{"total":143,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057,"area":null},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540,"area":null},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381,"area":null},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185,"area":null},{"id":"2110.14503","title":"Simple data balancing achieves competitive worst-group-accuracy","created":"2021-10-27","cited_by_count":178,"area":null},{"id":"2110.11328","title":"A Fine-Grained Analysis on Distribution Shift","created":"2021-10-21","cited_by_count":171,"area":null},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145,"area":null},{"id":"2101.06046","title":"Counterfactual Generative Networks","created":"2021-01-15","cited_by_count":111,"area":null},{"id":"2102.10717","title":"Abstraction and Analogy-Making in Artificial Intelligence","created":"2021-02-22","cited_by_count":103,"area":null},{"id":"2105.14944","title":"The effectiveness of feature attribution methods and its correlation with automatic evaluation scores","created":"2021-05-31","cited_by_count":88,"area":null},{"id":"2106.03721","title":"OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization","created":"2021-06-07","cited_by_count":86,"area":null},{"id":"2109.05184","title":"MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets","created":"2021-09-11","cited_by_count":86,"area":null},{"id":"2204.08040","title":"NICO++: Towards Better Benchmarking for Domain Generalization","created":"2022-04-17","cited_by_count":86,"area":null},{"id":"2202.08360","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","created":"2022-02-16","cited_by_count":80,"area":null},{"id":"2104.03149","title":"Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering","created":"2021-04-07","cited_by_count":71,"area":null},{"id":"2106.04972","title":"Understanding Softmax Confidence and Uncertainty","created":"2021-06-09","cited_by_count":63,"area":null},{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2210.03895","title":"ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints","created":"2022-10-08","cited_by_count":48,"area":null},{"id":"2111.14341","title":"OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images","created":"2021-11-29","cited_by_count":46,"area":null},{"id":"2211.01866","title":"ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations","created":"2022-11-03","cited_by_count":44,"area":null},{"id":"2208.00780","title":"Visual correspondence-based explanations improve AI robustness and human-AI team accuracy","created":"2022-07-26","cited_by_count":39,"area":null},{"id":"2302.07865","title":"Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation","created":"2023-02-15","cited_by_count":35,"area":null},{"id":"2304.05538","title":"ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification","created":"2023-04-11","cited_by_count":33,"area":null},{"id":"2106.03805","title":"3DB: A Framework for Debugging Computer Vision Models","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2308.03977","title":"PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning","created":"2023-08-08","cited_by_count":31,"area":null},{"id":"2508.06426","title":"Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation","created":"2025-08-08","cited_by_count":31,"area":"vla"},{"id":"2102.10867","title":"Linear unit-tests for invariance discovery","created":"2021-02-22","cited_by_count":27,"area":null},{"id":"2106.05121","title":"Grounding inductive biases in natural images:invariance stems from variations in data","created":"2021-06-09","cited_by_count":27,"area":null},{"id":"2206.00515","title":"Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detection","created":"2022-06-01","cited_by_count":26,"area":null},{"id":"2209.14262","title":"A Survey on Physical Adversarial Attack in Computer Vision","created":"2022-09-28","cited_by_count":25,"area":null},{"id":"2109.02765","title":"Robustness and Generalization via Generative Adversarial Training","created":"2021-09-06","cited_by_count":20,"area":null},{"id":"2110.13939","title":"CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generation","created":"2021-10-26","cited_by_count":20,"area":null},{"id":"2209.07592","title":"Explicit Tradeoffs between Adversarial and Natural Distributional Robustness","created":"2022-09-15","cited_by_count":20,"area":null},{"id":"2406.17720","title":"BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity","created":"2024-06-25","cited_by_count":20,"area":null},{"id":"2307.10235","title":"Towards Viewpoint-Invariant Visual Recognition via Adversarial Training","created":"2023-07-16","cited_by_count":19,"area":null},{"id":"2106.10606","title":"Attack