FORUM8 MIT SPECIAL SEMINAR 2025
Time: 09:00~11:00(Local time)
Language: English (Presentations in English will be translated into Japanese on the day of the seminar.)
Fee: Free
| 9:00～ 9:20 |
Opening Speech |
| 9:20～ 10:20 |
Special Seminar／Special Lecture Q&A(about 10 to 15 minutes) |
| 10:20～ 11:00 |
FORUM8 Presentation |
Seminar overview
“The Forefront of Autonomous Driving, AI, and Cloud Research”
Lecturer : Vincent Sitzmann
MIT Department of Electrical Engineering & Computer Science , Computer Science and Artificial Intelligence Laboratory (CSAIL)
Prof. Vincent Sitzmann is an Assistant Professor at MIT EECS, where he is leading the Scene Representation. Group Vincent’s research interest lies in neural scene representations – the way neural networks learn to represent information on our world. This work aims to allow independent agents to reason about our world
given only a few visual observations, such as inferring a complete model of a scene, geometry, material, lighting – a task that is simple for humans but currently impossible for AI.
Specifically, Prof. Sitzmann works towards models that can learn to reconstruct a rich state description of their environment, such as reconstructing its 3D structure, materials, semantics, etc. from vision. These models should also be able to model the impact of their own actions on that environment, i.e., learn a “mental simulator” or “world model”. He is particularly interested in models that can learn these skills fully self-supervised only from video and by self-directed interaction with the world.
