Capabilities

Diffeomorphic Transforms for Generalised Imitation Learning L4DC 2022 Differentiable Dynamics for Articulated 3D Human Motion Reconstruction CVPR 2022 DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools ICLR 2022 Discovering State and Action Abstractions for Generalized Task and Motion Planning AAAI 2022 Ditto: Building Digital Twins of Articulated Objects From Interaction CVPR 2022 Egocentric Prediction of Action Target in 3D CVPR 2022 Few-shot Subgoal Planning with Language Models NAACL 2022 FILM: Following Instructions in Language with Modular Methods ICLR 2022 Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction CVPR 2022 FS6D: Few-Shot 6D Pose Estimation of Novel Objects CVPR 2022 Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior CVPR 2022 Global-Aware Registration of Less-Overlap RGB-D Scans CVPR 2022 Habitat-Web: Learning Embodied Object-Search Strategies From Human Demonstrations at Scale CVPR 2022 Hierarchical Few-Shot Imitation with Skill Transition Models ICLR 2022 HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction CVPR 2022 HSC4D: Human-Centered 4D Scene Capture in Large-Scale Indoor-Outdoor Space Using Wearable IMUs and LiDAR CVPR 2022 HTRON: Efficient Outdoor Navigation with Sparse Rewards via Heavy Tailed Adaptive Reinforce Algorithm CoRL 2022 Human-in-the-loop Robotic Grasping Using BERT Scene Representation COLING 2022 HybVIO: Pushing the Limits of Real-Time Visual-Inertial Odometry WACV 2022 Information Extraction and Human-Robot Dialogue towards Real-life Tasks A Baseline Study with the MobileCS Dataset EMNLP 2022 Interactron: Embodied Adaptive Object Detection CVPR 2022 Is Mapping Necessary for Realistic PointGoal Navigation? CVPR 2022 Iterative Residual Policy for Goal-Conditioned Dynamic Manipulation of Deformable Objects RSS 2022 KernelGPA: A Deformable SLAM Back-end RSS 2022 Learning Active Camera for Multi-Object Navigation NeurIPS 2022