{"list":"other","total":57,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"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":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2102.09844","title":"E(n) Equivariant Graph Neural Networks","created":"2021-02-19","cited_by_count":965},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"1501.01332","title":"Causal inference using invariant prediction: identification and confidence intervals","created":"2015-01-06","cited_by_count":536},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316},{"id":"2205.05055","title":"Data Distributional Properties Drive Emergent In-Context Learning in Transformers","created":"2022-04-22","cited_by_count":309},{"id":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"id":"1912.09713","title":"Measuring Compositional Generalization: A Comprehensive Method on Realistic Data","created":"2019-12-20","cited_by_count":284},{"id":"2011.15091","title":"Inductive Biases for Deep Learning of Higher-Level Cognition","created":"2020-11-30","cited_by_count":275},{"id":"2010.05465","title":"COGS: A Compositional Generalization Challenge Based on Semantic Interpretation","created":"2020-10-12","cited_by_count":263},{"id":"1904.09545","title":"Good-Enough Compositional Data Augmentation","created":"2019-04-21","cited_by_count":158},{"id":"1702.08389","title":"Equivariance Through Parameter-Sharing","created":"2017-02-27","cited_by_count":141},{"id":"2205.01397","title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)","created":"2022-05-03","cited_by_count":138},{"id":"2003.05161","title":"A Benchmark for Systematic Generalization in Grounded Language Understanding","created":"2020-03-11","cited_by_count":108},{"id":"2102.10717","title":"Abstraction and Analogy-Making in Artificial Intelligence","created":"2021-02-22","cited_by_count":103},{"id":"2304.03843","title":"Why think step by step? Reasoning emerges from the locality of experience","created":"2023-04-07","cited_by_count":103},{"id":"1906.05381","title":"Compositional generalization through meta sequence-to-sequence learning","created":"2019-06-12","cited_by_count":99},{"id":"2209.15003","title":"Compositional Semantic Parsing with Large Language Models","created":"2022-09-29","cited_by_count":95},{"id":"1710.10686","title":"Regularization for Deep Learning: A Taxonomy","created":"2017-10-29","cited_by_count":91},{"id":"2312.09230","title":"Successor Heads: Recurring, Interpretable Attention Heads In The Wild","created":"2023-12-14","cited_by_count":77},{"id":"2003.05562","title":"Learning Compositional Rules via Neural Program Synthesis","created":"2020-03-12","cited_by_count":74},{"id":"2108.04378","title":"Making Transformers Solve Compositional Tasks","created":"2021-08-09","cited_by_count":72},{"id":"2010.03706","title":"Learning to Recombine and Resample Data for Compositional Generalization","created":"2020-10-08","cited_by_count":65},{"id":"2106.04252","title":"Meta-Learning to Compositionally Generalize","created":"2021-06-08","cited_by_count":62},{"id":"2107.08221","title":"Visual Representation Learning Does Not Generalize Strongly Within the Same Domain","created":"2021-07-17","cited_by_count":61},{"id":"2006.10627","title":"Compositional Generalization by Learning Analytical Expressions","created":"2020-06-18","cited_by_count":53},{"id":"1905.12614","title":"Unsupervised Model Selection for Variational Disentangled Representation Learning","created":"2019-05-29","cited_by_count":46},{"id":"2112.07610","title":"Improving Compositional Generalization with Latent Structure and Data Augmentation","created":"2021-12-14","cited_by_count":46},{"id":"2210.00482","title":"Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language","created":"2022-10-02","cited_by_count":42},{"id":"1911.03872","title":"Location Attention for Extrapolation to Longer Sequences","created":"2019-11-10","cited_by_count":33},{"id":"2106.05121","title":"Grounding inductive biases in natural images:invariance stems from variations in data","created":"2021-06-09","cited_by_count":27},{"id":"1905.08527","title":"CNNs found to jump around more skillfully than RNNs: Compositional generalization in seq2seq convolutional networks","created":"2019-05-21","cited_by_count":22},{"id":"2209.07431","title":"Compositional generalization through abstract representations in human and artificial neural networks","created":"2022-09-15","cited_by_count":22},{"id":"2203.07402","title":"Revisiting the Compositional Generalization Abilities of Neural Sequence Models","created":"2022-03-14","cited_by_count":20},{"id":"2008.02742","title":"Compositional Networks Enable Systematic Generalization for Grounded Language Understanding","created":"2020-08-06","cited_by_count":18},{"id":"2205.01538","title":"SUBS: Subtree Substitution for Compositional Semantic Parsing","created":"2022-05-03","cited_by_count":16},{"id":"2009.05552","title":"Systematic Generalization on gSCAN with Language Conditioned Embedding","created":"2020-09-11","cited_by_count":15},{"id":"2109.12243","title":"Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?","created":"2021-09-25","cited_by_count":15},{"id":"2407.05897","title":"Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models","created":"2024-07-08","cited_by_count":13},{"id":"2009.13962","title":"Think before you act: A simple baseline for compositional generalization","created":"2020-09-29","cited_by_count":11},{"id":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11},{"id":"2201.12926","title":"Compositionality as Lexical Symmetry","created":"2022-01-30","cited_by_count":8},{"id":"2211.15578","title":"Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality","created":"2022-11-28","cited_by_count":8},{"id":"2311.04420","title":"Data Factors for Better Compositional Generalization","created":"2023-11-08","cited_by_count":5},{"id":"2309.08798","title":"D3: Data Diversity Design for Systematic Generalization in Visual Question Answering","created":"2023-09-15","cited_by_count":2}],"next_cursor":null}