Embedded Files
September 15 Afternoon (14:30 - 18:00)
September 15 Afternoon (14:30 - 18:00)
14:30 - 14:45 Welcome and Opening Remarks from the Organizers
14:30 - 14:45 Welcome and Opening Remarks from the Organizers
14:45 - 15:30 Keynote Speech - Allegra De Filippo (+ Q & A)
14:45 - 15:30 Keynote Speech - Allegra De Filippo (+ Q & A)
"Human-AI Co-Creation in Artistic Domains"
"Human-AI Co-Creation in Artistic Domains"
Abstract: "The talk explores the role of humans in artistic co-creation with AI, focusing on music and dance. Moving beyond the view of humans as just end-users, we frame co-creation as an iterative process where artists, audiences, and AI systems jointly shape the creative outcome. Through case studies in choreographic generation and sample-based music composition, we show how human knowledge (expressed through constraints, prompt design, and evaluation) consistently improves both the quality and acceptance of AI-generated works. We present protocols for evaluation, methods for embedding domain expertise into AI-driven creativity, and patterns of human intervention across stages of the generative process."
15:30- 16:15 Paper Session: Human-in-the-Loop and Large Language Models in Virtual Scenarios
15:30- 16:15 Paper Session: Human-in-the-Loop and Large Language Models in Virtual Scenarios
- "On the LLM Robustness in a Simulated Conversational XR Scenario: A Preliminary Semantic Analysis
Michele Braccini, Gianluca Aguzzi, Paolo Baldini, Andrea Roli
Michele Braccini, Gianluca Aguzzi, Paolo Baldini, Andrea Roli
- "A Modular and Efficient Framework for the Development of Large Language Model‑Based Virtual Humans: An Educational Scenario"
Michele Giordano, Daniele Berardini, Primo Zingaretti, Emanuele Frontoni, Lorenzo Stacchio
Michele Giordano, Daniele Berardini, Primo Zingaretti, Emanuele Frontoni, Lorenzo Stacchio
- "XRidge: Enabling Cross-Reality Co‑Creation with Generative AI and LLMs"
Giacomo Vallasciani, Pasquale Cascarano, Gustavo Marfia
Giacomo Vallasciani, Pasquale Cascarano, Gustavo Marfia
16:15 - 16:45 Coffee Break
16:15 - 16:45 Coffee Break
16:45 - 17:30 Keynote from Riccardo Bovo (+ Q & A)
16:45 - 17:30 Keynote from Riccardo Bovo (+ Q & A)
"Leveraging the multi-modal nature of communication in immersive XR environments"
Abstract: Communication is inherently multimodal: speech leans on gaze, pointing, and shared scene context. Unlike prior paradigms, spatial computing is uniquely positioned to exploit this richness. This keynote surveys a line of work that illustrate how blending explicit speech with behaviours and environmental signals makes mixed-reality collaboration and interaction more natural, efficient, and robust. We show how fusing speech with gaze, pointing, and semantic scene metadata resolves deictic references and yields more faithful interpretations of collaborative activity, we introduce EmBARDiment, an embodied agent that turns gaze-driven contextual memory and voice into low-friction, implicit assistance for multi-window workflows finally we revisit “Put That There” by coupling LLMs with head-gaze, pointing, and scene understanding to enable intent-based placement and manipulation of virtual objects."
17:30 - 18:00 Paper Session: Human-in-the-loop AI for Creativity
17:30 - 18:00 Paper Session: Human-in-the-loop AI for Creativity
- "Towards a Human-in-the-Loop Framework for Swarm Intelligence‑Driven Dance Generation"
Michele Braccini, Allegra De Filippo, Michele Lombardi, Michela Milano
Michele Braccini, Allegra De Filippo, Michele Lombardi, Michela Milano
- The Digital Garment: A Comparative Study of 3D Digitisation Techniques for Fashion Heritage
Eleo Stacchiotti, Pasquale Cascarano, Jacopo Megliorardi, Gustavo Marfia
Eleo Stacchiotti, Pasquale Cascarano, Jacopo Megliorardi, Gustavo Marfia
18:00 - 18:15 Closing Remarks from the Organizers
18:00 - 18:15 Closing Remarks from the Organizers
Page updated
Google Sites
Report abuse