30 citations · 52 across the 22 of their papers we have counts for
27 papers
Training Generalist Navigation Policies via Action Self-Distillation
Bowen Feng, Keqin Wang, Yulong Yang +4
Language provides a natural interface for humans to specify and reason about goals, but training language-conditioned robotic policies and reasoning typically requires expensive ma…
Higher-Order Morphology Priors for Quadruped Reinforcement Learning Under Actuator Degradation
Derek You, Zafir Shamsi, Keqin Wang +1
Actuator degradation turns quadruped locomotion into a coordination problem requiring joints to compensate for lost actuation. Prior work suggests that morphology-aware graph polic…
Demonstration Calibrated Port-Hamiltonian Retuning for Manipulation Policies
Yulong Yang, Fan Wu, Christine Allen-Blanchette +1
Diffusion and VLA policies for manipulation are often deployed through downstream impedance controllers. The stiffness and damping gains of these controllers affect task success, y…
Learning Discrete Riemannian Metrics for Physical Fields with Cochain-Frame Equivariance
Dongzhe Zheng, Christine Allen-Blanchette
Physical fields on meshes require a separation between topology and geometry: differential identities should remain exact, while geometry, material response, and anisotropic coupli…
Generating Physically Plausible Parachute Dynamics with Deep Generative Modeling
Yulong Yang, Clara O'Farrell, Christine Allen-Blanchette
Accurately modeling the dynamics of planetary parachute and entry vehicle systems is critical for Entry, Descent, and Landing events such as vehicle separation and sensor activatio…
Topology-Preserving Neural Operator Learning via Hodge Decomposition
Dongzhe Zheng, Tao Zhong, Christine Allen-Blanchette
In this paper, we study solution operators of physical field equations on geometric meshes from a function-space perspective. We reveal that Hodge orthogonality fundamentally resol…
HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts
Tao Zhong, Dongzhe Zheng, Christine Allen-Blanchette
Sparse Mixture-of-Experts (MoE) layers route tokens through a handful of experts, and learning-free compression of these layers reduces inference cost without retraining. A subtle…
Neural Fields for NV-Center Inverse Sensing
Zhixuan Zhao, Tao Zhong, Yixun Hu +2
Inverse problems in scientific sensing are often solved with either hand-designed regularizers or supervised networks trained on simulated labels, yet both can fail when the forwar…
Frequency-Separable Hamiltonian Neural Network for Multi-Timescale Dynamics
Yaojun Li, Yulong Yang, Christine Allen-Blanchette
While Hamiltonian mechanics provides a powerful inductive bias for neural networks modeling dynamical systems, Hamiltonian Neural Networks and their variants often fail to capture…
Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation
Tao Zhong, Yixun Hu, Dongzhe Zheng +2
Inverse problems for stiff parabolic partial differential equations (PDEs), such as the inverse heat conduction problem (IHCP), are severely ill-posed: the forward map rapidly damp…
A Hypertoroidal Covering for Perfect Color Equivariance
Yulong Yang, Zhikun Xu, Yaojun Li +1
When the color distribution of input images changes at inference, the performance of conventional neural network architectures drops considerably. A few researchers have begun to i…
Discovering Phase Space Structure in Learned Hamiltonian Systems
Jiayin Liu, Yulong Yang, Vineet Bansal +1
Mechanics-inspired neural dynamical models improve interpretability and physical consistency, but they usually assume a known configuration space, fixed physical parameters, and de…
Local-Canonicalization Equivariant Graph Neural Networks for Sample-Efficient and Generalizable Swarm Robot Control
Keqin Wang, Tao Zhong, David Chang +1
Multi-agent reinforcement learning (MARL) policies for swarm control often learn inefficiently and generalize poorly across coordinate frames, team sizes, and agent roles. We intro…
Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schrödinger Bridges
Tao Zhong, Jonah Buchanan, Christine Allen-Blanchette
We propose a new approach to vision-based dexterous grasp translation, which aims to transfer grasp intent across robotic hands with differing morphologies. Given a visual observat…
Surrogate Modeling of 3D Rayleigh-Benard Convection with Equivariant Autoencoders
Fynn Fromme, Hans Harder, Christine Allen-Blanchette +1
The use of machine learning for modeling, understanding, and controlling large-scale physics systems is quickly gaining in popularity, with examples ranging from electromagnetism o…
GAGrasp: Geometric Algebra Diffusion for Dexterous Grasping
Tao Zhong, Christine Allen-Blanchette
We propose GAGrasp, a novel framework for dexterous grasp generation that leverages geometric algebra representations to enforce equivariance to SE(3) transformations. By encoding…
Resolving Oversmoothing with Opinion Dissensus
Keqin Wang, Yulong Yang, Ishan Saha +1
While graph neural networks (GNNs) have allowed researchers to successfully apply neural networks to non-Euclidean domains, deep GNNs often exhibit lower predictive performance tha…
Behavior-Inspired Neural Networks for Relational Inference
Yulong Yang, Bowen Feng, Keqin Wang +3
From pedestrians to Kuramoto oscillators, interactions between agents govern how dynamical systems evolve in space and time. Discovering how these agents relate to each other has t…
Learning Color Equivariant Representations
Yulong Yang, Felix O'Mahony, Christine Allen-Blanchette
In this paper, we introduce group convolutional neural networks (GCNNs) equivariant to color variation. GCNNs have been designed for a variety of geometric transformations from 2D…
Hamiltonian GAN
Christine Allen-Blanchette
A growing body of work leverages the Hamiltonian formalism as an inductive bias for physically plausible neural network based video generation. The structure of the Hamiltonian ens…
Learning to Predict 3D Rotational Dynamics from Images of a Rigid Body with Unknown Mass Distribution
Justice Mason, Christine Allen-Blanchette, Nicholas Zolman +2
In many real-world settings, image observations of freely rotating 3D rigid bodies may be available when low-dimensional measurements are not. However, the high-dimensionality of i…
Learning Interpretable Dynamics from Images of a Freely Rotating 3D Rigid Body
Justice Mason, Christine Allen-Blanchette, Nicholas Zolman +2
In many real-world settings, image observations of freely rotating 3D rigid bodies, such as satellites, may be available when low-dimensional measurements are not. However, the hig…
Joint Estimation of Image Representations and their Lie Invariants
Christine Allen-Blanchette, Kostas Daniilidis
Images encode both the state of the world and its content. The former is useful for tasks such as planning and control, and the latter for classification. The automatic extraction…
LagNetViP: A Lagrangian Neural Network for Video Prediction
Christine Allen-Blanchette, Sushant Veer, Anirudha Majumdar +1
The dominant paradigms for video prediction rely on opaque transition models where neither the equations of motion nor the underlying physical quantities of the system are easily i…