{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1811.03115","title":"Blockwise Parallel Decoding for Deep Autoregressive Models","created":"2018-11-07","cited_by_count":323},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322},{"id":"2212.14024","title":"Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP","created":"2022-12-28","cited_by_count":318},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"2212.00193","title":"Distilling Reasoning Capabilities into Smaller Language Models","created":"2022-12-01","cited_by_count":158},{"id":"2206.09557","title":"LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models","created":"2022-06-20","cited_by_count":105},{"id":"2102.08124","title":"Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks","created":"2021-02-16","cited_by_count":103},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70},{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62},{"id":"1906.03593","title":"Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound","created":"2019-06-09","cited_by_count":59},{"id":"1311.2495","title":"The Noisy Power Method: A Meta Algorithm with Applications","created":"2013-11-11","cited_by_count":58},{"id":"2108.09420","title":"Fast Sketching of Polynomial Kernels of Polynomial Degree","created":"2021-08-21","cited_by_count":33},{"id":"1607.07837","title":"First Efficient Convergence for Streaming k-PCA: a Global, Gap-Free, and Near-Optimal Rate","created":"2016-07-26","cited_by_count":32},{"id":"2210.13738","title":"Pruning's Effect on Generalization Through the Lens of Training and Regularization","created":"2022-10-25","cited_by_count":31},{"id":"2011.06997","title":"Kernel Density Estimation through Density Constrained Near Neighbor Search","created":"2020-11-13","cited_by_count":29},{"id":"2006.08228","title":"Finding trainable sparse networks through Neural Tangent Transfer","created":"2020-06-15","cited_by_count":28},{"id":"2303.00106","title":"The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning","created":"2023-02-28","cited_by_count":27},{"id":"1712.09007","title":"Stochastic Multi-armed Bandits in Constant Space","created":"2017-12-25","cited_by_count":22},{"id":"2011.02466","title":"Algorithms and Hardness for Linear Algebra on Geometric Graphs","created":"2020-11-04","cited_by_count":22},{"id":"1307.0032","title":"Memory Limited, Streaming PCA","created":"2013-06-28","cited_by_count":21},{"id":"2102.03646","title":"Streaming k-PCA: Efficient guarantees for Oja's algorithm, beyond rank-one updates","created":"2021-02-06","cited_by_count":21},{"id":"1602.02262","title":"Recovery guarantee of weighted low-rank approximation via alternating minimization","created":"2016-02-06","cited_by_count":20},{"id":"2205.06249","title":"Optimal-Degree Polynomial Approximations for Exponentials and Gaussian Kernel Density Estimation","created":"2022-05-12","cited_by_count":19},{"id":"1501.03796","title":"The Fast Convergence of Incremental PCA","created":"2015-01-15","cited_by_count":15},{"id":"2210.08361","title":"A Nearly Optimal Size Coreset Algorithm with Nearly Linear Time","created":"2022-10-15","cited_by_count":13},{"id":"2106.14857","title":"Bootstrapping the error of Oja's algorithm","created":"2021-06-28","cited_by_count":11},{"id":"1307.1674","title":"Stochastic Optimization of PCA with Capped MSG","created":"2013-07-05","cited_by_count":6},{"id":"1802.08237","title":"Improved Massively Parallel Computation Algorithms for MIS, Matching, and Vertex Cover","created":"2018-02-22","cited_by_count":2},{"id":"1807.08331","title":"Independent Sets in Vertex-Arrival Streams","created":"2018-07-22","cited_by_count":2},{"id":"1808.04995","title":"The Sketching Complexity of Graph and Hypergraph Counting","created":"2018-08-15","cited_by_count":2},{"id":"1903.12150","title":"Dynamic Streaming Spectral Sparsification in Nearly Linear Time and Space","created":"2019-03-28","cited_by_count":2},{"id":"1409.2138","title":"Streaming Lower Bounds for Approximating MAX-CUT","created":"2014-09-07","cited_by_count":1},{"id":"1811.02760","title":"Weighted Matchings via Unweighted Augmentations","created":"2018-11-07","cited_by_count":1}],"next_cursor":null}