17
Jul
We are (still?) not giving data enough credit
Alexei A. Efros, UC Berkeley
17.07.2024
6:00 pm - 8:00 pm
Bayerische Akademie der Wissenschaften, Plenarsaal, 1. Stock, Alfons-Goppel-Straße 11, 80539 München
On behalf of our partners at the Bavarian AI network baiosphere, the MCML cordially invites you to the first Highlight Lecture of the year as part of the Munich AI Lectures.
For most of Computer Vision’s existence, the focus has been solidly on algorithms and models, with data treated largely as an afterthought. Onlyrecently did the discipline finally begin to appreciate the singularly crucialrole played by data, but even now we might still be underestimating it.
In this talk, Alexei A. Efros from UC Berkeley will begin with some historical examples illustrating theimportance of large visual data in human and computer vision. He will thenshare some of their recent work demonstrating the power of very simple algorithms when used with the right data, including visual in-contextlearning and visual data attribution.
Please register for the event.
Organized by:
baiosphere
Bavarian Academy of Science and Humanities
Helmholtz Munich
LMU Munich
TUM
AI-HUB LMU
ELLIS Munich Unit
Konrad Zuse School of Excellence in Reliable AI
MCML
Munich Data Science Institute TUM
Munich Institute of Robotics and Machine Intelligence TUM
Related
Munich AI Lectures • 22.07.2024 • TUM Garching Campus, FMI Building, Hörsaal 2 (00.04.011), Boltzmannstr. 3, 85748 Garching bei München or online via Livestream
Multi-Modal and Multi-Robot Coordination in Challenging Environments
Munich AI Lecture with Sebastian Scherer from CMU outlining some of their approaches progress, and results on multi-modal sensing.
Munich AI Lectures • 15.07.2024 • TU Munich, Institute for Advanced Study, Auditorium (Ground floor), Lichtenbergstraße 2a, 85748 Garching
Physical AI: Promises and Challenges
Munich AI Lecture with Daniela Rus from MIT discussing recent developments in ML and robotics.
Munich AI Lectures • 25.06.2024 • TUM Campus Munich, Room 0790, Arcisstraße 21, 80333 München
From Video Understanding to Embodied Agents
The MCML invites you to the Munich AI Lectures with Ivan Laptev discussing AI models that make reliable predictions from explanatory videos.
Munich AI Lectures • 18.06.2024 • TUM, Arcisstr. 21, 80333 Munich, Room 0790 (ground floor)
Learning complex robotic behaviors with optimal control
Munich AI Lecture with Ludovic Righetti from NYU presenting their recent work with a particular eye towards unifying learning and numerical optimal control.
Munich AI Lectures • 08.04.2024 • TUM, Arcisstr. 21, 80333 Munich, Room 0790 (ground floor)
Learning complex robotic behaviors with optimal control
Munich AI Lecture with Marc Toussaint from TU Berlin taking a look at the progress and prospects of AI in robotics.