Build with AI: Unlocking the Power of Multimodal Intelligence

Hallerstraße 6, 6 Hallerstraße, Berlin, 10587

GDG Berlin

šŸš€ Join us for an evening of cutting-edge AI innovation hosted by GDG Berlin at IAV! This Build with AI special event explores how multimodal intelligence—the fusion of šŸŽ„ video, šŸ—£ļø language, and šŸ“” sensor data—is transforming industries, with a spotlight on the automotive sector šŸš— and video understanding šŸ¤–

May 22, 4:30 – 7:30 PM (UTC)

117 RSVP'd

Key Themes

Build with AI

About this event

Join us for an evening of cutting-edge AI innovation hosted by GDG Berlin at IAV. This Build with AI special event explores how multimodal intelligence—the fusion of video, language, and sensor data—is transforming industries, with a spotlight on the automotive sector and video understanding.

In Talk 1, Dr. Christoph Raab discover the automotive industry in Germany is undergoing transformative changes marked by electrification, software-defined vehicles, and AI. Among these, AI plays a pivotal role—not only in features like self-driving cars and intelligent infotainment but also in transforming how vehicles are engineered. AI can significantly optimize and accelerate the design process, particularly within the V-model, a key framework for developing and validating automotive systems. By leveraging AI, efficiency gains of quite over 50% can be achieved in requirements engineering, testing, and software development.This talk will explore how AI enhances the V-model, showcasing real-world use cases, IAV's cutting-edge solutions, and hands-on demonstrations. Expect practical insights, interactive demos, and a roadmap to integrating AI into the automotive industry.

In Talk 2, Hrishikesh Yadav, dives deep into the world of video understanding and explore how models like Marengo craft meaningful video embeddings, enabling applications such as video-to-text generation, scene analysis, and AI agents.
ive into the fast-evolving field of video understanding and discover how multimodal AI models—like vision transformers and Marengo—are shaping the future of intelligent systems. This session covers real-world use cases, how to generate meaningful video embeddings, and the journey from video to text using models like Pegasus. Includes a live demo and open-source resources to start building your own applications. No prior experience needed!

In talk 3, Nidaa Fatimah Mungloo will take us through the practical side of Retrieval-Augmented Generation (RAG) — breaking it down and showing how this powerful architecture is used in real-world applications today.

When

When

Thursday, May 22, 2025
4:30 PM – 7:30 PM (UTC)

Agenda

4:30 PMOpen doors
5:00 PMTalk 1 begins
5:30 PMshort break and food/drinks
5:45 PMTalk 2 begins
6:30 PMTalk 3 begins
7:00 PMNetworking, food, drinks

Speakers

  • Dr. Christoph Raab

    IAV

  • Hrishikesh Yadav

    Twelve Labs

  • Nidaa Fatimah Mungloo

    Gallup

Organizers

  • Abhinav Kulshreshtha

    Organizer

  • Alex Mir

    Adevinta

    GDG Organizer

  • Emy Jamalian

    Atlas Metrics

    QA engineer

  • Jerome Mouton

    Cloud GDE

    Organizer

  • Louis Tsai

    Zalando SE

    GDG Organizer

  • manjula dube

    Organizer

  • Mohamed Islem Ayari

    CLOUDPILOTS Software and Consulting GmbH

    Organizer

  • Shrinish Donde

    Fraunhofer HHI

Contact Us