{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"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":"2402.02491","title":"VM-UNet: Vision Mamba UNet for Medical Image Segmentation","created":"2024-02-04","cited_by_count":287},{"id":"2401.13560","title":"SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation","created":"2024-01-24","cited_by_count":266},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179},{"id":"2402.03302","title":"Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining","created":"2024-02-05","cited_by_count":179},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136},{"id":"2402.00789","title":"Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces","created":"2024-02-01","cited_by_count":134},{"id":"2402.05079","title":"Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation","created":"2024-02-07","cited_by_count":133},{"id":"2110.11945","title":"SOFT: Softmax-free Transformer with Linear Complexity","created":"2021-10-22","cited_by_count":128},{"id":"1709.04057","title":"Parallelizing Linear Recurrent Neural Nets Over Sequence Length","created":"2017-09-12","cited_by_count":127},{"id":"2102.02611","title":"CKConv: Continuous Kernel Convolution For Sequential Data","created":"2021-02-04","cited_by_count":120},{"id":"2303.14526","title":"Selective Structured State-Spaces for Long-Form Video Understanding","created":"2023-03-25","cited_by_count":105},{"id":"2202.07304","title":"XAI for Transformers: Better Explanations through Conservative Propagation","created":"2022-02-15","cited_by_count":100},{"id":"2206.09959","title":"Global Context Vision Transformers","created":"2022-06-20","cited_by_count":98},{"id":"1706.07206","title":"Explaining Recurrent Neural Network Predictions in Sentiment Analysis","created":"2017-06-22","cited_by_count":88},{"id":"2402.08678","title":"Graph Mamba: Towards Learning on Graphs with State Space Models","created":"2024-02-13","cited_by_count":86},{"id":"2311.18257","title":"Diffusion Models Without Attention","created":"2023-11-30","cited_by_count":75},{"id":"2309.11523","title":"RMT: Retentive Networks Meet Vision Transformers","created":"2023-09-20","cited_by_count":68},{"id":"2303.01267","title":"Token Contrast for Weakly-Supervised Semantic Segmentation","created":"2023-03-02","cited_by_count":65},{"id":"2401.14168","title":"Vivim: a Video Vision Mamba for Medical Video Segmentation","created":"2024-01-25","cited_by_count":52},{"id":"1904.00605","title":"Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks","created":"2019-04-01","cited_by_count":49},{"id":"2104.12753","title":"Vision Transformers with Patch Diversification","created":"2021-04-26","cited_by_count":45},{"id":"2402.03526","title":"nnMamba: 3D Biomedical Image Segmentation, Classification and Landmark Detection with State Space Model","created":"2024-02-05","cited_by_count":45},{"id":"2309.08586","title":"Replacing softmax with ReLU in Vision Transformers","created":"2023-09-15","cited_by_count":44},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41},{"id":"2312.00751","title":"Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals","created":"2023-12-01","cited_by_count":32},{"id":"2306.05167","title":"Decision S4: Efficient Sequence-Based RL via State Spaces Layers","created":"2023-06-08","cited_by_count":26},{"id":"2302.14120","title":"Diagonal State Space Augmented Transformers for Speech Recognition","created":"2023-02-27","cited_by_count":25},{"id":"2012.02166","title":"Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization","created":"2020-12-03","cited_by_count":23},{"id":"2212.00768","title":"Simplifying and Understanding State Space Models with Diagonal Linear RNNs","created":"2022-12-01","cited_by_count":23},{"id":"2401.04301","title":"Setting the Record Straight on Transformer Oversmoothing","created":"2024-01-09","cited_by_count":21},{"id":"2311.08610","title":"Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption","created":"2023-11-15","cited_by_count":19},{"id":"2306.06635","title":"2-D SSM: A General Spatial Layer for Visual Transformers","created":"2023-06-11","cited_by_count":18},{"id":"2305.06154","title":"Alleviating Over-smoothing for Unsupervised Sentence Representation","created":"2023-05-09","cited_by_count":16},{"id":"2305.14952","title":"Focus Your Attention (with Adaptive IIR Filters)","created":"2023-05-24","cited_by_count":12},{"id":"2112.08914","title":"Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling","created":"2021-12-16","cited_by_count":10},{"id":"2311.16620","title":"On the Long Range Abilities of Transformers","created":"2023-11-28","cited_by_count":10},{"id":"2306.01610","title":"Centered Self-Attention Layers","created":"2023-06-02","cited_by_count":7},{"id":"2309.13600","title":"Multi-Dimensional Hyena for Spatial Inductive Bias","created":"2023-09-24","cited_by_count":5},{"id":"2111.13156","title":"Global Interaction Modelling in Vision Transformer via Super Tokens","created":"2021-11-25","cited_by_count":4}],"next_cursor":null}