{"total":22,"rows":[{"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":"2205.01089","title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","created":"2022-05-02","cited_by_count":63,"area":null},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"area":null},{"id":"2401.01862","title":"A Vision Check-up for Language Models","created":"2024-01-03","cited_by_count":36,"area":null},{"id":"2311.09682","title":"MacGyver: Are Large Language Models Creative Problem Solvers?","created":"2023-11-16","cited_by_count":34,"area":null},{"id":"2205.05678","title":"RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation","created":"2022-05-11","cited_by_count":29,"area":null},{"id":"2303.17842","title":"Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning","created":"2023-03-31","cited_by_count":17,"area":null},{"id":"2310.17914","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","created":"2023-10-27","cited_by_count":16,"area":null},{"id":"2205.02835","title":"Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics","created":"2022-05-05","cited_by_count":14,"area":null},{"id":"2212.10029","title":"Do language models have coherent mental models of everyday things?","created":"2022-12-20","cited_by_count":13,"area":null},{"id":"2203.03282","title":"Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks","created":"2022-03-07","cited_by_count":11,"area":null},{"id":"2210.02075","title":"On the Learning Mechanisms in Physical Reasoning","created":"2022-10-05","cited_by_count":11,"area":null},{"id":"2205.02671","title":"What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learning","created":"2022-05-05","cited_by_count":10,"area":null},{"id":"2203.16168","title":"FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing","created":"2022-03-30","cited_by_count":9,"area":null},{"id":"2407.09686","title":"SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images","created":"2024-07-12","cited_by_count":5,"area":null},{"id":"2406.10885","title":"On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions","created":"2024-06-16","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":"2310.08929","title":"Leveraging Image Augmentation for Object Manipulation: Towards Interpretable Controllability in Object-Centric Learning","created":"2023-10-13","cited_by_count":2,"area":null},{"id":"2211.15566","title":"Neuro-Symbolic Spatio-Temporal Reasoning","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2308.02835","title":"Physics-Based Task Generation through Causal Sequence of Physical Interactions","created":"2023-08-05","cited_by_count":0,"area":null},{"id":"2411.02858","title":"OLAF: A Plug-and-Play Framework for Enhanced Multi-object Multi-part Scene Parsing","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2603.15997","title":"Visual Set Program Synthesizer","created":"2026-03-16","cited_by_count":0,"area":null}],"next_cursor":null}