Keynote
Learning for physical interaction: from manipulating objects to designing protein interfaces
Josef Sivic
Abstract
Large-scale neural networks have enabled major progress in several areas of artificial intelligence, including natural language processing and computer vision, demonstrating remarkable performance on complex tasks such as writing computer programs or creating images. These impressive results are powered by Internet-scale datasets, transformer-based neural architectures, self-supervised learning techniques, and supercomputer infrastructures. However, the progress has been limited so far in areas that require interactions with physical environments, where collecting large-scale datasets is challenging and slow. Examples include robotic manipulation, where data collection is limited by the speed of the robot, or designing protein-protein interactions, where data collection is limited by the speed of laboratory experiments. In this talk, I will show our recent progress in this area.
Short Bio
Josef Sivic holds a distinguished researcher position at the Czech Institute of Robotics, Informatics and Cybernetics (CIIRC) at the Czech Technical University in Prague, where he heads the Intelligent Machine Perception team and the ELLIS Unit Prague. He received the habilitation degree from Ecole Normale Superieure in Paris and PhD from the University of Oxford. After PhD, he was a post-doctoral associate at the Computer Science and Artificial Intelligence Laboratory at the Massachusetts Institute of Technology and then spent more than 10 years at Inria Paris where he received an ERC Starting Grant. He was awarded the British Machine Vision Association Sullivan Thesis Prize, three test-of-time awards at major computer vision conferences, and, in 2023, an ERC Advanced Grant. From 2019 to 2025 he served on the board of the European Laboratory of Learning and Intelligent Systems (ELLIS).
