Knowledge Guided AI Partner
Welcome to the Robotics & Embodied Intelligence Seminar!
Join us for an engaging session exploring how AI, robotics, and wireless innovation are converging to transform the physical world. This hybrid event will be held at 370 Jay Street and online. Mark your calendars and don't miss this opportunity to connect with leading researchers shaping the future of intelligent machines. Whether you're a student, professional, or enthusiast, this talk offers a front-row seat to the breakthroughs redefining how robots sense, learn, and act.
About the Talk
Building trustworthy AI partners alongside humans faces a reality that scaling alone cannot fix: embodied data is orders of magnitude scarcer than language and vision data. Before sufficient data can be collected, agents need to make smart use of what we have by reasoning with structure. This talk will show how structured knowledge and inductive bias can reduce reliance on brute-force data, enabling AI agents to understand context, generalize robustly, and collaborate with humans in the real world. The talk will introduce how structured knowledge can be embedded directly into neural architectures, integrating logical structure into representations rather than attaching reasoning as a post-hoc module. It will then demonstrate how knowledge-guided models support reliable contextual perception, including robust scene understanding and hallucination mitigation. Finally, it will present how grounded representations enable proactive human-robot collaboration across various real-world scenarios, where robots interpret human intent, anticipate actions, and coordinate behavior in dynamic environments. Together, these efforts outline a pathway toward capable, efficient, and trustworthy AI agents as genuine partners for humans, both digitally and physically.
About the Speaker
Yaqi Xie is a Postdoctoral Fellow at the Robotics Institute, Carnegie Mellon University, advised by Katia Sycara. She received her Ph.D. in Computer Science from the National University of Singapore, advised by Harold Soh. Her research focuses on human-AI synergy through neuro-symbolic fusion, bridging deep learning and symbolic reasoning to build trustworthy AI partners. Her long-term vision is to endow intelligent agents with knowledge-guided world models that evolve through continual interaction. She serves as an Organizing Committee member and Area Chair at top-tier venues such as HRI and NeurIPS. She has received several distinctions, including the NUS Achievement Award and the Keppel Award of Excellence. Her works have been recognized with Best Paper Awards at RSS 2025 GenAI-HRI and ICRA 2025 Nonverbal Cues workshops.
We invite you to join the conversation.
Visitor Information
This event is open to NYU students, faculty, and staff.
📍 Location: NYU Tandon School of Engineering, 370 Jay Street 12 FL Room 1201 [NYU ID required]
Zoom Link: https://nyu.zoom.us/j/94679794904?pwd=VzOlQraRGla3jW5QbWE6Y51SWIrP8v.1
Meeting ID: 946 7979 4904
Passcode: 266975
About the Robotics & Embodied Intelligence Candidate Talk Series
The Robotics & Embodied Intelligence Candidate Talk Series invites the NYU Tandon community to engage directly with exceptional researchers being considered to join our faculty. These sessions are a chance to explore cutting-edge ideas, ask hard questions, and help shape the future of our robotics ecosystem.