Linfeng Zhao

Linfeng Zhao

CS Ph.D. Student

Northeastern University

Biography

I am Linfeng Zhao (赵林风), a CS Ph.D. student at Khoury College of Computer Sciences of Northeastern University. I’m advised by Prof. Lawson L.S. Wong and also working with Prof. Robin Walters. During PhD: I am collaborating with and visiting MIT LIS group led by Prof. Leslie Kaelbling and Prof. Tomás Lozano-Pérez. I interned at Meta (2024 summer), Boston Dynamics AI Institute (2023 Spring-Summer) and earlier at Amazon Science (2021 Summer). During undergraduate: I interned at Microsoft Research Asia (2019) and earlier worked with Prof. Hao Su at UC San Diego (2018-19).

My research focuses on enabling robots and agents to act in open-world and long-horizon scenarios by advancing learning for planning and world modeling. I employ structured approaches that integrate planning and perception, leveraging lossless and lossy abstractions such as symmetry, compositionality, and hierarchy. My work involves building learning-based systems that bridge perception and planning through neural networks, including the use of recent pre-trained foundation models, to enhance scalability, generalizability, and efficiency in decision-making systems.

Updates

Publications

Publication List

(2024). ThinkGrasp: A Vision-Language System for Strategic Part Grasping in Clutter. In CoRL 2024.

PDF Project Video

(2024). Open-vocabulary Pick and Place via Patch-level Semantic Maps. In Conference Submission.

arXiv

(2024). Equivariant Action Sampling for Reinforcement Learning and Planning. In WAFR 2024.

PDF Poster Slides Program Page (WAFR 2024) arXiv (Coming soon) Code (Coming soon)

(2024). Practice Makes Perfect: Planning to Learn Skill Parameter Policies. In RSS 2024.

PDF Code Project Video Press (MIT News)

(2023). Sample Efficient Modeling of Drag Coefficients for Satellites with Symmetry. In Workshop on Symmetry and Geometry in Neural Representations @ NeurIPS 2023.

OpenReview

(2023). Language Conditioned Equivariant Grasp. In Conference Submission.

arXiv (coming soon)

(2023). E(2)-Equivariant Graph Planning for Navigation. In RA-L 2024, Present at IROS 2024.

Project Slides arXiv Program (IROS 2024 oral) Code (Coming soon)

(2023). Can Euclidean Symmetry Help in Reinforcement Learning and Planning?. In TAGML Workshop @ ICML 2023.

Poster arXiv OpenReview Workshop Page (ICML 2023)

(2023). Equivariant Single View Pose Prediction Via Induced and Restriction Representations. In NeurIPS 2023.

arXiv

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

PDF Code Poster Slides ICLR page OpenReview arXiv Webpage (Available soon)

(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 (ICML) Slides (ICML oral)

(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 @ 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.