81 citations · 202 across the 38 of their papers we have counts for
38 papers
Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D
Haojie Huang, Owen Howell, Dian Wang +3
Many complex robotic manipulation tasks can be decomposed as a sequence of pick and place actions. Training a robotic agent to learn this sequence over many different starting cond…
Latent Space Symmetry Discovery
Jianke Yang, Nima Dehmamy, Robin Walters +1
Equivariant neural networks require explicit knowledge of the symmetry group. Automatic symmetry discovery methods aim to relax this constraint and learn invariance and equivarianc…
Leveraging Symmetries in Pick and Place
Haojie Huang, Dian Wang, Arsh Tangri +2
Robotic pick and place tasks are symmetric under translations and rotations of both the object to be picked and the desired place pose. For example, if the pick object is rotated o…
Disentangling Node Attributes from Graph Topology for Improved Generalizability in Link Prediction
Ayan Chatterjee, Robin Walters, Giulia Menichetti +1
Link prediction is a crucial task in graph machine learning with diverse applications. We explore the interplay between node attributes and graph topology and demonstrate that inco…
Can Euclidean Symmetry be Leveraged in Reinforcement Learning and Planning?
Linfeng Zhao, Owen Howell, Jung Yeon Park +3
In robotic tasks, changes in reference frames typically do not influence the underlying physical properties of the system, which has been known as invariance of physical laws.These…
Equivariant Single View Pose Prediction Via Induced and Restricted Representations
Owen Howell, David Klee, Ondrej Biza +2
Learning about the three-dimensional world from two-dimensional images is a fundamental problem in computer vision. An ideal neural network architecture for such tasks would levera…
On Robot Grasp Learning Using Equivariant Models
Xupeng Zhu, Dian Wang, Guanang Su +3
Real-world grasp detection is challenging due to the stochasticity in grasp dynamics and the noise in hardware. Ideally, the system would adapt to the real world by training direct…
One-shot Imitation Learning via Interaction Warping
Ondrej Biza, Skye Thompson, Kishore Reddy Pagidi +7
Imitation learning of robot policies from few demonstrations is crucial in open-ended applications. We propose a new method, Interaction Warping, for learning SE(3) robotic manipul…
Improving Convergence and Generalization Using Parameter Symmetries
Bo Zhao, Robert M. Gower, Robin Walters +1
In many neural networks, different values of the parameters may result in the same loss value. Parameter space symmetries are loss-invariant transformations that change the model p…
A General Theory of Correct, Incorrect, and Extrinsic Equivariance
Dian Wang, Xupeng Zhu, Jung Yeon Park +4
Although equivariant machine learning has proven effective at many tasks, success depends heavily on the assumption that the ground truth function is symmetric over the entire doma…
Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction
David M. Klee, Ondrej Biza, Robert Platt +1
Predicting the pose of objects from a single image is an important but difficult computer vision problem. Methods that predict a single point estimate do not predict the pose of ob…
Generative Adversarial Symmetry Discovery
Jianke Yang, Robin Walters, Nima Dehmamy +1
Despite the success of equivariant neural networks in scientific applications, they require knowing the symmetry group a priori. However, it may be difficult to know which symmetry…
The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry
Dian Wang, Jung Yeon Park, Neel Sortur +3
Extensive work has demonstrated that equivariant neural networks can significantly improve sample efficiency and generalization by enforcing an inductive bias in the network archit…
SEIL: Simulation-augmented Equivariant Imitation Learning
Mingxi Jia, Dian Wang, Guanang Su +4
In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the…
Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detection
Haojie Huang, Dian Wang, Xupeng Zhu +2
Given point cloud input, the problem of 6-DoF grasp pose detection is to identify a set of hand poses in SE(3) from which an object can be successfully grasped. This important prob…
Symmetries, flat minima, and the conserved quantities of gradient flow
Bo Zhao, Iordan Ganev, Robin Walters +2
Empirical studies of the loss landscape of deep networks have revealed that many local minima are connected through low-loss valleys. Yet, little is known about the theoretical ori…
Quiver neural networks
Iordan Ganev, Robin Walters
We develop a uniform theoretical approach towards the analysis of various neural network connectivity architectures by introducing the notion of a quiver neural network. Inspired b…
Image to Icosahedral Projection for Object Reasoning from Single-View Images
David Klee, Ondrej Biza, Robert Platt +1
Reasoning about 3D objects based on 2D images is challenging due to variations in appearance caused by viewing the object from different orientations. Tasks such as object classifi…
Data Augmentation vs. Equivariant Networks: A Theory of Generalization on Dynamics Forecasting
Rui Wang, Robin Walters, Rose Yu
Exploiting symmetry in dynamical systems is a powerful way to improve the generalization of deep learning. The model learns to be invariant to transformation and hence is more robu…
Integrating Symmetry into Differentiable Planning with Steerable Convolutions
Linfeng Zhao, Xupeng Zhu, Lingzhi Kong +2
We study how group symmetry helps improve data efficiency and generalization for end-to-end differentiable planning algorithms when symmetry appears in decision-making tasks. Motiv…
Topological Deep Learning: Going Beyond Graph Data
Mustafa Hajij, Ghada Zamzmi, Theodore Papamarkou +11
Topological deep learning is a rapidly growing field that pertains to the development of deep learning models for data supported on topological domains such as simplicial complexes…
Symmetry Teleportation for Accelerated Optimization
Bo Zhao, Nima Dehmamy, Robin Walters +1
Existing gradient-based optimization methods update parameters locally, in a direction that minimizes the loss function. We study a different approach, symmetry teleportation, that…
Probabilistic Symmetry for Multi-Agent Dynamics
Sophia Sun, Robin Walters, Jinxi Li +1
Learning multi-agent dynamics is a core AI problem with broad applications in robotics and autonomous driving. While most existing works focus on deterministic prediction, producin…
Toward Compositional Generalization in Object-Oriented World Modeling
Linfeng Zhao, Lingzhi Kong, Robin Walters +1
Compositional generalization is a critical ability in learning and decision-making. We focus on the setting of reinforcement learning in object-oriented environments to study compo…