{"total":95,"rows":[{"id":"2102.09844","title":"E(n) Equivariant Graph Neural Networks","created":"2021-02-19","cited_by_count":965,"area":null},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209,"area":null},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147,"area":null},{"id":"2105.00696","title":"Graph Learning: A Survey","created":"2021-05-03","cited_by_count":141,"area":null},{"id":"2106.05266","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","created":"2021-06-09","cited_by_count":141,"area":null},{"id":"2104.02646","title":"gradSim: Differentiable simulation for system identification and visuomotor control","created":"2021-04-06","cited_by_count":100,"area":null},{"id":"2211.08064","title":"Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications","created":"2022-11-15","cited_by_count":92,"area":null},{"id":"2403.02622","title":"World Models for Autonomous Driving: An Initial Survey","created":"2024-03-05","cited_by_count":80,"area":"wm"},{"id":"2103.01937","title":"Neural Production Systems: Learning Rule-Governed Visual Dynamics","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2202.11855","title":"Learning Multi-Object Dynamics with Compositional Neural Radiance Fields","created":"2022-02-24","cited_by_count":63,"area":null},{"id":"2110.15358","title":"Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language","created":"2021-10-28","cited_by_count":55,"area":null},{"id":"2302.04419","title":"An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning","created":"2023-02-09","cited_by_count":49,"area":null},{"id":"2207.14299","title":"Graph Inverse Reinforcement Learning from Diverse Videos","created":"2022-07-28","cited_by_count":46,"area":"offlinerl"},{"id":"2108.05928","title":"Data-driven discovery of intrinsic dynamics","created":"2021-08-12","cited_by_count":45,"area":null},{"id":"2107.12544","title":"Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning","created":"2021-07-27","cited_by_count":43,"area":null},{"id":"2509.21309","title":"NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics","created":"2025-09-25","cited_by_count":41,"area":null},{"id":"2107.02367","title":"Discrete-Valued Neural Communication","created":"2021-07-06","cited_by_count":39,"area":null},{"id":"2206.07681","title":"Learning to Accelerate Partial Differential Equations via Latent Global Evolution","created":"2022-06-15","cited_by_count":39,"area":null},{"id":"2108.01316","title":"RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting","created":"2021-08-03","cited_by_count":36,"area":null},{"id":"2111.01495","title":"Constructing Neural Network-Based Models for Simulating Dynamical Systems","created":"2021-11-02","cited_by_count":31,"area":null},{"id":"2206.11403","title":"Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation","created":"2022-06-22","cited_by_count":31,"area":"wm"},{"id":"2106.11083","title":"Conditional Neural Relational Inference for Interacting Systems","created":"2021-06-21","cited_by_count":28,"area":null},{"id":"2210.05495","title":"MAgNet: Mesh Agnostic Neural PDE Solver","created":"2022-10-11","cited_by_count":28,"area":null},{"id":"2311.09048","title":"GRASP: A novel benchmark for evaluating language GRounding And Situated Physics understanding in multimodal language models","created":"2023-11-15","cited_by_count":28,"area":"mllm"},{"id":"2501.10928","title":"Generative Physical AI in Vision: A Survey","created":"2025-01-19","cited_by_count":24,"area":null},{"id":"2306.16700","title":"Dynamic-Resolution Model Learning for Object Pile Manipulation","created":"2023-06-29","cited_by_count":22,"area":null},{"id":"2412.01800","title":"PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2202.06481","title":"A Survey on Machine Learning Approaches for Modelling Intuitive Physics","created":"2022-02-14","cited_by_count":20,"area":null},{"id":"2306.02500","title":"Systematic Visual Reasoning through Object-Centric Relational Abstraction","created":"2023-06-04","cited_by_count":20,"area":"lr"},{"id":"2301.11494","title":"Learning Vortex Dynamics for Fluid Inference and Prediction","created":"2023-01-27","cited_by_count":17,"area":null},{"id":"2312.05359","title":"Learning 3D Particle-based Simulators from RGB-D Videos","created":"2023-12-08","cited_by_count":17,"area":null},{"id":"2104.14040","title":"Pushing it out of the Way: Interactive Visual Navigation","created":"2021-04-28","cited_by_count":16,"area":null},{"id":"2404.04308","title":"Visual Knowledge in the Big Model Era: Retrospect and Prospect","created":"2024-04-05","cited_by_count":16,"area":null},{"id":"2302.11864","title":"Grounding Graph Network Simulators using Physical Sensor