The ELLIS Unit Prague, led by Unit Director Josef Šivic, will be featured in a highly anticipated workshop and talk at the Indian Institute of Technology Delhi (IIT Delhi) on April 4, 2025. Dr. Šivic, an internationally recognized researcher in computer vision and artificial intelligence, will deliver a talk titled „Learning for Physical Interaction: From Objects to Molecular Structures“.
What is his talk about?
Recent advancements in large-scale neural networks have revolutionized artificial intelligence, particularly in fields like natural language processing and computer vision. These technologies have achieved impressive milestones, including the ability to write computer programs and generate images. However, AI’s progress has been less pronounced in areas that involve interactions with physical environments, where data collection is inherently slow or limited. This includes tasks like robotic manipulation, where robots‘ physical limitations slow down data collection, or protein engineering, where laboratory experiment speed imposes challenges.
In his talk, Dr. Šivic will present innovative approaches to overcoming these challenges. He will highlight recent work in learning physical manipulation from instructional videos and transferring those skills to robotic systems. Furthermore, he will discuss developments in neural architectures and self-supervised learning techniques tailored to the intricate task of protein engineering.
About Josef Šivic
Josef Šivic is a distinguished researcher at the Czech Institute of Informatics, Robotics, and Cybernetics (CIIRC) at the Czech Technical University in Prague, where he heads the Intelligent Machine Perception team and serves as the Unit Director and ELLIS Fellowof the ELLIS Unit Prague. He has made significant contributions to the fields of computer vision and artificial intelligence throughout his career.
Dr. Šivic earned his PhD from the University of Oxford in 2006 under the supervision of Prof. Andrew Zisserman. He also received his habilitation degree from Ecole Normale Superieure in Paris in 2014. After completing his PhD, Dr. Šivic continued his research as a postdoctoral associate at the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), before moving to Inria Paris, where he spent over a decade conducting groundbreaking research. In 2023, Dr. Šivic was awarded an ERC Advanced Grant.
In addition to his research accomplishments, Dr. Šivic has received several prestigious awards, including the British Machine Vision Association Sullivan Thesis Prize and multiple test-of-time awards at major computer vision conferences. He also currently serves on the board of the European Laboratory of Learning and Intelligent Systems (ELLIS), an organization committed to advancing AI and machine learning in Europe.