Linfeng Zhao

Linfeng Zhao

CS Ph.D. Student

Northeastern University


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.



Publication List

(2022). Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation. In ICLR 2023.

PDF OpenReview

(2022). Learning to Navigate in Mazes with Novel Layouts Using Abstract Top-down Maps. Under Conference Review.

(Extended version coming soon)

(2022). Integrating Symmetry into Differentiable Planning with Steerable Convolutions. In ICLR 2023, RLDM 2022.

PDF Webpage (Available soon) OpenReview

(2022). Toward Compositional Generalization in Object‑Oriented World Modeling. In ICML 2022 (Long Presentation, 2.1%), RLDM 2022.

PDF Code ICML Page Website (Available soon) Poster (RLDM, v1) Poster (ICML, v2)

(2022). Learning Symmetric Embeddings for Equivariant World Models. In ICML 2022.

PDF Code ICML Page

(2020). Model-based Navigation in Environments with Novel Layouts Using Abstract 2-D Maps. In Deep RL workshop at NeurIPS 2020.

PDF Poster Slides Video

(2020). Deep Imitation Learning for Bimanual Robotic Manipulation. In NeurIPS 2020.

PDF Poster NeurIPS Page

(2020). Match Plan Generation in Web Search with Parameterized Action Reinforcement Learning. In WWW 2021.

PDF Video Source Document

(2019). InterFact: Towards Interactive Factorization of Actionable Entities. In preparation.