VenueCode/DataLink
NeurIPS24CodePhyRecon: Physically Plausible Neural Scene Reconstruction
IROS24CodeAg2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations
IROS24CodePreAfford: Universal Affordance-Based Pre-Grasping for Diverse Objects and Environments
ECCV24CodeZero-Shot Image Feature Consensus with Deep Functional Maps
CogSci24CodeEvaluating and Modeling Social Intelligence: A Comparative Study of Human and AI Capabilities
CVPR24CodeMove as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance
CVPR24CodeAnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents
CVPR24CodeScaling Up Dynamic Human-Scene Interaction Modeling
CVPR24HuggingFaceScaling Up Dynamic Human-Scene Interaction Modeling
RAL24CodeGrasp Multiple Objects with One Hand
RAL24DatasetGrasp Multiple Objects with One Hand
3DV24CodeSingle-view 3D Scene Reconstruction with High-fidelity Shape and Texture
3DV24DatasetSingle-view 3D Scene Reconstruction with High-fidelity Shape and Texture
ICLR24CodeI-PHYRE: Interactive Physical Reasoning
ICLR24CodeSparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation
ICLR24CodeNeural-Symbolic Recursive Machine for Systematic Generalization
NeurIPS23CodeProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab
NeurIPS23DatasetProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab
NeurIPS23CodeActive Reasoning in an Open-World Environment
NeurIPS23CodeChimpAct: A Longitudinal Dataset for Understanding Chimpanzee Behaviors
NeurIPS23Data ExamplesChimpAct: A Longitudinal Dataset for Understanding Chimpanzee Behaviors
NeurIPS23DatasetChimpAct: A Longitudinal Dataset for Understanding Chimpanzee Behaviors
NeurIPS23Code & DatasetEvaluating and Inducing Personality in Pre-trained Language Models
NeurIPS23Online GameInteractive Visual Reasoning under Uncertainty
NeurIPS23CodeInteractive Visual Reasoning under Uncertainty
NeurIPS23Data ExamplesInteractive Visual Reasoning under Uncertainty
ICCV23CodeFull-Body Articulated Human-Object Interaction
ICCV23DatasetFull-Body Articulated Human-Object Interaction
ICCV23CodeX-VoE: Measuring eXplanatory Violation of Expectation in Physical Events
ICCV23DatasetX-VoE: Measuring eXplanatory Violation of Expectation in Physical Events
IROS23CodePart-level Scene Reconstruction Affords Robot Interaction
ICML23CodeMEWL: Few-shot multimodal word learning with referential uncertainty
ICML23DatasetMEWL: Few-shot multimodal word learning with referential uncertainty
ICML23CodeOn the Complexity of Bayesian Generalization
CVPR23CodeDiffusion-based Generation, Optimization, and Planning in 3D Scenes
CVPR23CheckpointsDiffusion-based Generation, Optimization, and Planning in 3D Scenes
CVPR23HuggingFaceDiffusion-based Generation, Optimization, and Planning in 3D Scenes
ICLR23CodeUnderstanding Embodied Reference with Touch-Line Transformer
ICLR23CodeA Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics
ICLR23DatasetA Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics
ICRA23CodeGenDexGrasp: Generalizable Dexterous Grasping
ICRA23DatasetGenDexGrasp: Generalizable Dexterous Grasping
ICRA23CodeRearrange Indoor Scenes for Human-Robot Co-Activity
NeurIPS22CodeOn the Learning Mechanisms in Physical Reasoning
NeurIPS22CodeEmergent Graphical Conventions in a Visual Communication Game
NeurIPS22CodeHUMANISE: Language-conditioned Human Motion Generation in 3D Scenes
NeurIPS22DatasetHUMANISE: Language-conditioned Human Motion Generation in 3D Scenes
IJCV22CodeScene Reconstruction with Functional Objects for Robot Autonomy
ScienceRobotics22Code & DataIn situ bidirectional human-robot value alignment
ECCV22CodeLearning Algebraic Representation for Systematic Generalization in Abstract Reasoning
ECCV22DatasetLearning Algebraic Representation for Systematic Generalization in Abstract Reasoning
IROS22CodePlanning Sequential Tasks on Contact Graph
RA-L22CodeUnderstanding Physical Effects for Effective Tool-use
ICML22CodeLatent Diffusion Energy-Based Model for Interpretable Text Modeling
RA-L22CodeObject Gathering with a Tethered Robot Duo
NeurIPS21CodeUnsupervised Foreground Extraction via Deep Region Competition
