{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"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":"2011.15091","title":"Inductive Biases for Deep Learning of Higher-Level Cognition","created":"2020-11-30","cited_by_count":275},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"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":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"1603.08575","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","created":"2016-03-28","cited_by_count":209},{"id":"2404.12377","title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","created":"2024-04-18","cited_by_count":195},{"id":"2001.02407","title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","created":"2020-01-08","cited_by_count":190},{"id":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"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":"1806.01794","title":"Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects","created":"2018-06-05","cited_by_count":128},{"id":"1708.03498","title":"Neural Expectation Maximization","created":"2017-08-11","cited_by_count":123},{"id":"1910.12827","title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":110},{"id":"2107.04589","title":"ViTGAN: Training GANs with Vision Transformers","created":"2021-07-09","cited_by_count":110},{"id":"1910.02384","title":"SCALOR: Generative World Models with Scalable Object Representations","created":"2019-10-06","cited_by_count":108},{"id":"1802.10353","title":"Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions","created":"2018-02-28","cited_by_count":100},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90},{"id":"2303.10834","title":"Object-Centric Slot Diffusion","created":"2023-03-20","cited_by_count":90},{"id":"2305.11281","title":"SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models","created":"2023-05-18","cited_by_count":85},{"id":"2306.04829","title":"Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities","created":"2023-06-07","cited_by_count":78},{"id":"2103.01937","title":"Neural Production Systems: Learning Rule-Governed Visual Dynamics","created":"2021-03-02","cited_by_count":75},{"id":"2012.08508","title":"Attention over learned object embeddings enables complex visual reasoning","created":"2020-12-15","cited_by_count":59},{"id":"2006.16225","title":"Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems","created":"2020-06-29","cited_by_count":48},{"id":"1911.09033","title":"Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking","created":"2019-11-20","cited_by_count":40},{"id":"2204.02075","title":"Complex-Valued Autoencoders for Object Discovery","created":"2022-04-05","cited_by_count":40},{"id":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","cited_by_count":37},{"id":"2105.08710","title":"Fast and Slow Learning of Recurrent Independent Mechanisms","created":"2021-05-18","cited_by_count":36},{"id":"2303.15555","title":"Object Discovery from Motion-Guided Tokens","created":"2023-03-27","cited_by_count":25},{"id":"2107.09240","title":"Generative Video Transformer: Can Objects be the Words?","created":"2021-07-20","cited_by_count":24},{"id":"2204.13661","title":"Toward Compositional Generalization in Object-Oriented World Modeling","created":"2022-04-28","cited_by_count":22},{"id":"2406.12272","title":"Slot State Space Models","created":"2024-06-18","cited_by_count":17},{"id":"2310.12690","title":"Neurosymbolic Grounding for Compositional World Models","created":"2023-10-19","cited_by_count":14},{"id":"2011.11201","title":"Modular Action Concept Grounding in Semantic Video Prediction","created":"2020-11-23","cited_by_count":12},{"id":"2402.01203","title":"Neural Language of Thought Models","created":"2024-02-02","cited_by_count":9},{"id":"2209.07453","title":"Replay and compositional computation","created":"2022-09-15","cited_by_count":8},{"id":"2404.15109","title":"Compete and Compose: Learning Independent Mechanisms for Modular World Models","created":"2024-04-23","cited_by_count":4},{"id":"2402.17077","title":"Parallelized Spatiotemporal Binding","created":"2024-02-26","cited_by_count":2}],"next_cursor":null}