to Fool and Explain Deep Networks","created":"2021-06-20","cited_by_count":17,"area":null},{"id":"2208.12880","title":"Neuromorphic Visual Scene Understanding with Resonator Networks","created":"2022-08-26","cited_by_count":17,"area":null},{"id":"2212.06254","title":"You Only Need a Good Embeddings Extractor to Fix Spurious Correlations","created":"2022-12-12","cited_by_count":17,"area":null},{"id":"2303.15443","title":"GeoNet: Benchmarking Unsupervised Adaptation across Geographies","created":"2023-03-27","cited_by_count":17,"area":null},{"id":"2109.06429","title":"Robust Inverse Framework using Knowledge-guided Self-Supervised Learning: An application to Hydrology","created":"2021-09-14","cited_by_count":15,"area":null},{"id":"2110.14213","title":"Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose","created":"2021-10-27","cited_by_count":15,"area":null},{"id":"2203.11096","title":"CLIP meets GamePhysics: Towards bug identification in gameplay videos using zero-shot transfer learning","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2210.13604","title":"The Robustness Limits of SoTA Vision Models to Natural Variation","created":"2022-10-24","cited_by_count":15,"area":null},{"id":"2102.05623","title":"Addressing the Topological Defects of Disentanglement via Distributed Operators","created":"2021-02-10","cited_by_count":14,"area":null},{"id":"2207.08034","title":"Progress and limitations of deep networks to recognize objects in unusual poses","created":"2022-07-16","cited_by_count":13,"area":null},{"id":"2212.02648","title":"Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases","created":"2022-12-05","cited_by_count":13,"area":null},{"id":"2105.02468","title":"Relative stability toward diffeomorphisms indicates performance in deep nets","created":"2021-05-06","cited_by_count":12,"area":null},{"id":"2108.00107","title":"Comparing object recognition in humans and deep convolutional neural networks -- An eye tracking study","created":"2021-07-30","cited_by_count":12,"area":null},{"id":"2304.10266","title":"OOD-CV-v2: An extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images","created":"2023-04-17","cited_by_count":12,"area":null},{"id":"2109.14501","title":"Towards a theory of out-of-distribution learning","created":"2021-09-29","cited_by_count":11,"area":null},{"id":"2110.04545","title":"Towards Data-Free Domain Generalization","created":"2021-10-09","cited_by_count":11,"area":null},{"id":"2106.04569","title":"Simulated Adversarial Testing of Face Recognition Models","created":"2021-06-08","cited_by_count":10,"area":null},{"id":"2305.17023","title":"Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?","created":"2023-05-26","cited_by_count":10,"area":null},{"id":"2412.11521","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","created":"2024-12-16","cited_by_count":10,"area":null},{"id":"2205.13042","title":"How explainable are adversarially-robust CNNs?","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2404.12139","title":"Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models","created":"2024-04-18","cited_by_count":9,"area":"mllm"},{"id":"2405.20439","title":"Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2103.12719","title":"Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations","created":"2021-03-23","cited_by_count":8,"area":null},{"id":"2212.04401","title":"A Rubric for Human-like Agents and NeuroAI","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"2107.09546","title":"Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions","created":"2021-07-20","cited_by_count":7,"area":null},{"id":"2307.11528","title":"Improving Viewpoint Robustness for Visual Recognition via Adversarial Training","created":"2023-07-21","cited_by_count":7,"area":null},{"id":"2402.03973","title":"A comparison between humans and AI at recognizing objects in unusual poses","created":"2024-02-06","cited_by_count":7,"area":null},{"id":"2404.10727","title":"How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model","created":"2024-04-16","cited_by_count":7,"area":null},{"id":"2410.04740","title":"Evaluating the Generalization Ability of Spatiotemporal Model in Urban Scenario","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2201.07372","title":"Prospective Learning: Principled Extrapolation to the Future","created":"2022-01-19","cited_by_count":6,"area":null},{"id":"2206.13034","title":"Monitoring Shortcut Learning using Mutual Information","created":"2022-06-27","cited_by_count":6,"area":null},{"id":"2208.12259","title":"Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2211.16499","title":"Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing","created":"2022-11-29","cited_by_count":6,"area":null},{"id":"2308.11300","title":"Approaching