22.01.2024
![Teaser image to The MCML-Exhibition at Deutsches Museum Munich](/images/logos/deutsches-museum.jpg)
The MCML-Exhibition at Deutsches Museum Munich
Our exhibition was a great success - A short recap
Around 1.000 visitors per day passed by the Science Communication Lab at Deutsches Museum and saw our exhibition during the last three weeks. It was a lot of fun and we are happy that so many visitors were interested and got a glimpse of our research.
One of the exhibits called AMELIE taught visitors the basics of machine learning in a fun and interactive way. The exhibit was built by the LMU Media Informatics Group of our PI Albrecht Schmidt. You can see a video of the exhibit on YouTube.
In addition we had a demo showing how it is possible to simultaneously do localization and mapping of the environment using a camera and an attached IMU sensor. The method is called DM-VIO and can be used in self-driving cars, for example. DM-VIO is a project of the TUM Computer Vision Group led by our director Daniel Cremers.
Last but not least, we gave some insights into Stable Diffusion, a deep learning model that generates images from text descriptions. Stable Diffusion is developed by the LMU Computer Vision & Learning Group of our PI Björn Ommer. We explained how Stable Diffusion learns the connection between image and text through a latent diffusion model process.
![Poster 1](/images/news/2023-12-26-dt-museum-poster/2023-12-26-dt-museum2.jpg)
©MCML
Poster 1: How does AI learn
AMELIE is the name of the museum exhibit that helped visitors understand machine learning principles.
![Poster 2](/images/news/2023-12-26-dt-museum-poster/2023-12-26-dt-museum5.jpg)
©MCML
Poster 2: Reconstructing the world with AI
We presented DM-VIO, a monocular visual-inertial odometry system based on two novel techniques called delayed marginalization and pose graph bundle adjustment.
![Poster 3](/images/news/2023-12-26-dt-museum-poster/2023-12-26-dt-museum6.jpg)
©MCML
Poster 3: DM-VIO demo
On this poster visitors saw how the Simultaneous Localization and Mapping unfolds
![Poster 4](/images/news/2023-12-26-dt-museum-poster/2023-12-26-dt-museum9.jpg)
©MCML
Poster 4: Image generation using AI
Visitors saw how Stable Diffusion works and were able to try it out themselves.
22.01.2024
Related
![Link to MCML at the 18th International For..Net Symposium 2024](/images/logos/for-net.webp)
©for..net
25.05.2024
MCML at the 18th International For..Net Symposium 2024
The MCML had the honour of presenting AMELIE - our demonstrator offering a glimpse into the inner learning processes of machines - at the 18th International For..Net …
![Link to MCML launches new collaborative format for scientific exchange](/images/adobestock/adobeStock-485536191-kasto.jpeg)
©kasto - stock.adobe.com
27.03.2024
MCML launches new collaborative format for scientific exchange
With the Pitch Talk Series, the MCML proudly presents their new collaborative format for scientific exchange and community building.
![Link to ELLIS Workshop: Semantic, Symbolic and Interpretable Machine Learning](/images/logos/ellis.jpg)
25.02.2024
ELLIS Workshop: Semantic, Symbolic and Interpretable Machine Learning
MCML PI Volker Tresp organized an ELLIS Workshop together with Kristian Kersting (TU Darmstadt) & Paolo Frasconi (Università di Firenze).
![Link to Girls'Day 2024](/images/logos/girlsDay23.jpg)
22.02.2024
Girls'Day 2024
As part of Girls'Day, the MCML offers interested girls and the opportunity to delve into the everyday life of AI researchers and data scientists.
![Link to 2023 ACM Fellows](/images/logos/acm.jpg)
30.01.2024
2023 ACM Fellows
The 2023 ACM Fellows were recently announced: MCML PI Albrecht Schmidt is one of them.