{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307},{"id":"1908.08593","title":"Revealing the Dark Secrets of BERT","created":"2019-08-21","cited_by_count":301},{"id":"1911.03584","title":"On the Relationship between Self-Attention and Convolutional Layers","created":"2019-11-08","cited_by_count":300},{"id":"1906.05714","title":"A Multiscale Visualization of Attention in the Transformer Model","created":"2019-06-12","cited_by_count":292},{"id":"1906.04284","title":"Analyzing the Structure of Attention in a Transformer Language Model","created":"2019-06-07","cited_by_count":243},{"id":"1906.02715","title":"Visualizing and Measuring the Geometry of BERT","created":"2019-06-06","cited_by_count":216},{"id":"2012.14214","title":"TransPose: Keypoint Localization via Transformer","created":"2020-12-28","cited_by_count":126},{"id":"2008.05122","title":"The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models","created":"2020-08-12","cited_by_count":125},{"id":"1906.01698","title":"Open Sesame: Getting Inside BERT's Linguistic Knowledge","created":"2019-06-04","cited_by_count":120},{"id":"1801.06889","title":"Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers","created":"2018-01-21","cited_by_count":117},{"id":"2005.04511","title":"Finding Universal Grammatical Relations in Multilingual BERT","created":"2020-05-09","cited_by_count":110},{"id":"2005.02324","title":"Neural CRF Model for Sentence Alignment in Text Simplification","created":"2020-05-05","cited_by_count":106},{"id":"1803.07416","title":"Tensor2Tensor for Neural Machine Translation","created":"2018-03-16","cited_by_count":85},{"id":"2212.06727","title":"What do Vision Transformers Learn? A Visual Exploration","created":"2022-12-13","cited_by_count":76},{"id":"1904.02323","title":"Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations","created":"2019-04-04","cited_by_count":72},{"id":"1804.09299","title":"Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models","created":"2018-04-25","cited_by_count":69},{"id":"2203.17247","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","created":"2022-03-30","cited_by_count":53},{"id":"2009.07053","title":"Attention Flows: Analyzing and Comparing Attention Mechanisms in Language Models","created":"2020-09-03","cited_by_count":49},{"id":"1611.05469","title":"Embedding Projector: Interactive Visualization and Interpretation of Embeddings","created":"2016-11-16","cited_by_count":44},{"id":"1912.04853","title":"Embedding Comparator: Visualizing Differences in Global Structure and Local Neighborhoods via Small Multiples","created":"2019-12-10","cited_by_count":38},{"id":"1910.05276","title":"exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models","created":"2019-10-11","cited_by_count":33},{"id":"1802.00400","title":"A Comparison of Word Embeddings for the Biomedical Natural Language Processing","created":"2018-02-01","cited_by_count":29},{"id":"2103.14625","title":"Dodrio: Exploring Transformer Models with Interactive Visualization","created":"2021-03-26","cited_by_count":28},{"id":"2203.05922","title":"Visualizing and Understanding Patch Interactions in Vision Transformer","created":"2022-03-11","cited_by_count":26},{"id":"2010.01869","title":"Linguistic Profiling of a Neural Language Model","created":"2020-10-05","cited_by_count":23},{"id":"1909.09595","title":"SANVis: Visual Analytics for Understanding Self-Attention Networks","created":"2019-09-13","cited_by_count":21},{"id":"2104.00926","title":"VisQA: X-raying Vision and Language Reasoning in Transformers","created":"2021-04-02","cited_by_count":19},{"id":"1808.09074","title":"EmbeddingVis: A Visual Analytics Approach to Comparative Network Embedding Inspection","created":"2018-08-28","cited_by_count":18},{"id":"2202.02641","title":"Emblaze: Illuminating Machine Learning Representations through Interactive Comparison of Embedding Spaces","created":"2022-02-05","cited_by_count":16},{"id":"2303.01542","title":"Self-attention in Vision Transformers Performs Perceptual Grouping, Not Attention","created":"2023-03-02","cited_by_count":16},{"id":"2208.08176","title":"Visual Comparison of Language Model Adaptation","created":"2022-08-17","cited_by_count":14}],"next_cursor":null}