human 3D shape perception with neurally mappable models","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2103.07640","title":"Generating Unrestricted Adversarial Examples via Three Parameters","created":"2021-03-13","cited_by_count":5,"area":null},{"id":"2201.12440","title":"Certifying Model Accuracy under Distribution Shifts","created":"2022-01-28","cited_by_count":5,"area":null},{"id":"2210.01506","title":"How deep convolutional neural networks lose spatial information with training","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2302.04246","title":"Shortcut Detection with Variational Autoencoders","created":"2023-02-08","cited_by_count":5,"area":null},{"id":"2308.14925","title":"Patient-specific, mechanistic models of tumor growth incorporating artificial intelligence and big data","created":"2023-08-28","cited_by_count":5,"area":null},{"id":"2403.04701","title":"ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes","created":"2024-03-07","cited_by_count":5,"area":null},{"id":"2408.03303","title":"Understanding How Blind Users Handle Object Recognition Errors: Strategies and Challenges","created":"2024-08-06","cited_by_count":5,"area":null},{"id":"2412.03002","title":"AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?","created":"2024-12-04","cited_by_count":5,"area":"mllm"},{"id":"2412.19920","title":"Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models","created":"2024-12-27","cited_by_count":5,"area":null},{"id":"2210.13356","title":"Robust Self-Supervised Learning with Lie Groups","created":"2022-10-24","cited_by_count":4,"area":null},{"id":"2305.07888","title":"Consistency Regularization for Domain Generalization with Logit Attribution Matching","created":"2023-05-13","cited_by_count":4,"area":null},{"id":"2507.11690","title":"The Impact of Coreset Selection on Spurious Correlations and Group Robustness","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2510.21332","title":"Weak-to-Strong Generalization under Distribution Shifts","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2104.05031","title":"Deformable Capsules for Object Detection","created":"2021-04-11","cited_by_count":3,"area":null},{"id":"2106.16198","title":"In-distribution adversarial attacks on object recognition models using gradient-free search","created":"2021-06-30","cited_by_count":3,"area":null},{"id":"2203.15529","title":"Treatment Learning Causal Transformer for Noisy Image Classification","created":"2022-03-29","cited_by_count":3,"area":null},{"id":"2205.13094","title":"Undersampling is a Minimax Optimal Robustness Intervention in Nonparametric Classification","created":"2022-05-26","cited_by_count":3,"area":null},{"id":"2210.05667","title":"Human Body Measurement Estimation with Adversarial Augmentation","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2301.06975","title":"Vision Based Machine Learning Algorithms for Out-of-Distribution Generalisation","created":"2023-01-17","cited_by_count":3,"area":null},{"id":"2302.00775","title":"Model Monitoring and Robustness of In-Use Machine Learning Models: Quantifying Data Distribution Shifts Using Population Stability Index","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2307.06825","title":"A Causal Framework to Unify Common Domain Generalization Approaches","created":"2023-07-13","cited_by_count":3,"area":null},{"id":"2307.08551","title":"On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization","created":"2023-07-17","cited_by_count":3,"area":null},{"id":"2404.08285","title":"A Survey of Neural Network Robustness Assessment in Image Recognition","created":"2024-04-12","cited_by_count":3,"area":null},{"id":"2410.14315","title":"Optimizing importance weighting in the presence of sub-population shifts","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2411.09749","title":"RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering","created":"2024-11-14","cited_by_count":3,"area":null},{"id":"2111.00131","title":"Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations","created":"2021-10-30","cited_by_count":2,"area":null},{"id":"2203.05006","title":"Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization","created":"2022-03-09","cited_by_count":2,"area":null},{"id":"2207.05796","title":"Estimating Test Performance for AI Medical Devices under Distribution Shift with Conformal Prediction","created":"2022-07-12","cited_by_count":2,"area":null},{"id":"2211.09782","title":"Assessing Neural Network Robustness via Adversarial Pivotal Tuning","created":"2022-11-17","cited_by_count":2,"area":null}],"next_cursor":"100"}