Jeannette Bohg is an Assistant Professor at Stanford University, where she directs the Interactive Perception and Robot Learning Lab. Her research investigates the principles of robust sensorimotor coordination and how to transfer them to robotic systems, working at the intersection of robotics, machine learning, and computer vision. Her recent work on scene-aware grasping and language-grounded robot planning connects directly to the workshop’s core themes.
Taku Komura is a Professor at the University of Hong Kong. His research focuses on data-driven and physically-based character animation, crowd simulation, 3D modelling, and robotics. Recently, his main research interests have been on physically-based animation and the application of machine learning techniques for animation synthesis, including human–scene interaction.
Zhengyi Luo is a Research Scientist at NVIDIA GEAR Lab. His research lies at the intersection of robotics, vision, and learning, including humanoid control, humanoid–object interaction, and egocentric perception. He is the lead author of SONIC, a large-scale motion-tracking foundation model for natural humanoid whole-body control.
Gerard Pons-Moll is Professor at the University of Tübingen and core faculty at the Tübingen AI Centre. His research lies at the intersection of computer vision, computer graphics, and machine learning, with special focus on analysing people in videos and creating virtual human models. His recent work spans human-object interaction modelling, human-scene interaction modelling and 3D human reconstruction.