Univ.-Prof. Dr. Xi Wang
Univ.-Prof. Dr.
Xi Wang
Administration
University Ulm
Institute of Neural Information Processing
James-Franck-Ring
89081 Ulm
89081 Ulm
Prof. Dr. Xi Wang
Before joining the Ulm University, Xi was an established researcher in the Computer Vision and Geometry Lab at ETH Zurich while continuing to collaborate with the excellent team at INSAIT. She is also leading the junior research group UDance hosted at the Computer Vision Group at Technical University of Munich and Munich Center for Machine Learning (MCML). She was an ETH Postdoc Fellow in the Advanced Interactive Technologies lab at ETH and a member of the virtual group of Ruth Rosenholtz at MIT. She completed my PhD in the Computer Graphics group at TU Berlin. In 2020, she visited MIT working in the Computational Perception & Cognition Group led by Aude Oliva. Later that year she interned at Adobe Research working with Zoya Bylinskii and Aaron Hertzmann. She hold a dual M.Sc. in Computer Science from TU Berlin and Shanghai Jiao Tong University, where she also completed her B.Eng. in Computer Science.
Research
Her research operates at the intersection of egocentric vision and embodied AI. She aims to incorporate human common sense and behavioral patterns into machine learning to build embodied agents capable of learning structured models from human-world interactions and generalizing to diverse real-world settings. She tackles these challenges through three core lenses:
- Act via Prediction: Determining the optimal abstractions for representing past experiences from partial human activity data, modeling underlying task structures, and leveraging multimodal integration to boost downstream performance.
- Interact via 3D Reconstruction: Capturing the nuances of dynamic human interactions from an egocentric viewpoint to reconstruct detailed 3D physical models for robotic manipulation.
- Collaborate via Understanding: Creating intelligent robots that seamlessly interface with humans by decoding underlying intent and estimating human goals from multimodal observational cues.
For more details and updates, please check her homepage: https://xiwang1212.github.io/homepage/