{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"1907.04809","title":"Variational Autoencoders and Nonlinear ICA: A Unifying Framework","created":"2019-07-10","cited_by_count":503},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2106.04619","title":"Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style","created":"2021-06-08","cited_by_count":312},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279},{"id":"2002.02886","title":"Weakly-Supervised Disentanglement Without Compromises","created":"2020-02-07","cited_by_count":239},{"id":"2102.08850","title":"Contrastive Learning Inverts the Data Generating Process","created":"2021-02-17","cited_by_count":221},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"2002.07017","title":"Learning Robust Representations via Multi-View Information Bottleneck","created":"2020-02-17","cited_by_count":191},{"id":"2107.10098","title":"Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA","created":"2021-07-21","cited_by_count":160},{"id":"2209.11924","title":"Interventional Causal Representation Learning","created":"2022-09-24","cited_by_count":142},{"id":"2203.16437","title":"Weakly supervised causal representation learning","created":"2022-03-30","cited_by_count":140},{"id":"2202.03169","title":"CITRIS: Causal Identifiability from Temporal Intervened Sequences","created":"2022-02-07","cited_by_count":133},{"id":"1707.06422","title":"Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions","created":"2017-07-20","cited_by_count":126},{"id":"2001.09691","title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","created":"2020-01-27","cited_by_count":115},{"id":"2002.11537","title":"ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA","created":"2020-02-26","cited_by_count":102},{"id":"1907.12743","title":"Temporal Attentive Alignment for Large-Scale Video Domain Adaptation","created":"2019-07-30","cited_by_count":100},{"id":"2306.02235","title":"Learning Linear Causal Representations from Interventions under General Nonlinear Mixing","created":"2023-06-04","cited_by_count":92},{"id":"2211.16467","title":"Linear Causal Disentanglement via Interventions","created":"2022-11-29","cited_by_count":84},{"id":"2109.03795","title":"Desiderata for Representation Learning: A Causal Perspective","created":"2021-09-08","cited_by_count":76},{"id":"2311.04056","title":"Multi-View Causal Representation Learning with Partial Observability","created":"2023-11-07","cited_by_count":74},{"id":"2505.04769","title":"Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges","created":"2025-05-07","cited_by_count":74},{"id":"2205.11402","title":"Causal Machine Learning for Healthcare and Precision Medicine","created":"2022-05-23","cited_by_count":68},{"id":"2206.01101","title":"Weakly Supervised Representation Learning with Sparse Perturbations","created":"2022-06-02","cited_by_count":65},{"id":"1904.09096","title":"Causal Discovery with General Non-Linear Relationships Using Non-Linear ICA","created":"2019-04-19","cited_by_count":58},{"id":"2305.17225","title":"Causal Component Analysis","created":"2023-05-26","cited_by_count":56},{"id":"2301.08230","title":"Score-based Causal Representation Learning with Interventions","created":"2023-01-19","cited_by_count":49},{"id":"2401.04890","title":"Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies","created":"2024-01-10","cited_by_count":41},{"id":"2306.09643","title":"BISCUIT: Causal Representation Learning from Binary Interactions","created":"2023-06-16","cited_by_count":38},{"id":"2403.08335","title":"A Sparsity Principle for Partially Observable Causal Representation Learning","created":"2024-03-13","cited_by_count":35},{"id":"2211.03553","title":"Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling","created":"2022-11-07","cited_by_count":34},{"id":"2402.06665","title":"The Essential Role of Causality in Foundation World Models for Embodied AI","created":"2024-02-06","cited_by_count":32},{"id":"2409.02772","title":"Unifying Causal Representation Learning with the Invariance Principle","created":"2024-09-04","cited_by_count":31},{"id":"2310.14935","title":"Causal machine learning for single-cell genomics","created":"2023-10-23","cited_by_count":23},{"id":"2301.05169","title":"Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning","created":"2023-01-12","cited_by_count":22},{"id":"2406.05937","title":"Linear Causal Representation Learning from Unknown Multi-node Interventions","created":"2024-06-09","cited_by_count":14},{"id":"2203.09380","title":"Identifiability of Sparse Causal Effects using Instrumental Variables","created":"2022-03-17","cited_by_count":9},{"id":"2405.20482","title":"Sparsity regularization via tree-structured environments for disentangled representations","created":"2024-05-30","cited_by_count":2}],"next_cursor":null}