I am Linfeng Zhao (赵林风), a CS Ph.D. student at Khoury College of Computer Sciences of Northeastern University since 2019. I’m advised by Prof. Lawson L.S. Wong and also working with Prof. Robin Walters. My research interests lie in the intersection of machine learning, robotics and artificial intelligence.
I study how structure helps improve learning and generalization in model-based reinforcement learning and planning and focus on robotic manipulation and navigation, including: (1) structured representation learning of state and action, (2) factored/structured world modeling and planning, etc.
During PhD, I am interning in part-time at Boston Dynamics AI Institute with Jennifer L. Barry, and interned at Amazon Science with Kari Torkkola and Dhruv Madeka in 2021 Summer. During undergraduate, I interned at Microsoft Research Asia in fourth year and earlier worked with Prof. Hao Su at UC San Diego.
We study how implicit differentiation helps scale up and improve convergence of differentiable planning algorithms.
We formulate how differentiable planning algorithms can exploit inherent symmetry in path planning problems, named SymPlan, and propose practical algorithms.
We formulate compositional generalization in object-oriented world modeling, and propose a soft and efficient mechanism for practice.