{"total":55,"rows":[{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248,"area":"wm"},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213,"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":"2305.11281","title":"SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models","created":"2023-05-18","cited_by_count":85,"area":"diffusion"},{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2505.04769","title":"Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges","created":"2025-05-07","cited_by_count":74,"area":"mllm"},{"id":"2205.01089","title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","created":"2022-05-02","cited_by_count":63,"area":null},{"id":"2307.07696","title":"Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text","created":"2023-07-15","cited_by_count":59,"area":"lr"},{"id":"2306.15668","title":"Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties","created":"2023-06-27","cited_by_count":54,"area":null},{"id":"2407.07889","title":"AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulation","created":"2024-07-10","cited_by_count":54,"area":null},{"id":"2301.05226","title":"See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning","created":"2023-01-12","cited_by_count":51,"area":"lr"},{"id":"2210.06096","title":"Masked Motion Encoding for Self-Supervised Video Representation Learning","created":"2022-10-12","cited_by_count":39,"area":null},{"id":"2305.18035","title":"Physics-Informed Computer Vision: A Review and Perspectives","created":"2023-05-29","cited_by_count":28,"area":null},{"id":"2501.10928","title":"Generative Physical AI in Vision: A Survey","created":"2025-01-19","cited_by_count":24,"area":null},{"id":"2206.06417","title":"Image-based Treatment Effect Heterogeneity","created":"2022-06-13","cited_by_count":20,"area":null},{"id":"2406.00622","title":"Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering","created":"2024-06-02","cited_by_count":18,"area":"mllm"},{"id":"2307.11558","title":"Advancing Visual Grounding with Scene Knowledge: Benchmark and Method","created":"2023-07-21","cited_by_count":17,"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":"2304.03282","title":"Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention","created":"2023-04-06","cited_by_count":12,"area":null},{"id":"2210.02075","title":"On the Learning Mechanisms in Physical Reasoning","created":"2022-10-05","cited_by_count":11,"area":null},{"id":"2310.03635","title":"CLEVRER-Humans: Describing Physical and Causal Events the Human Way","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2402.16836","title":"PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Models","created":"2024-02-26","cited_by_count":11,"area":"mllm"},{"id":"2203.10488","title":"Inferring Articulated Rigid Body Dynamics from RGBD Video","created":"2022-03-20","cited_by_count":10,"area":null},{"id":"2412.08619","title":"Physics Context Builders: A Modular Framework for Physical Reasoning in Vision-Language Models","created":"2024-12-11","cited_by_count":10,"area":"lr"},{"id":"2505.06191","title":"Building Intelligent Agents with Neuro-Symbolic Concepts","created":"2025-05-09","cited_by_count":10,"area":null},{"id":"2304.03767","title":"Embodied Concept Learner: Self-supervised Learning of Concepts and Mapping through Instruction Following","created":"2023-04-07","cited_by_count":9,"area":null},{"id":"2301.12985","title":"Integrating Earth Observation Data into Causal Inference: Challenges and Opportunities","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2303.01869","title":"Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models","created":"2023-03-03","cited_by_count":8,"area":null},{"id":"2311.01620","title":"ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2312.10728","title":"Benchmarks for Physical Reasoning AI","created":"2023-12-17","cited_by_count":8,"area":null},{"id":"2403.15245","title":"Reasoning-Enhanced Object-Centric Learning for Videos","created":"2024-03-22","cited_by_count":7,"area":"lr"},{"id":"2512.00762","title":"Seeing the Wind from a Falling Leaf","created":"2025-11-30","cited_by_count":7,"area":null},{"id":"2409.14109","title":"Vision-Language Models Assisted Unsupervised Video Anomaly Detection","created":"2024-09-21","cited_by_count":6,"area":"mllm"},{"id":"2510.02311","title":"Inferring Dynamic Physical Properties from Video Foundation Models","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2403.15891","title":"Human Motion Prediction under Unexpected Perturbation","created":"2024-03-23","cited_by_count":5,"area":null},{"id":"2206.06410","title":"Estimating Causal Effects Under Image Confounding Bias with an Application to Poverty in Africa","created":"2022-06-13","cited_by_count":4,"area":null},{"id":"2312.17429","title":"Commonsense for Zero-Shot Natural Language Video Localization","created":"2023-12-29","cited_by_count":4,"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":"2408.12674","title":"One-shot Video Imitation via Parameterized Symbolic Abstraction Graphs","created":"2024-08-22","cited_by_count":3,"area":null},{"id":"2410.09379","title":"Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering","created":"2024-10-12","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":"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":"2205.02834","title":"Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction","created":"2022-05-05","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":"2503.11269","title":"Prof. Robot: Differentiable Robot Rendering Without Static and Self-Collisions","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2203.13762","title":"A World-Self Model Towards Understanding Intelligence","created":"2022-03-25","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":"2408.15201","title":"An Investigation on The Position Encoding in Vision-Based Dynamics Prediction","created":"2024-08-27","cited_by_count":1,"area":null},{"id":"2411.00402","title":"Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2503.23820","title":"When Counterfactual Reasoning Fails: Chaos and Real-World Complexity","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2405.20180","title":"Transformers and Slot Encoding for Sample Efficient Physical World Modelling","created":"2024-05-30","cited_by_count":0,"area":"wm"},{"id":"2506.10753","title":"Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering","created":"2025-06-12","cited_by_count":0,"area":"lr"},{"id":"2511.06761","title":"SRNN: Spatiotemporal Relational Neural Network for Intuitive Physics Understanding","created":"2025-11-10","cited_by_count":0,"area":null},{"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":"2608.23330","title":"IntentQA: Intent Question Answering in Videos by Cognitive Context Reasoning","created":"2026-08-24","cited_by_count":0,"area":"lr"}],"next_cursor":null}