{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"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":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166},{"id":"2107.10098","title":"Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA","created":"2021-07-21","cited_by_count":160},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","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":"1901.07017","title":"Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs","created":"2019-01-21","cited_by_count":117},{"id":"2104.09958","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","created":"2021-04-20","cited_by_count":109},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93},{"id":"2310.09336","title":"Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task","created":"2023-10-13","cited_by_count":93},{"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":"2307.05596","title":"Compositional Generalization from First Principles","created":"2023-07-10","cited_by_count":64},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60},{"id":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51},{"id":"2310.06907","title":"Self-supervised Object-Centric Learning for Videos","created":"2023-10-10","cited_by_count":49},{"id":"2312.00648","title":"SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers","created":"2023-12-01","cited_by_count":49},{"id":"2207.00787","title":"Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation","created":"2022-07-02","cited_by_count":46},{"id":"2305.14229","title":"Provably Learning Object-Centric Representations","created":"2023-05-23","cited_by_count":45},{"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":"2408.11537","title":"A Survey of Embodied Learning for Object-Centric Robotic Manipulation","created":"2024-08-21","cited_by_count":35},{"id":"2406.09196","title":"Adaptive Slot Attention: Object Discovery with Dynamic Slot Number","created":"2024-06-13","cited_by_count":34},{"id":"2401.05735","title":"Object-Centric Diffusion for Efficient Video Editing","created":"2024-01-11","cited_by_count":31},{"id":"2412.14295","title":"Temporally Consistent Object-Centric Learning by Contrasting Slots","created":"2024-12-18","cited_by_count":31},{"id":"2306.00600","title":"Rotating Features for Object Discovery","created":"2023-06-01","cited_by_count":29},{"id":"2207.14012","title":"Video Mask Transfiner for High-Quality Video Instance Segmentation","created":"2022-07-28","cited_by_count":28},{"id":"2404.01220","title":"Entity-Centric Reinforcement Learning for Object Manipulation from Pixels","created":"2024-04-01","cited_by_count":27},{"id":"2303.15555","title":"Object Discovery from Motion-Guided Tokens","created":"2023-03-27","cited_by_count":25},{"id":"2310.19054","title":"Object-centric architectures enable efficient causal representation learning","created":"2023-10-29","cited_by_count":21},{"id":"2408.09162","title":"Zero-Shot Object-Centric Representation Learning","created":"2024-08-17","cited_by_count":19},{"id":"2307.09437","title":"Grounded Object Centric Learning","created":"2023-07-18","cited_by_count":17},{"id":"2302.08023","title":"Object-centric Learning with Cyclic Walks between Parts and Whole","created":"2023-02-16","cited_by_count":16},{"id":"2502.07600","title":"PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning","created":"2025-02-11","cited_by_count":14},{"id":"2502.20263","title":"Vector-Quantized Vision Foundation Models for Object-Centric Learning","created":"2025-02-27","cited_by_count":11},{"id":"2504.07092","title":"Are We Done with Object-Centric Learning?","created":"2025-04-09","cited_by_count":11},{"id":"2402.01203","title":"Neural Language of Thought Models","created":"2024-02-02","cited_by_count":9},{"id":"2406.07141","title":"Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention","created":"2024-06-11","cited_by_count":9},{"id":"2306.02204","title":"Cycle Consistency Driven Object Discovery","created":"2023-06-03","cited_by_count":7}],"next_cursor":null}