Shengjie Lin's Homepage


Toyota Technological Institute at Chicago

6045 S. Kenwood Ave.

Chicago, IL 60637

I am currently a Ph.D. candidate in computer science at Toyota Technological Institute at Chicago under the supervision of Prof. Matthew R. Walter. Before joining TTIC, I received a bachelor’s degree in electronic engineering at Tsinghua University, being awarded Outstanding Undergraduate and Outstanding Thesis by the department.

My research interests lie at the intersection of robotics, computer vision, and machine learning. I am particularly interested in developing algorithms that enable robots to understand and interact with their surroundings in a natural and intuitive way. My research efforts have been recently dedicated to 3D scene reconstruction and understanding, with a focus on scalable representation and natural language interaction for embodied agents.

Besides research, I have also led several comprehensive event-driven projects that have been showcased in public exhibitions. These experiences have granted me considerable practical knowledge of not only various software frameworks and tools for developing robotic applications, but also project management and team collaboration. Notably, Baxter Pose Following, a project I led, gained significant popularity upon its debute at the Museum of Science and Industry in Chicago and has since been featured at multiple public events.


Mar 3, 2024 I am excited to share that I will be joining Dexterity as a robotics engineer intern starting this month! I am looking forward to working with the team and learning from the best in the field.
Jan 29, 2024 Our paper Statler: State-Maintaining Language Models for Embodied Reasoning is accepted to ICRA 2024!
Oct 20, 2023 Our paper Transcribe3D: Grounding LLMs Using Transcribed Information for 3D Referential Reasoning with Self-Corrected Finetuning is accepted to the LangRob Workshop @ CoRL 2023!
Jun 30, 2023 Our paper Statler: State-Maintaining Language Models for Embodied Reasoning is now available on Arxiv.
May 22, 2023 Our paper NeRFuser: Large-Scale Scene Representation by NeRF Fusion is now available on Arxiv.