Observations","created":"2023-02-23","cited_by_count":15,"area":null},{"id":"2407.15589","title":"Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2107.08881","title":"Reasoning-Modulated Representations","created":"2021-07-19","cited_by_count":13,"area":null},{"id":"2410.01376","title":"Learning Physics From Video: Unsupervised Physical Parameter Estimation for Continuous Dynamical Systems","created":"2024-10-02","cited_by_count":13,"area":null},{"id":"2304.11470","title":"3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes","created":"2023-04-22","cited_by_count":12,"area":null},{"id":"2412.11785","title":"InterDyn: Controllable Interactive Dynamics with Video Diffusion Models","created":"2024-12-16","cited_by_count":12,"area":"diffusion"},{"id":"2212.06795","title":"GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation","created":"2022-12-13","cited_by_count":11,"area":null},{"id":"2403.03458","title":"Slot Abstractors: Toward Scalable Abstract Visual Reasoning","created":"2024-03-06","cited_by_count":11,"area":"lr"},{"id":"2101.09486","title":"Neural Relational Inference with Efficient Message Passing Mechanisms","created":"2021-01-23","cited_by_count":10,"area":null},{"id":"2208.05470","title":"EvolveHypergraph: Group-Aware Dynamic Relational Reasoning for Trajectory Prediction","created":"2022-08-10","cited_by_count":10,"area":null},{"id":"2104.12276","title":"Learning to Better Segment Objects from Unseen Classes with Unlabeled Videos","created":"2021-04-25","cited_by_count":9,"area":null},{"id":"2104.14679","title":"Physically Feasible Vehicle Trajectory Prediction","created":"2021-04-29","cited_by_count":8,"area":null},{"id":"2403.11237","title":"FORCE: Physics-aware Human-object Interaction","created":"2024-03-17","cited_by_count":7,"area":null},{"id":"2403.15245","title":"Reasoning-Enhanced Object-Centric Learning for Videos","created":"2024-03-22","cited_by_count":7,"area":"lr"},{"id":"2407.01049","title":"SE(3)-Hyena Operator for Scalable Equivariant Learning","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2101.02930","title":"Symmetry-adapted graph neural networks for constructing molecular dynamics force fields","created":"2021-01-08","cited_by_count":5,"area":null},{"id":"2102.02100","title":"Object and Relation Centric Representations for Push Effect Prediction","created":"2021-02-03","cited_by_count":5,"area":null},{"id":"2105.02799","title":"Object-centric Video Prediction without Annotation","created":"2021-05-06","cited_by_count":5,"area":null},{"id":"2205.11894","title":"Learning Interacting Dynamical Systems with Latent Gaussian Process ODEs","created":"2022-05-24","cited_by_count":5,"area":null},{"id":"2402.03326","title":"Slot Structured World Models","created":"2024-01-08","cited_by_count":5,"area":"wm"},{"id":"2512.03350","title":"SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation","created":"2025-12-03","cited_by_count":5,"area":null},{"id":"2106.13393","title":"Interpreting Depression From Question-wise Long-term Video Recording of SDS Evaluation","created":"2021-06-25","cited_by_count":4,"area":null},{"id":"2301.04783","title":"Predictive World Models from Real-World Partial Observations","created":"2023-01-12","cited_by_count":4,"area":"wm"},{"id":"2410.08983","title":"DEL: Discrete Element Learner for Learning 3D Particle Dynamics with Neural Rendering","created":"2024-10-11","cited_by_count":4,"area":null},{"id":"2410.20922","title":"FACTS: A Factored State-Space Framework For World Modelling","created":"2024-10-28","cited_by_count":4,"area":"wm"},{"id":"2603.16432","title":"IRIS: A Real-World Benchmark for Inverse Recovery and Identification of Physical Dynamic Systems from Monocular Video","created":"2026-03-17","cited_by_count":4,"area":null},{"id":"2211.06027","title":"Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attention","created":"2022-11-11","cited_by_count":3,"area":null},{"id":"2308.10441","title":"X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events","created":"2023-08-21","cited_by_count":3,"area":null},{"id":"2404.06044","title":"Object Dynamics Modeling with Hierarchical Point Cloud-based Representations","created":"2024-04-09","cited_by_count":3,"area":null},{"id":"2405.02041","title":"Stabilizing Backpropagation Through Time to Learn Complex Physics","created":"2024-05-03","cited_by_count":3,"area":null},{"id":"2501.18291","title":"CueTip: An Interactive and Explainable Physics-aware Pool Assistant","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2510.04978","title":"Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI","created":"2025-10-06","cited_by_count":3,"area":"wm"},{"id":"2601.09658","title":"Image2Garment: Simulation-ready Garment Generation from a Single