A self-supervised multimodal alignment step plus equivariant GNN-based MARL yields over twofold sensing accuracy and 50% performance gains in decentralized V2I rate maximization.
Group equivariant convolutional networks,
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
PhyGAIL uses bounded local graphs and physics-informed graph neural networks with gated message passing for attraction and repulsion to enable zero-shot transfer of recovery policies from 20-UAV to 500-UAV swarms.
A JAX-implemented flow-based equivariant model for multi-embodiment grasping that deduces kinematics from geometry to support variable-DoF grippers with a new dataset of 25k scenes and 20M grasps.
A DoF codec exploiting kernel symmetries compresses neural models for noisy channels and projects received weights onto the symmetry subspace to mitigate errors, outperforming pruning on MNIST and CIFAR-10.
citing papers explorer
-
Equivariant Multi-agent Reinforcement Learning for Multimodal Vehicle-to-Infrastructure Systems
A self-supervised multimodal alignment step plus equivariant GNN-based MARL yields over twofold sensing accuracy and 50% performance gains in decentralized V2I rate maximization.
-
Zero-Shot Scalable Resilience in UAV Swarms: A Decentralized Imitation Learning Framework with Physics-Informed Graph Interactions
PhyGAIL uses bounded local graphs and physics-informed graph neural networks with gated message passing for attraction and repulsion to enable zero-shot transfer of recovery policies from 20-UAV to 500-UAV swarms.
-
Towards a Multi-Embodied Grasping Agent
A JAX-implemented flow-based equivariant model for multi-embodiment grasping that deduces kinematics from geometry to support variable-DoF grippers with a new dataset of 25k scenes and 20M grasps.
-
Leveraging Kernel Symmetry for Joint Compression and Error Mitigation in Edge Model Transfer
A DoF codec exploiting kernel symmetries compresses neural models for noisy channels and projects received weights onto the symmetry subspace to mitigate errors, outperforming pruning on MNIST and CIFAR-10.