{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"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":"1904.06991","title":"Improved Precision and Recall Metric for Assessing Generative Models","created":"2019-04-15","cited_by_count":944},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"2103.03841","title":"Generating Images with Sparse Representations","created":"2021-03-05","cited_by_count":266},{"id":"1906.04284","title":"Analyzing the Structure of Attention in a Transformer Language Model","created":"2019-06-07","cited_by_count":243},{"id":"1604.06443","title":"Robust Estimators in High Dimensions without the Computational Intractability","created":"2016-04-21","cited_by_count":209},{"id":"2112.13890","title":"SPViT: Enabling Faster Vision Transformers via Soft Token Pruning","created":"2021-12-27","cited_by_count":167},{"id":"2110.07814","title":"Meta-learning via Language Model In-context Tuning","created":"2021-10-15","cited_by_count":164},{"id":"2305.13311","title":"VDT: General-purpose Video Diffusion Transformers via Mask Modeling","created":"2023-05-22","cited_by_count":103},{"id":"1810.07896","title":"Solving Linear Programs in the Current Matrix Multiplication Time","created":"2018-10-18","cited_by_count":100},{"id":"1905.04447","title":"Solving Empirical Risk Minimization in the Current Matrix Multiplication Time","created":"2019-05-11","cited_by_count":53},{"id":"2009.10217","title":"A Faster Interior Point Method for Semidefinite Programming","created":"2020-09-21","cited_by_count":53},{"id":"2004.07470","title":"Faster Dynamic Matrix Inverse for Faster LPs","created":"2020-04-16","cited_by_count":44},{"id":"2303.15725","title":"Solving Regularized Exp, Cosh and Sinh Regression Problems","created":"2023-03-28","cited_by_count":44},{"id":"2310.04064","title":"How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation","created":"2023-10-06","cited_by_count":44},{"id":"1910.11957","title":"A Deterministic Linear Program Solver in Current Matrix Multiplication Time","created":"2019-10-25","cited_by_count":42},{"id":"1906.11366","title":"Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detection","created":"2019-06-26","cited_by_count":41},{"id":"2304.04397","title":"Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension","created":"2023-04-10","cited_by_count":37},{"id":"2211.06033","title":"A Faster Small Treewidth SDP Solver","created":"2022-11-11","cited_by_count":36},{"id":"1802.10542","title":"Memory-based Parameter Adaptation","created":"2018-02-28","cited_by_count":35},{"id":"2006.06980","title":"Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing","created":"2020-06-12","cited_by_count":35},{"id":"2305.00660","title":"An Iterative Algorithm for Rescaled Hyperbolic Functions Regression","created":"2023-05-01","cited_by_count":35},{"id":"2108.08910","title":"Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search","created":"2021-08-18","cited_by_count":34},{"id":"2101.08208","title":"Solving SDP Faster: A Robust IPM Framework and Efficient Implementation","created":"2021-01-20","cited_by_count":33},{"id":"2312.05693","title":"Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge","created":"2023-12-09","cited_by_count":33},{"id":"2206.01198","title":"Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization","created":"2022-06-02","cited_by_count":32},{"id":"1409.3257","title":"Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization","created":"2014-09-10","cited_by_count":31},{"id":"2011.05365","title":"A Nearly-Linear Time Algorithm for Linear Programs with Small Treewidth: A Multiscale Representation of Robust Central Path","created":"2020-11-10","cited_by_count":29},{"id":"2211.10801","title":"Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training","created":"2022-11-19","cited_by_count":24},{"id":"2406.05871","title":"OmniControlNet: Dual-stage Integration for Conditional Image Generation","created":"2024-06-09","cited_by_count":24},{"id":"2310.16305","title":"Dolfin: Diffusion Layout Transformers without Autoencoder","created":"2023-10-25","cited_by_count":23},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22},{"id":"2410.11268","title":"Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent","created":"2024-10-15","cited_by_count":22},{"id":"2002.02304","title":"Solving Tall Dense Linear Programs in Nearly Linear Time","created":"2020-02-06","cited_by_count":21},{"id":"1412.6606","title":"Competing with the Empirical Risk Minimizer in a Single Pass","created":"2014-12-20","cited_by_count":20},{"id":"2207.12577","title":"Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution","created":"2022-07-25","cited_by_count":20},{"id":"2410.11261","title":"Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix","created":"2024-10-15","cited_by_count":20},{"id":"2410.15567","title":"Pruning Foundation Models for High Accuracy without Retraining","created":"2024-10-21","cited_by_count":20},{"id":"2410.09375","title":"Looped ReLU MLPs May Be All You Need as Practical Programmable Computers","created":"2024-10-12","cited_by_count":19},{"id":"2407.13621","title":"Differential Privacy Mechanisms in Neural Tangent Kernel Regression","created":"2024-07-18","cited_by_count":14},{"id":"2411.01171","title":"Fast and Memory-Efficient Video Diffusion Using Streamlined Inference","created":"2024-11-02","cited_by_count":14},{"id":"1803.09357","title":"On the Local Minima of the Empirical Risk","created":"2018-03-25","cited_by_count":12},{"id":"2309.13482","title":"A Unified Scheme of ResNet and Softmax","created":"2023-09-23","cited_by_count":12},{"id":"2310.12462","title":"Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights","created":"2023-10-19","cited_by_count":12},{"id":"2305.17482","title":"Federated Empirical Risk Minimization via Second-Order Method","created":"2023-05-27","cited_by_count":9},{"id":"2311.15390","title":"Local Convergence of Approximate Newton Method for Two Layer Nonlinear Regression","created":"2023-11-26","cited_by_count":9},{"id":"2203.08542","title":"Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act","created":"2022-03-16","cited_by_count":7},{"id":"2211.01484","title":"Data Level Lottery Ticket Hypothesis for Vision Transformers","created":"2022-11-02","cited_by_count":7},{"id":"2310.20051","title":"The Expressibility of Polynomial based Attention Scheme","created":"2023-10-30","cited_by_count":7},{"id":"2010.13888","title":"Unifying Matrix Data Structures: Simplifying and Speeding up Iterative Algorithms","created":"2020-10-26","cited_by_count":4},{"id":"1412.0156","title":"Constant Step Size Least-Mean-Square: Bias-Variance Trade-offs and Optimal Sampling Distributions","created":"2014-11-29","cited_by_count":2},{"id":"2402.07027","title":"Quantum Speedup for Spectral Approximation of Kronecker Products","created":"2024-02-10","cited_by_count":1}],"next_cursor":null}