Image","created":"2026-01-14","cited_by_count":3,"area":null},{"id":"2605.20576","title":"$\\Delta$ynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos","created":"2026-05-20","cited_by_count":3,"area":null},{"id":"2107.11676","title":"The Impact of Negative Sampling on Contrastive Structured World Models","created":"2021-07-24","cited_by_count":2,"area":"wm"},{"id":"2202.10996","title":"Learning Dynamics and Structure of Complex Systems Using Graph Neural Networks","created":"2022-02-22","cited_by_count":2,"area":null},{"id":"2305.07648","title":"A Critical View of Vision-Based Long-Term Dynamics Prediction Under Environment Misalignment","created":"2023-05-12","cited_by_count":2,"area":null},{"id":"2310.04617","title":"SlotGNN: Unsupervised Discovery of Multi-Object Representations and Visual Dynamics","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2410.11617","title":"M$^{2}$M: Learning controllable Multi of experts and multi-scale operators are the Partial Differential Equations need","created":"2024-10-01","cited_by_count":2,"area":null},{"id":"2411.17438","title":"Object-centric proto-symbolic behavioural reasoning from pixels","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2411.17511","title":"Training Hamiltonian neural networks without backpropagation","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2506.06558","title":"Rapid training of Hamiltonian graph networks using random features","created":"2025-06-06","cited_by_count":2,"area":null},{"id":"2106.04776","title":"Uncovering Closed-form Governing Equations of Nonlinear Dynamics from Videos","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2111.05514","title":"Discovering Latent Representations of Relations for Interacting Systems","created":"2021-11-10","cited_by_count":1,"area":null},{"id":"2202.04109","title":"Learning Similarity Metrics for Volumetric Simulations with Multiscale CNNs","created":"2022-02-08","cited_by_count":1,"area":null},{"id":"2202.09006","title":"KINet: Unsupervised Forward Models for Robotic Pushing Manipulation","created":"2022-02-18","cited_by_count":1,"area":null},{"id":"2311.18788","title":"Automated interpretation of congenital heart disease from multi-view echocardiograms","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2403.10079","title":"Learning Physical Dynamics for Object-centric Visual Prediction","created":"2024-03-15","cited_by_count":1,"area":null},{"id":"2406.18220","title":"Guiding Video Prediction with Explicit Procedural Knowledge","created":"2024-06-26","cited_by_count":1,"area":null},{"id":"2603.17993","title":"GMT: Goal-Conditioned Multimodal Transformer for 6-DOF Object Trajectory Synthesis in 3D Scenes","created":"2026-03-18","cited_by_count":1,"area":"lr"},{"id":"2606.00115","title":"Physics from Video: Identifiability of Time-Invariant Second-Order ODEs under Minimal Trajectory Conditions","created":"2026-05-27","cited_by_count":1,"area":"wm"},{"id":"2104.01980","title":"Probabilistic Programming Bots in Intuitive Physics Game Play","created":"2021-04-05","cited_by_count":0,"area":null},{"id":"2109.03391","title":"Visual Sensation and Perception Computational Models for Deep Learning: State of the art, Challenges and Prospects","created":"2021-09-08","cited_by_count":0,"area":null},{"id":"2406.04575","title":"Optimization of geological carbon storage operations with multimodal latent dynamic model and deep reinforcement learning","created":"2024-06-07","cited_by_count":0,"area":"deeprl"},{"id":"2407.09537","title":"ViPro: Enabling and Controlling Video Prediction for Complex Dynamical Scenarios using Procedural Knowledge","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2408.07624","title":"Battery GraphNets : Relational Learning for Lithium-ion Batteries(LiBs) Life Estimation","created":"2024-08-14","cited_by_count":0,"area":null},{"id":"2410.18539","title":"Interpretable Representation Learning from Videos using Nonlinear Priors","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2606.26916","title":"PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation","created":"2026-06-25","cited_by_count":0,"area":"rag"},{"id":"2608.20009","title":"ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory Forecasting","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.22750","title":"MOSH-WM: Mask-Grounded Soft-Hamiltonian Dynamics for Object-Centric World Models","created":"2026-08-24","cited_by_count":0,"area":"wm"},{"id":"2609.36985","title":"Abductive World Modeling via Causal Representation Learning","created":"2026-09-29","cited_by_count":0,"area":"wm"},{"id":"2610.15722","title":"PhySimCode: A Benchmark and Evaluation Method for Physics Video to Code Generation","created":"2026-10-11","cited_by_count":0,"area":"mllm"}],"next_cursor":null}