Yingdong Hu

I am a third-year Ph.D. student at Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University, advised by Prof. Yang Gao. Previously, I obtained my bachelor's degree from Beijing University of Posts and Telecommunications (BUPT).

My research primarily revolves around Embodied AI, a multidisciplinary domain intersecting computer vision, machine learning, and robotics. Specifically, I am dedicated to exploring how prior knowledge in foundational models can be leveraged to construct general-purpose robots capable of effective generalization in diverse, real-world environments.

Email  /  Google Scholar  /  Github

We introduce ViLa, a novel approach for long-horizon robotic planning that leverages GPT-4V to generate a sequence of actionable steps. ViLa empowers robots to execute complex tasks with a profound understanding of the visual world.

We present Semantic-Geometric Representation (SGR), a universal perception module for robotics that leverages the rich semantic information of large-scale pre-trained 2D models and inherits the merits of 3D spatial reasoning.

We conduct the first thorough evaluation of pre-trained vision model performance across different downstream policy learning methods and environments. We discover that the effectiveness of pre-training is highly dependent on the choice of the downstream policy learning algorithm.

We show that fine-grained features learned with pixel-level self-supervised learning (SSL) objectives are complementary to semantic features from image-level SSL methods. Fusing these features can significantly improve the performance for visual correspondence tasks.

Modified from Jon Barron