino
https://mamartino.com/
https://urbanaverba.com/
Urbana Verba - Generative Urban Cinema
In my work at the intersection of art and artificial intelligence, I have delved into the potential of generative cinema to reinterpret and recount our cities in entirely novel ways. My latest project, 'Urbana Verba,' endeavors to capture the essence of metropolises through the discerning eye of AI, transforming literature, architecture and art into audiovisual experiences. 'Milan Factory of Future' is the inaugural execution of this project, a distinct expression that pays homage to the city of Milan. This city, as described and experienced by writers and artists who have immortalized its soul in their writings, is reborn in my work of Co-Creation with Generative Models. Words extracted from the works of these Milanese authors are the cornerstone from which AI draws to generate the video, creating a bridge between the tangibility of urban life and its literary intangibility. I invite you to immerse yourself in this multisensory experience, where each frame is a dialogue between the actual city and the imaginative universe so magnificently evoked by its writers and artists.
Bio
Mauro Martino is an Italian American artist, designer, and researcher renowned for pioneering work in the integration of art, data, and artificial intelligence. As founder of IBM Research's Visual Artificial Intelligence Lab and Professor of Practice at Northeastern University, Martino has significantly influenced the fields of data visualization and AI art. Notably, his recent project 'Strolling Cities', showcased at the 2021 Venice Biennale, marked the first artistic instance of poetry readings transformed into real-time film, enriching the relationship between language, technology, and visual art. Further exemplifying Martino's groundbreaking lyrics to video approach are his exhibits NFT Revolution (September 2022) at MEET | Digital Culture Center in Milan, Exercises in Style (March 2023) displayed at the BCA Center in Burlington, Milano - Factory of Future in Malpensa Airport (September 2023) all compelling intersections of AI text to video technology and music.
Replay
Workshop Program
Times are listed in Eastern Daylight Time (UTC-4).
Time | Activity |
---|---|
9:00am |
Welcome Opening remarks from Werner Geyer & organizing committee |
9:05am |
Keynote: Mauro Martino — Urbana Verba – Generative Urban Cinema Introduction by Werner Geyer |
10:00am |
Overview, Logistics & Icebreaker |
10:30am |
Coffee Break |
10:45am |
Session 1: Co-Creative Applications & Studies Chair: Mike Desmond Collaborative Canvas: A Tool for Exploring LLM Use in Group Ideation Tasks Gabriel E. Gonzalez, Dario Andres Silva Moran, Stephanie Houde, Jessica He, Steven I. Ross, Michael Muller, Siya Kunde and Justin D. Weisz Toward Enhancing Ideation through Collaborative Group-AI Brainwriting Orit Shaer, Angelora Cooper, Andrew Kun and Osnat Mokryn Towards Full Authorship with AI: Supporting Revision with AI-Generated Views Jiho Kim, Ray C. Flanagan, Noelle E. Haviland, Ze Ai Sun, Souad N. Yakubu, Edom A. Maru and Kenneth C. Arnold Human-AI Co-Creation of Worked Examples for Programming Classes Mohammad Hassany, Peter Brusilovsky, Jiaze Ke, Kamil Akhuseyinoglu and Arun Balajiee Lekshmi Narayanan ExpressEdit: Video Editing with Natural Language and Sketching Bekzat Tilekbay, Saelyne Yang, Michal Lewkowicz, Alex Suryapranata and Juho Kim A Pilot Study Comparing ChatGPT and Google Search in Supporting Visualization Insight Discovery Chen He, Robin Welsch and Giulio Jacucci Killer Apps: Low-Speed, Large-Scale AI Weapons Philip Feldman, Aaron Dant and James Foulds |
12:10pm | |
12:30pm |
Lunch |
2:00pm |
Session 2: Co-Creative Frameworks & Artistic Expression Chair: Mary Lou Maher Conceptual Models as a Basis for a Framework for Exploring Mental Models of Co-Creative AI Jeba Rezwana and Mary Lou Maher Intent Elicitation in Mixed-Initiative Co-Creativity Max Kreminski and John Joon Young Chung Holistic Approach to Design of Generative AI Evaluations: Insights from the Research Onion Model Manoj Deshpande and Brian Magerko Quan Gu, Yiduo Wang, Xiaoxiao Hu and Orit Shaer Towards Personalizing Generative AI with Small Data for Co-Creation in the Visual Arts Ahmed M. Abuzuraiq and Philippe Pasquier |
3:25pm | |
3:45pm |
Coffee Break |
4:00pm |
Discussion & Closing Remarks Mary Lou Maher |
5:00pm |
Workshop end |
Posters & Demos
Poster | Bryan Wang, Yuliang Li, Zhaoyang Lv, Haijun Xia, Yan Xu and Raj Sodhi. LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing |
Poster | David Lee, Dustin Palea and Giridhar Vadhul. Collaborative Generative AI for Co-Creative Learning |
Poster | Florian Richter. Ethical Assessment of Generative AI |
Demo | Jiho Kim, Ray C. Flanagan, Noelle E. Haviland, Ze Ai Sun, Souad N. Yakubu, Edom A. Maru and Kenneth C. Arnold. Towards Full Authorship with AI: Supporting Revision with AI-Generated Views |
Demo | Philip Feldman, Aaron Dant and James Foulds. Killer Apps: Low-Speed, Large-Scale AI Weapons |
Demo | Mohammad Hassany, Peter Brusilovsky, Jiaze Ke, Kamil Akhuseyinoglu and Arun Balajiee Lekshmi Narayanan. Human-AI Co-Creation of Worked Examples for Programming Classes |
Demo | Chen He, Robin Welsch and Giulio Jacucci. A Pilot Study Comparing ChatGPT and Google Search in Supporting Visualization Insight Discovery |
Demo | Gabriel E. Gonzalez, Dario Andres Silva Moran, Stephanie Houde, Jessica He, Steven I. Ross, Michael Muller, Siya Kunde and Justin D. Weisz. Collaborative Canvas: A Tool for Exploring LLM Use in Group Ideation Tasks |
Demo | Bekzat Tilekbay, Saelyne Yang, Michal Lewkowicz, Alex Suryapranata and Juho Kim. ExpressEdit: Video Editing with Natural Language and Sketching |