{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"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":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"1502.05767","title":"Automatic differentiation in machine learning: a survey","created":"2015-02-20","cited_by_count":855},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1903.03894","title":"GNNExplainer: Generating Explanations for Graph Neural Networks","created":"2019-03-10","cited_by_count":737},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1910.01279","title":"Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks","created":"2019-10-03","cited_by_count":582},{"id":"2008.02217","title":"Hopfield Networks is All You Need","created":"2020-07-16","cited_by_count":475},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"2206.02647","title":"Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning","created":"2022-06-06","cited_by_count":359},{"id":"1806.08049","title":"On the Robustness of Interpretability Methods","created":"2018-06-21","cited_by_count":314},{"id":"2305.17100","title":"BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks","created":"2023-05-26","cited_by_count":201},{"id":"2306.00802","title":"Birth of a Transformer: A Memory Viewpoint","created":"2023-06-01","cited_by_count":161},{"id":"2306.11300","title":"RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing","created":"2023-06-20","cited_by_count":151},{"id":"2311.17179","title":"SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery","created":"2023-11-28","cited_by_count":151},{"id":"2209.15639","title":"F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models","created":"2022-09-30","cited_by_count":150},{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139},{"id":"2107.07436","title":"FastSHAP: Real-Time Shapley Value Estimation","created":"2021-07-15","cited_by_count":125},{"id":"1903.10992","title":"Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation","created":"2019-03-26","cited_by_count":115},{"id":"1805.02855","title":"Tile2Vec: Unsupervised representation learning for spatially distributed data","created":"2018-05-08","cited_by_count":110},{"id":"2401.06148","title":"Artificial Intelligence for Digital and Computational Pathology","created":"2023-12-13","cited_by_count":108},{"id":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98},{"id":"1804.02391","title":"Learn To Pay Attention","created":"2018-04-06","cited_by_count":83},{"id":"2212.11870","title":"Impossibility Theorems for Feature Attribution","created":"2022-12-22","cited_by_count":78},{"id":"2310.12941","title":"The Foundation Model Transparency Index","created":"2023-10-19","cited_by_count":66},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59},{"id":"2209.11222","title":"Concept Activation Regions: A Generalized Framework For Concept-Based Explanations","created":"2022-09-22","cited_by_count":57},{"id":"2307.12914","title":"Towards a Visual-Language Foundation Model for Computational Pathology","created":"2023-07-24","cited_by_count":52},{"id":"1902.04793","title":"SECTOR: A Neural Model for Coherent Topic Segmentation and Classification","created":"2019-02-13","cited_by_count":48},{"id":"2206.05282","title":"Learning to Estimate Shapley Values with Vision Transformers","created":"2022-06-10","cited_by_count":45},{"id":"2105.00108","title":"Explaining a Series of Models by Propagating Shapley Values","created":"2021-04-30","cited_by_count":37},{"id":"2204.11790","title":"Can Rationalization Improve Robustness?","created":"2022-04-25","cited_by_count":36},{"id":"2008.02766","title":"Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging","created":"2020-08-06","cited_by_count":32},{"id":"2307.10504","title":"Identifying Interpretable Subspaces in Image Representations","created":"2023-07-20","cited_by_count":32},{"id":"2111.05685","title":"Efficient Neural Network Training via Forward and Backward Propagation Sparsification","created":"2021-11-10","cited_by_count":30},{"id":"2002.08483","title":"Strength from Weakness: Fast Learning Using Weak Supervision","created":"2020-02-19","cited_by_count":18},{"id":"2311.09191","title":"Domain Aligned CLIP for Few-shot Classification","created":"2023-11-15","cited_by_count":16},{"id":"2212.06925","title":"On the Relationship Between Explanation and Prediction: A Causal View","created":"2022-12-13","cited_by_count":14},{"id":"1908.06037","title":"Needles in Haystacks: On Classifying Tiny Objects in Large Images","created":"2019-08-16","cited_by_count":13},{"id":"1805.01033","title":"Unsupervised Learning using Pretrained CNN and Associative Memory Bank","created":"2018-05-02","cited_by_count":12},{"id":"1910.13140","title":"Concept Saliency Maps to Visualize Relevant Features in Deep Generative Models","created":"2019-10-29","cited_by_count":11},{"id":"2104.12437","title":"Towards Rigorous Interpretations: a Formalisation of Feature Attribution","created":"2021-04-26","cited_by_count":11},{"id":"2312.06141","title":"Survey on Memory-Augmented Neural Networks: Cognitive Insights to AI Applications","created":"2023-12-11","cited_by_count":7},{"id":"2305.19998","title":"Efficient Shapley Values Estimation by Amortization for Text Classification","created":"2023-05-31","cited_by_count":4},{"id":"2303.07991","title":"Finding the Needle in a Haystack: Unsupervised Rationale Extraction from Long Text Classifiers","created":"2023-03-14","cited_by_count":1}],"next_cursor":null}