International workshop on Deep learning for Multi-modal Data

12:55 - 13:10 (15min)

Opening Session

Welcome and workshop Introduction

13:10 - 13:50 (40min)

Keynote presentation — Beyond Text: The Rise of Truly Multimodal Intelligence

Farideh Tavazoee (Alexa AI, Amazon Seattle, WA, USA)

13:50 - 14:30 (40min)

Invited speaker — Cross-modal Information Modeling in the Age of LLMs

Zengchang Qin (VinUniversity, Hanoï, Vietnam)

14:30 - 15:00 (30min)

Industry presentation and demo — The Future of Intelligent Template Generation

David Calvo (CEO, OSIDOC - AI document intelligence)

15:00 - 15:15 (15min)

Break - Networking & refreshments

15:15 - 15:50 (35min)

Invited speaker — Toward Context-aware Foundation Models for Time Series

Abdul Fatir Ansari (AWS, Amazon Berlin, Germany)

15:50 - 16:05 (15min)

Closing Session

Final remarks and discussion

Program