{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"2004.07667","title":"Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection","created":"2020-04-16","cited_by_count":455},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"1904.01557","title":"Analysing Mathematical Reasoning Abilities of Neural Models","created":"2019-04-02","cited_by_count":335},{"id":"1908.08351","title":"Compositionality decomposed: how do neural networks generalise?","created":"2019-08-22","cited_by_count":265},{"id":"2010.05465","title":"COGS: A Compositional Generalization Challenge Based on Semantic Interpretation","created":"2020-10-12","cited_by_count":263},{"id":"1808.09031","title":"Targeted Syntactic Evaluation of Language Models","created":"2018-08-27","cited_by_count":242},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"id":"2006.14769","title":"Supermasks in Superposition","created":"2020-06-26","cited_by_count":227},{"id":"1905.01067","title":"Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask","created":"2019-05-03","cited_by_count":207},{"id":"2006.08381","title":"DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning","created":"2020-06-15","cited_by_count":161},{"id":"1908.08962","title":"Well-Read Students Learn Better: On the Importance of Pre-training Compact Models","created":"2019-08-23","cited_by_count":120},{"id":"1811.01157","title":"Identifying and Controlling Important Neurons in Neural Machine Translation","created":"2018-11-03","cited_by_count":111},{"id":"1912.04427","title":"Winning the Lottery with Continuous Sparsification","created":"2019-12-10","cited_by_count":100},{"id":"1906.05381","title":"Compositional generalization through meta sequence-to-sequence learning","created":"2019-06-12","cited_by_count":99},{"id":"2010.02066","title":"Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks","created":"2020-10-05","cited_by_count":98},{"id":"2002.01365","title":"Compositional Languages Emerge in a Neural Iterated Learning Model","created":"2020-02-04","cited_by_count":75},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75},{"id":"2003.05562","title":"Learning Compositional Rules via Neural Program Synthesis","created":"2020-03-12","cited_by_count":74},{"id":"1611.06694","title":"Training Sparse Neural Networks","created":"2016-11-21","cited_by_count":73},{"id":"2110.01518","title":"Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics","created":"2021-10-04","cited_by_count":67},{"id":"2104.03514","title":"Low-Complexity Probing via Finding Subnetworks","created":"2021-04-08","cited_by_count":64},{"id":"1608.03287","title":"Deep vs. shallow networks : An approximation theory perspective","created":"2016-08-10","cited_by_count":63},{"id":"2004.14992","title":"How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking","created":"2020-04-30","cited_by_count":63},{"id":"2108.05885","title":"The paradox of the compositionality of natural language: a neural machine translation case study","created":"2021-08-12","cited_by_count":59},{"id":"2112.07610","title":"Improving Compositional Generalization with Latent Structure and Data Augmentation","created":"2021-12-14","cited_by_count":46},{"id":"2205.01128","title":"Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems","created":"2022-05-02","cited_by_count":44},{"id":"2206.05379","title":"A Benchmark for Compositional Visual Reasoning","created":"2022-06-11","cited_by_count":43},{"id":"2010.03763","title":"Assessing Phrasal Representation and Composition in Transformers","created":"2020-10-08","cited_by_count":41},{"id":"2105.14002","title":"What if This Modified That? Syntactic Interventions via Counterfactual Embeddings","created":"2021-05-28","cited_by_count":39},{"id":"2210.03044","title":"Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?","created":"2022-10-06","cited_by_count":38},{"id":"2112.06837","title":"Sparse Interventions in Language Models with Differentiable Masking","created":"2021-12-13","cited_by_count":34},{"id":"2211.12312","title":"Interpreting Neural Networks through the Polytope Lens","created":"2022-11-22","cited_by_count":33},{"id":"1809.03992","title":"Assessing Composition in Sentence Vector Representations","created":"2018-09-11","cited_by_count":26},{"id":"2212.10769","title":"Uncontrolled Lexical Exposure Leads to Overestimation of Compositional Generalization in Pretrained Models","created":"2022-12-21","cited_by_count":26},{"id":"2208.10244","title":"Unit Testing for Concepts in Neural Networks","created":"2022-07-28","cited_by_count":23},{"id":"2105.01119","title":"Iterated learning for emergent systematicity in VQA","created":"2021-05-03","cited_by_count":21},{"id":"2112.02505","title":"Causal Distillation for Language Models","created":"2021-12-05","cited_by_count":19},{"id":"2110.08058","title":"Quantifying Local Specialization in Deep Neural Networks","created":"2021-10-13","cited_by_count":10},{"id":"1907.00262","title":"Dissecting Pruned Neural Networks","created":"2019-06-29","cited_by_count":8},{"id":"2111.05013","title":"Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks","created":"2021-11-09","cited_by_count":6}],"next_cursor":null}