{"list":"other","total":86,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"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":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"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":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"2502.19645","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","created":"2025-02-27","cited_by_count":883},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"2410.07864","title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","created":"2024-10-10","cited_by_count":691},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2405.05941","title":"Evaluating Real-World Robot Manipulation Policies in Simulation","created":"2024-05-09","cited_by_count":495},{"id":"2503.06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","created":"2025-03-09","cited_by_count":405},{"id":"2407.08693","title":"Robotic Control via Embodied Chain-of-Thought Reasoning","created":"2024-07-11","cited_by_count":346},{"id":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"id":"2402.07865","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","created":"2024-02-12","cited_by_count":339},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288},{"id":"2311.07575","title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","created":"2023-11-13","cited_by_count":286},{"id":"1904.00760","title":"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet","created":"2019-03-20","cited_by_count":260},{"id":"2502.19417","title":"Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models","created":"2025-02-26","cited_by_count":221},{"id":"2412.04453","title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","created":"2024-12-05","cited_by_count":211},{"id":"2403.01823","title":"RT-H: Action Hierarchies Using Language","created":"2024-03-04","cited_by_count":210},{"id":"1811.02790","title":"RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation","created":"2018-11-07","cited_by_count":204},{"id":"2307.00595","title":"RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot","created":"2023-07-02","cited_by_count":183},{"id":"2302.11550","title":"Scaling Robot Learning with Semantically Imagined Experience","created":"2023-02-22","cited_by_count":177},{"id":"2412.13877","title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","created":"2024-12-18","cited_by_count":175},{"id":"2309.01918","title":"RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking","created":"2023-09-05","cited_by_count":169},{"id":"1707.08475","title":"DARLA: Improving Zero-Shot Transfer in Reinforcement Learning","created":"2017-07-26","cited_by_count":149},{"id":"2409.20537","title":"Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers","created":"2024-09-30","cited_by_count":148},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145},{"id":"1811.11553","title":"Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects","created":"2018-11-28","cited_by_count":143},{"id":"2410.24185","title":"DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning","created":"2024-10-31","cited_by_count":116},{"id":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114},{"id":"2408.11812","title":"Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation","created":"2024-08-21","cited_by_count":114},{"id":"2310.17994","title":"ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image","created":"2023-10-27","cited_by_count":111},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85},{"id":"2306.02437","title":"Data Quality in Imitation Learning","created":"2023-06-04","cited_by_count":75},{"id":"2305.17256","title":"Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning","created":"2023-05-26","cited_by_count":69},{"id":"2201.10766","title":"A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes","created":"2022-01-26","cited_by_count":56},{"id":"2503.03734","title":"OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction","created":"2025-03-05","cited_by_count":54},{"id":"2107.07746","title":"Rectifying the Shortcut Learning of Background for Few-Shot Learning","created":"2021-07-16","cited_by_count":51},{"id":"1812.06707","title":"Not Using the Car to See the Sidewalk: Quantifying and Controlling the Effects of Context in Classification and Segmentation","created":"2018-12-17","cited_by_count":49},{"id":"2408.14037","title":"Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning","created":"2024-08-26","cited_by_count":47},{"id":"2409.03403","title":"RoVi-Aug: Robot and Viewpoint Augmentation for Cross-Embodiment Robot Learning","created":"2024-09-05","cited_by_count":46},{"id":"2402.12715","title":"The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning","created":"2024-02-20","cited_by_count":41},{"id":"2403.05110","title":"Efficient Data Collection for Robotic Manipulation via Compositional Generalization","created":"2024-03-08","cited_by_count":37},{"id":"2502.08623","title":"Robot Data Curation with Mutual Information Estimators","created":"2025-02-12","cited_by_count":37},{"id":"2108.00049","title":"Object-aware Contrastive Learning for Debiased Scene Representation","created":"2021-07-30","cited_by_count":35},{"id":"2409.03685","title":"View-Invariant Policy Learning via Zero-Shot Novel View Synthesis","created":"2024-09-05","cited_by_count":35},{"id":"2307.07907","title":"Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation","created":"2023-07-15","cited_by_count":25},{"id":"2410.13343","title":"Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models","created":"2024-10-17","cited_by_count":25},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23},{"id":"2505.13888","title":"InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning","created":"2025-05-20","cited_by_count":21},{"id":"2409.00951","title":"Semantically Controllable Augmentations for Generalizable Robot Learning","created":"2024-09-02","cited_by_count":18},{"id":"2110.14118","title":"Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning","created":"2021-10-27","cited_by_count":17},{"id":"2311.01489","title":"Invariant Causal Imitation Learning for Generalizable Policies","created":"2023-11-02","cited_by_count":15},{"id":"2310.07932","title":"What Matters to You? Towards Visual Representation Alignment for Robot Learning","created":"2023-10-11","cited_by_count":14},{"id":"1605.05538","title":"Improving Weakly-Supervised Object Localization By Micro-Annotation","created":"2016-05-18","cited_by_count":11},{"id":"2502.02853","title":"Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation","created":"2025-02-05","cited_by_count":10},{"id":"2410.14371","title":"Interpretable end-to-end Neurosymbolic Reinforcement Learning agents","created":"2024-10-18","cited_by_count":4},{"id":"2507.22380","title":"Improving Generalization Ability of Robotic Imitation Learning by Resolving Causal Confusion in Observations","created":"2025-07-30","cited_by_count":4},{"id":"2402.05090","title":"Language-Based Augmentation to Address Shortcut Learning in Object Goal Navigation","created":"2024-02-07","cited_by_count":3},{"id":"2409.13607","title":"RECON: Reducing Causal Confusion with Human-Placed Markers","created":"2024-09-20","cited_by_count":3}],"next_cursor":null}