Publications (75)
Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations
Minghao Fu, Fan Feng, Nicklas Hansen +1
World models enable agents to predict future dynamics conditioned on actions, making the choice of latent representation central to planning and control. Such representations are o…
Objective Moiré Pattern
Fan Feng
Moiré patterns, typically formed by overlaying two layers of two-dimensional materials, exhibit an effective long-range periodicity that depends on the short-range periodicity of…
Evolving, complex topography from combining centers of Gaussian curvature
Fan Feng, John S. Biggins, Mark Warner
Liquid crystal elastomers and glasses can have significant shape change determined by their director patterns. Cones deformed from circular director patterns have non-trivial Gauss…
Learning Object Manipulation from Scratch via Contrastive Interaction
Tongle Shen, Caleb Chuck, Fan Feng +1
Contrastive Reinforcement Learning (CRL) has seen recent success in a wide variety of goal-conditioned robotics tasks by learning structured representations of the dynamics. Howeve…
OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learning
Qi She, Fan Feng, Xinyue Hao +9
The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses u…
Incremental Few-Shot Object Detection for Robotics
Yiting Li, Haiyue Zhu, Sichao Tian +6
Incremental few-shot learning is highly expected for practical robotics applications. On one hand, robot is desired to learn new tasks quickly and flexibly using only few annotated…