Kuan Fang


Email: kuanfang [at] berkeley [dot] edu

I am a Postdoctoral Scholar at the Berkeley Artificial Intelligence Research (BAIR) working with Sergey Levine. I received my Ph.D. from Stanford University, advised by Fei-Fei Li and Silvio Savarese. I received my B.E. degree from Tsinghua University. I have spent time at Google Brain, Google [x] Robotics and Microsoft Research Asia. My research is supported by a Computing Innovation Fellowship.

Google Scholar   |   GitHub   |   LinkedIn   |   Twitter


I will be joining the Department of Computer Science at Cornell University in Fall 2024.

Research

My research aims to enable robots to solve diverse and complex tasks in unstructured environments. To that end, I work towards building scalable data-driven methods for perception and control, with a focus on two axes: (1) How to automate data collection through the generation of feasible, diverse, and useful tasks in simulation and the real world; and correspondingly, (2) how to acquire general-purpose skills that are robust, adaptable, and extensible for efficiently solving novel long-horizon tasks.

News


Preprints


Stabilizing Contrastive RL: Techniques for Offline Goal Reaching
Chongyi Zheng, Benjamin Eysenbach, Homer Walke, Patrick Yin, Kuan Fang, Ruslan Salakhutdinov, Sergey Levine
ArXiv Preprint
PDF | Website | Code | BibTex

Multi-Stage Cable Routing Through Hierarchical Imitation Learning
Jianlan Luo*, Charles Xu*, Xinyang Geng*, Gilbert Feng, Kuan Fang, Liam Tan, Stefan Schaal, Sergey Levine
ArXiv Preprint
PDF | Website | Code | Dataset | BibTex

Publications


Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control
Vivek Myers*, Andre He*, Kuan Fang, Homer Walke, Philippe Hansen-Estruch, Ching-An Cheng, Mihai Jalobeanu, Andrey Kolobov, Anca Dragan, Sergey Levine
CoRL 2023
PDF | Website | Code | BibTex

BridgeData V2: A Dataset for Robot Learning at Scale
Homer Walke, Kevin Black, Abraham Lee, Moo Jin Kim, Max Du, Chongyi Zheng, Tony Zhao, Philippe Hansen-Estruch, Quan Vuong, Andre He, Vivek Myers, Kuan Fang, Chelsea Finn, Sergey Levine
CoRL 2023
PDF | Website | Code | Data | BibTex

Active Task Randomization: Learning Robust Skills Via Unsupervised Generation of Diverse and Feasible Tasks
Kuan Fang*, Toki Migimatsu*, Ajay Mandlekar, Li Fei-Fei, Jeannette Bohg
IROS 2023
PDF | Website | BibTex

Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks
Kuan Fang, Patrick Yin, Ashvin Nair, Homer Walke, Gengchen Yan, Sergey Levine

CoRL 2022 (Oral Presentation)

PDF | Website | Code | BibTex

Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space
Kuan Fang*, Patrick Yin*, Ashvin Nair, Sergey Levine (* indicates equal contribution)
IROS 2022
PDF | Website | Code | BibTex

Discovering Generalizable Skills via Automated Generation of Diverse Tasks
Kuan Fang, Yuke Zhu, Silvio Savarese, Li Fei-Fei
RSS 2021
PDF | Website | BibTex

Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations
Zhenyu Jiang, Yifeng Zhu, Maxwell Svetlik, Kuan Fang, Yuke Zhu,
RSS 2021
PDF | Website | Code | BibTex

Adaptive Procedural Task Generation for Hard-Exploration Problems
Kuan Fang, Yuke Zhu, Silvio Savarese, Li Fei-Fei
ICLR 2021
PDF | Website | BibTex

KETO: Learning Keypoint Representations for Tool Manipulation
Zengyi Qin, Kuan Fang, Yuke Zhu, Li Fei-Fei, Silvio Savarese
ICRA 2020
PDF | Website | Code | BibTex

Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation
Kuan Fang, Yuke Zhu, Animesh Garg, Silvio Savarese, Li Fei-Fei

CoRL 2019 (Oral Presentation)

PDF | Website | Blog | Environment | Code | BibTex

Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks
Kuan Fang, Alexander Toshev, Li Fei-Fei, Silvio Savarese
CVPR 2019
PDF | Website | BibTex

Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision
Kuan Fang, Yuke Zhu, Animesh Garg, Andrey Kurenkov, Viraj Mehta, Li Fei-Fei, Silvio Savarese
RSS 2018 (Journal version in IJRR 2019)
PDF (RSS 2018) | PDF (IJRR 2019) | Website | Video | BibTex

Multi-Task Domain Adaptation for Deep Learning of Instance Grasping from Simulation
Kuan Fang, Yunfei Bai, Stefan Hinterstoisser, Silvio Savarese, Mrinal Kalakrishnan
ICRA 2018
PDF | Website | Video | BibTex

Demo2Vec: Reasoning Object Affordances from Online Videos
Kuan Fang*, Te-Lin Wu*, Daniel Yang, Silvio Savarese, Joseph J. Lim (* indicates equal contribution)
CVPR 2018
PDF | Website | Code | BibTex

Recurrent Autoregressive Networks for Online Multi-Object Tracking
Kuan Fang, Yu Xiang, Xiaocheng Li, Silvio Savarese
WACV 2018
PDF | Video | BibTex

DeLay: Robust Spatial Layout Estimation for Cluttered Indoor Scenes
Saumitro Dasgupta, Kuan Fang*, Kevin Chen*, Silvio Savarese (* indicates equal contribution)
CVPR 2016
PDF | Website | BibTex

Awards and Honors


Teaching


Website template courtesy