ICCV21CodeYouRefIt: Embodied Reference Understanding with Language and Gesture
ICCV21DatasetYouRefIt: Embodied Reference Understanding with Language and Gesture
ICCV21CodeSpatio-temporal Self-Supervised Representation Learning for 3D Point Clouds
RA-L22CodeSynthesizing Diverse and Physically Stable Grasps with Arbitrary Hand Structures using Differentiable Force Closure Estimator
IROS21CodeConsolidating Kinematic Models to Promote Coordinated Mobile Manipulations
IROS21CodeEfficient Task Planning for Mobile Manipulation: a Virtual Kinematic Chain Perspective
IROS21CodeCommunicative Learning with Natural Gestures for Embodied Navigation Agents with Human-in-the-Scene
CVPR21CodeLearning Triadic Belief Dynamics in Nonverbal Communication from Videos
CVPR21DataLearning Triadic Belief Dynamics in Nonverbal Communication from Videos
CVPR21CodeACRE: Abstract Causal Reasoning Beyond Covariation
CVPR21DatasetACRE: Abstract Causal Reasoning Beyond Covariation
CVPR21CodeAbstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution
ICRA21CodeReconstructing Interactive 3D Scene by Panoptic Mapping and CAD Model Alignments
ICRA21CodeCongestion-aware Multi-agent Trajectory Prediction for Collision Avoidance
IJNME21CodeLagrangian‐Eulerian Multi‐Density Topology Optimization with the Material Point Method
ECCV20CodeLEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities
ECCV20DatasetLEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities
IROS20CodeHuman-Robot Interaction in a Shared Augmented Reality Workspace
IROS20CodeGraph-based Hierarchical Knowledge Representation for Robot Task Transfer from Virtual to Physical World
SIGGRAPH20CodeA Massively Parallel and Scalable Multi-GPU Material Point Method
SIGGRAPH20CodeIQ-MPM: An Interface Quadrature Material Point Method for Non-sticky Strongly Two-Way Coupled Nonlinear Solids and Fluids
ICRA20CodeCongestion-aware Evacuation Routing using Augmented Reality Devices
ScienceRobotics19CodeA tale of two explanations: Enhancing human trust by explaining robot behavior
AAAI20CodeTheory-based Causal Transfer: Integrating Instance-level Induction and Abstract-level Structure Learning
AAAI20CodeMachine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning
AAAI20DatasetMachine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning [Google Drive] [Baidu Netdisk]
NeurIPS19CodeLearning Perceptual Inference by Contrasting
ICCV19CodeHolistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense
IROS19CodeLearning Virtual Grasp with Failed Demonstrations via Bayesian Inverse Reinforcement Learning
TURC19CodeVRGym: A Virtual Testbed for Physical and Interactive AI
CVPR19CodeRAVEN: A Dataset for Relational and Analogical Visual rEasoNing
CVPR19DatasetRAVEN-10000
ICRA19CodeHigh-Fidelity Grasping in Virtual Reality using a Glove-based System
ICRA19CodeSelf-Supervised Incremental Learning for Sound Source Localization in Complex Indoor Environment
AAAI19CodeMetaStyle: Three-Way Trade-Off Among Speed, Flexibility and Quality in Neural Style Transfer
NeurIPS18CodeCooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation
ECCV18CodeHolistic 3D Scene Parsing and Reconstruction from a Single RGB Image
CogSci18CodeHuman Causal Transfer: Challenges for Deep Reinforcement Learning
CVPR18CodeHuman-centric Indoor Scene Synthesis Using Stochastic Grammar
SIGGRAPH18CodeA Moving Least Squares Material Point Method with Displacement Discontinuity and Two-Way Rigid Body Coupling
ICRA18CodeInteractive Robot Knowledge Patching using Augmented Reality
ICRA18CodeUnsupervised Learning of Hierarchical Models for Hand-Object Interactions
IROS17CodeFeeling the Force: Integrating Force and Pose for Fluent Discovery through Imitation Learning to Open Medicine Bottles
IROS17CodeA Glove-based System for Studying Hand-Object Manipulation via Joint Pose and Force Sensing
SIGGRAPHAsia16WorkshopCodeA Virtual Reality Platform for Dynamic Human-Scene Interaction
CVPR16CodeFEM Simulation for Inferring Forces during Human-scene Interactions
CVPR16DataWatertight 3D Scene Dataset
CVPR15CodeKinect2 Toolbox
CVPR15DataTool 3D Dataset