Junbang Liang

Email: junbang [dot] liang [at] columbia.edu

original_photo_circle.png

I am a master’s student at Columbia University, advised by Carl Vondrick. Previously I completed my BE(Hons) in Mechatronics Engineering at The University of Auckland, where I worked on robotics at the New Dexterity research group advised by Minas Liarokapis.

My research focuses on improving the scalability of robotic systems leveraging large-scale pretraining of language and vision models, pushing robots towards handling a wide range of real-world scenarios and complex tasks.

In my free time, I enjoy spending time with my friends building creative gadgets and systems such as LightSense. Feel free to email me to chat about research and opportunities!

Publications

  1. dreamitate.gif
    Dreamitate: Real-World Visuomotor Policy Learning via Video Generation
    Junbang Liang*, Ruoshi Liu*, Ege Ozguroglu, Sruthi Sudhakar, Achal Dave, Pavel Tokmakov, Shuran Song, and Carl Vondrick
    Conference on Robot Learning, 2024
    HTML PDF Video
  2. assembly.gif
    On Robust Assembly of Flexible Flat Cables Combining CAD and Image Based Multiview Pose Estimation and a Multi-Modal Robotic Gripper
    Junbang Liang, Joao Buzzatto, Bryan Busby, Haodan Jiang, Saori Matsunaga, Rintaro Haraguchi, Toshisada Mariyama, Bruce A MacDonald, and Minas Liarokapis
    IEEE Open Journal of the Industrial Electronics Society, 2024
    PDF Video
  3. paperbot.gif
    PaperBot: Learning to Design Real-World Tools Using Paper
    Ruoshi Liu, Junbang Liang, Sruthi Sudhakar, Huy Ha, Cheng Chi, Shuran Song, and Carl Vondrick
    arXiv preprint, 2024
    HTML PDF Video
  4. identification.gif
    Employing Multi-Layer, Sensorised Kirigami Grippers for Single-Grasp Based Identification of Objects and Force Exertion Estimation
    Junbang Liang, Joao Buzzatto, Bryan Busby, Ricardo V Godoy, Saori Matsunaga, Rintaro Haraguchi, Toshisada Mariyama, Bruce A MacDonald, and Minas Liarokapis
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 2023
    HTML PDF Video
  5. bioinspired.gif
    A Tailsitter UAV Based on Bioinspired, Tendon-Driven, Shape-Morphing Wings with Aerofoil-Shaped Artificial Feathers
    Junbang Liang, Joao Buzzatto, and Minas Liarokapis
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 2023
    HTML PDF Video
  6. compress.gif
    A Soft, Multi-Layer, Kirigami Inspired Robotic Gripper with a Compact, Compression-Based Actuation System
    Joao Buzzatto, Junbang Liang, Mojtaba Shahmohammadi, Saori Matsunaga, Rintaro Haraguchi, Toshisada Mariyama, Bruce A MacDonald, and Minas Liarokapis
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 2023
    HTML PDF Video
  7. jamming.gif
    Mechanically Programmable Jamming Based on Articulated Mesh Structures for Variable Stiffness Robots
    Geng Gao, Junbang Liang, and Minas Liarokapis
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 2022
    HTML PDF Video
  8. disposable.gif
    Soft, Multi-layer, Disposable, Kirigami Based Robotic Grippers: On Handling of Delicate, Contaminated, and Everyday Objects
    Joao Buzzatto, Mojtaba Shahmohammadi, Junbang Liang, Felipe Sanches, Saori Matsunaga, Rintaro Haraguchi, Toshisada Mariyama, Bruce MacDonald, and Minas Liarokapis
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 2022
    HTML PDF Video
  9. aerial.png
    An Adaptive, Reconfigurable, Tethered Aerial Grasping System for Reliable Caging and Transportation of Packages
    Shaoqian Lin, Joao Buzzatto, Junbang Liang, and Minas Liarokapis
    In IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) , 2022
    HTML PDF Video