Facebook group
Twitter
From Perception to Action LECTURES
| Speakers | Syllabus | Titles & Abstracts |
| Frank Dellaert Georgia Institute of Technology, USA |
3D Reconstruction, NeRF, Neural Radiance Fields, Bundle Adjustment | Structure from Motion and Neural Radiance Fields |
| Alyosha Efros UC Berkeley, USA |
Data, Self-Supervised Learning | Computer Vision after the Victory of Data |
| William T. Freeman Computer Science and Artificial Intelligence Laboratory, MIT, USA |
Motion and Sound, Wavelet Processing, Visualizing Motions, Audio Suppression | Motion and sounds: Using video to reveal invisible motions and to suppress unwanted sounds. |
| Phillip Isola Massachusetts Institute of Technology, USA |
Generative models, GANs, diffusion models, autoregressive models, synthetic data | Generative Models as Data++ |
| Angjoo Kanazawa University of California at Berkeley, USA |
3D Vision, Non-rigid 3D Reconstruction, 4D Human Perception, Volumetric Neural Rendering, Neural Radiance Fields | From Videos to 4D Worlds and Beyond |
| Andrej Karpathy OpenAI, USA |
Language Models, GPT | GPT-4 from Scratch |
| Vladlen Koltun Apple, USA |
Robotics | A Quiet Revolution in Robotics |
| Jitendra Malik University of California at Berkeley, USA |
TBA | The sensorimotor road to artificial intelligence |
| Deepak Pathak Carnegie Mellon University, USA |
Robot Learning, Generalization, Adaptation, Social Learning, Curiosity | Robot Learning In The Wild: Continual Improvement by Watching and Practicing |
| Jean Ponce Ecole normale supérieure, FRA & Inria, USA |
Image Formation | Machine learning meets physical models of image formation for photography and astronomy applications |
| Jim Rehg University of Illinois at Urbana-Champaign, USA |
Egocentric Vision, Social AI, Multimodal Machine Learning, Face and Gesture, Action Recognition, Ego4D, Developmental Machine Learning | An Egocentric Approach to Social AI |
| Torsten Sattler Czech Technical University in Prague, CTU |
Visual Localization, Privacy | Visual Localization or Where Am I and Who Knows |
| Stefano Soatto Amazon and University of California Los Angeles, USA |
Foundational Issues in AI | Foundational Issues in AI: Views from the real and the ideal worlds |
| Lorenzo Torresani Facebook AI Research (FAIR), Meta, USA |
Video and language, multimodal learning | Learning to Understand Video Through Language |
| Angela Yao National University of Singapore, SGP |
Long-Range Video Understanding, Procedural Activities | Long-Range Video Understanding |
READING GROUP
| Speakers | Syllabus | Rules of Engagement |
| Stefano Soatto Amazon and University of California Los Angeles, USA |
Reading Group: Meeting with Mentors | Reading Group: Meeting with Mentors |
ESSAY COMPETITION (WITH PRIZE!)
| Speakers | Syllabus | Rules of Engagement |
| Fabio Galasso Sapienza University of Rome, Italy |
Essay Competition | Essay Competition |
INDUSTRY MEETS STUDENTS
Industrial Panel
- Amazon Science, US
- Ambarella-VISLAB, US
- Bosch, DE
- MBZUAI, AE
- Panasonic, US
- Qualcomm, US
- Reality Labs Research, US
- STMicroelectronics, IT
- Toyota Europe Motor, BE