{"list":"other","total":86,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"1912.09713","title":"Measuring Compositional Generalization: A Comprehensive Method on Realistic Data","created":"2019-12-20","cited_by_count":284},{"id":"1910.11215","title":"RoboNet: Large-Scale Multi-Robot Learning","created":"2019-10-24","cited_by_count":270},{"id":"2010.05465","title":"COGS: A Compositional Generalization Challenge Based on Semantic Interpretation","created":"2020-10-12","cited_by_count":263},{"id":"2209.00647","title":"Visual Prompting via Image Inpainting","created":"2022-09-01","cited_by_count":250},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"1711.00848","title":"Variational Inference of Disentangled Latent Concepts from Unlabeled Observations","created":"2017-11-02","cited_by_count":241},{"id":"2012.05208","title":"On the Binding Problem in Artificial Neural Networks","created":"2020-12-09","cited_by_count":233},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"1903.02741","title":"RAVEN: A Dataset for Relational and Analogical Visual rEasoNing","created":"2019-03-07","cited_by_count":226},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"1603.08575","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","created":"2016-03-28","cited_by_count":209},{"id":"2001.02407","title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","created":"2020-01-08","cited_by_count":190},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181},{"id":"1807.04225","title":"Measuring abstract reasoning in neural networks","created":"2018-07-11","cited_by_count":166},{"id":"2106.08261","title":"Physion: Evaluating Physical Prediction from Vision in Humans and Machines","created":"2021-06-15","cited_by_count":153},{"id":"1707.08475","title":"DARLA: Improving Zero-Shot Transfer in Reinforcement Learning","created":"2017-07-26","cited_by_count":149},{"id":"2010.12725","title":"Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?","created":"2020-10-24","cited_by_count":147},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147},{"id":"2205.14065","title":"Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos","created":"2022-05-27","cited_by_count":139},{"id":"2212.06800","title":"Diverse Demonstrations Improve In-context Compositional Generalization","created":"2022-12-13","cited_by_count":139},{"id":"1806.09029","title":"Improving Text-to-SQL Evaluation Methodology","created":"2018-06-23","cited_by_count":135},{"id":"1703.07469","title":"RobustFill: Neural Program Learning under Noisy I/O","created":"2017-03-21","cited_by_count":126},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120},{"id":"1910.02384","title":"SCALOR: Generative World Models with Scalable Object Representations","created":"2019-10-06","cited_by_count":108},{"id":"2003.05161","title":"A Benchmark for Systematic Generalization in Grounded Language Understanding","created":"2020-03-11","cited_by_count":108},{"id":"1905.12506","title":"Are Disentangled Representations Helpful for Abstract Visual Reasoning?","created":"2019-05-29","cited_by_count":100},{"id":"2006.07886","title":"On Disentangled Representations Learned From Correlated Data","created":"2020-06-14","cited_by_count":94},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93},{"id":"1811.03259","title":"Bias and Generalization in Deep Generative Models: An Empirical Study","created":"2018-11-08","cited_by_count":83},{"id":"1909.12000","title":"CoPhy: Counterfactual Learning of Physical Dynamics","created":"2019-09-26","cited_by_count":81},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81},{"id":"1803.07616","title":"IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning","created":"2018-03-20","cited_by_count":73},{"id":"2002.06838","title":"Stratified Rule-Aware Network for Abstract Visual Reasoning","created":"2020-02-17","cited_by_count":72},{"id":"1606.06724","title":"Tagger: Deep Unsupervised Perceptual Grouping","created":"2016-06-21","cited_by_count":69},{"id":"1912.05783","title":"CLOSURE: Assessing Systematic Generalization of CLEVR Models","created":"2019-12-12","cited_by_count":63},{"id":"2010.00763","title":"Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning","created":"2020-10-02","cited_by_count":63},{"id":"1905.09275","title":"COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration","created":"2019-05-22","cited_by_count":57},{"id":"1804.08018","title":"ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking","created":"2018-04-21","cited_by_count":55},{"id":"1902.00120","title":"Learning to Make Analogies by Contrasting Abstract Relational Structure","created":"2019-01-31","cited_by_count":53},{"id":"2107.00848","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","created":"2021-07-02","cited_by_count":53},{"id":"2305.04835","title":"How Do In-Context Examples Affect Compositional Generalization?","created":"2023-05-08","cited_by_count":51},{"id":"2302.04419","title":"An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning","created":"2023-02-09","cited_by_count":49},{"id":"2009.09405","title":"Scale-Localized Abstract Reasoning","created":"2020-09-20","cited_by_count":45},{"id":"2103.14230","title":"Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution","created":"2021-03-26","cited_by_count":43},{"id":"2206.05379","title":"A Benchmark for Compositional Visual Reasoning","created":"2022-06-11","cited_by_count":43},{"id":"2210.00482","title":"Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language","created":"2022-10-02","cited_by_count":42},{"id":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","cited_by_count":37},{"id":"2007.05059","title":"Learning Representations that Support Extrapolation","created":"2020-07-09","cited_by_count":36},{"id":"2205.13803","title":"Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions","created":"2022-05-27","cited_by_count":34},{"id":"2209.06970","title":"Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models","created":"2022-09-14","cited_by_count":27},{"id":"2109.10613","title":"COVR: A test-bed for Visually Grounded Compositional Generalization with real images","created":"2021-09-22","cited_by_count":25},{"id":"1907.12271","title":"V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices","created":"2019-07-29","cited_by_count":24},{"id":"2303.13716","title":"ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation","created":"2023-03-24","cited_by_count":24},{"id":"2010.02855","title":"CURI: A Benchmark for Productive Concept Learning Under Uncertainty","created":"2020-10-06","cited_by_count":21},{"id":"2109.08994","title":"ReaSCAN: Compositional Reasoning in Language Grounding","created":"2021-09-18","cited_by_count":19},{"id":"2201.13388","title":"Compositional Multi-Object Reinforcement Learning with Linear Relation Networks","created":"2022-01-31","cited_by_count":19},{"id":"1301.4083","title":"Knowledge Matters: Importance of Prior Information for Optimization","created":"2013-01-17","cited_by_count":15},{"id":"2109.12243","title":"Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?","created":"2021-09-25","cited_by_count":15},{"id":"2011.00496","title":"Generating Correct Answers for Progressive Matrices Intelligence Tests","created":"2020-11-01","cited_by_count":12},{"id":"2107.05686","title":"The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents","created":"2021-07-12","cited_by_count":12},{"id":"2105.07065","title":"Visual analogy: Deep learning versus compositional models","created":"2021-05-14","cited_by_count":11},{"id":"2204.02283","title":"Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation","created":"2022-04-05","cited_by_count":11},{"id":"2306.00763","title":"Learning Disentangled Prompts for Compositional Image Synthesis","created":"2023-06-01","cited_by_count":8},{"id":"2204.03758","title":"Compositional Generalization and Decomposition in Neural Program Synthesis","created":"2022-04-07","cited_by_count":6},{"id":"2211.13051","title":"Powderworld: A Platform for Understanding Generalization via Rich Task Distributions","created":"2022-11-23","cited_by_count":6},{"id":"2303.01711","title":"NovPhy: A Testbed for Physical Reasoning in Open-world Environments","created":"2023-03-03","cited_by_count":2}],"next_cursor":null}