{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"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":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2110.02711","title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","created":"2021-10-06","cited_by_count":642},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2310.15110","title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","created":"2023-10-23","cited_by_count":521},{"id":"2312.13286","title":"Generative Multimodal Models are In-Context Learners","created":"2023-12-20","cited_by_count":446},{"id":"1509.06321","title":"Evaluating the visualization of what a Deep Neural Network has learned","created":"2015-09-21","cited_by_count":419},{"id":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320},{"id":"1910.08485","title":"Understanding Deep Networks via Extremal Perturbations and Smooth Masks","created":"2019-10-18","cited_by_count":259},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250},{"id":"1605.05395","title":"Learning Deep Representations of Fine-grained Visual Descriptions","created":"2016-05-17","cited_by_count":182},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119},{"id":"2010.00977","title":"Group Equivariant Stand-Alone Self-Attention For Vision","created":"2020-10-02","cited_by_count":63},{"id":"2304.03916","title":"Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning","created":"2023-04-08","cited_by_count":47},{"id":"2204.08945","title":"Missingness Bias in Model Debugging","created":"2022-04-19","cited_by_count":38},{"id":"2312.17174","title":"Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution","created":"2023-12-28","cited_by_count":34},{"id":"2411.04097","title":"RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models","created":"2024-11-06","cited_by_count":20},{"id":"2503.11832","title":"Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning","created":"2025-03-14","cited_by_count":16},{"id":"2506.18322","title":"Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?","created":"2025-06-23","cited_by_count":14},{"id":"2407.08947","title":"Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort","created":"2024-07-12","cited_by_count":7},{"id":"2506.23663","title":"On the Domain Robustness of Contrastive Vision-Language Models","created":"2025-06-30","cited_by_count":1}],"next_cursor":null}