Connecting the world and beyond

Draft Programme

​​​​​​​​​​​​​​​​​​​​Workshop on Embodied AI for Multimedia Technologies

Hangzhou, China, 16 October 2026

Contact: tsbevents@itu.int

​09:00 - 09:15
​​Opening Remarks 
​​MOC: Stefano Polidori, Counsellor of ITU-T SG21 & FG-EAI,​ TSB, ITU
09:15-09:30​​​Special Session: ITU FG-EAI Achievements and Working Group progresses

Provides a focused overview of the Focus Group's progress, key achievements, and current working items across its Working Groups​ 
09:30-09:40​​Setting the Stage: Embodied AI industry developments in 2026

Key findings from the latest research from CAICT and Tsinghua University​ 
09:40-10:30​​Session 1: Core Technologies for Embodied AI

Move beyond foundational overviews to critically examine the practical bottlenecks in Embodied AI. ​This session will dissect the genuine challenges in foundation models, multimodal interaction, and spatial intelligence, while highlighting underappreciated yet critical infrastructures, such as data pipelines, that dictate the next wave of fundamental technical breakthroughs.

Moderator: Shin-Gak Kang, Vice-Chair, FG-EAI | ETRI (Korea)
10:30-10:50​​Coffee Break (offered by the host)​
​10:50-11:40
​Session 2: Industry Applications and Deployment

Shift the focus from theoretical introductions to actionable engineering insights. We will explore the hidden gaps in current EAI and multimodal capabilities, discuss the unglamorous but vital data and communication infrastructures, and share core technical experiences from the frontlines of Embodied AI development.

Moderator: Andrea Cavallaro​, Prof, EPFL (Switzerland)
11:40-12:20​​Roundtable: Making Embodied AI Deployable, Comparable, and Trusted

The roundtable provides a venue for the leadership of the Focus Group and Working Groups to share views on the next practical steps on interoperable services, data and safety practices, shared benchmarks, real-world testing, scaled deployment, and open-source ecosystem.

Moderator: Y​untao Wang​, Chair, FG-EAI | CAICT, China 

12:20-12:25​​Closing Remarks
12:25-12:30​Group Photo and Networking
​12h30-14h30
​Lunch break (offered by the host)​​
​14h30-18h0​0​
​​​Embodied AI Tour (more details)