{"list":"other","total":62,"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"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":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362},{"id":"2108.06209","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","created":"2021-08-07","cited_by_count":347},{"id":"1602.02068","title":"From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification","created":"2016-02-05","cited_by_count":341},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237},{"id":"2112.07916","title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","created":"2021-12-15","cited_by_count":232},{"id":"1502.04759","title":"Coordinate Descent Algorithms","created":"2015-02-17","cited_by_count":219},{"id":"1910.04732","title":"Structured Pruning of Large Language Models","created":"2019-10-10","cited_by_count":203},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191},{"id":"2203.17189","title":"Scaling Up Models and Data with $\\texttt{t5x}$ and $\\texttt{seqio}$","created":"2022-03-31","cited_by_count":187},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170},{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164},{"id":"2202.01855","title":"Self-supervised Learning with Random-projection Quantizer for Speech Recognition","created":"2022-02-03","cited_by_count":162},{"id":"2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","created":"2021-08-07","cited_by_count":120},{"id":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88},{"id":"1902.08295","title":"Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling","created":"2019-02-21","cited_by_count":86},{"id":"2303.09752","title":"CoLT5: Faster Long-Range Transformers with Conditional Computation","created":"2023-03-17","cited_by_count":84},{"id":"2211.09761","title":"Efficient Transformers with Dynamic Token Pooling","created":"2022-11-17","cited_by_count":76},{"id":"2009.07253","title":"Autoregressive Knowledge Distillation through Imitation Learning","created":"2020-09-15","cited_by_count":74},{"id":"1610.06519","title":"Stabilized Sparse Scaling Algorithms for Entropy Regularized Transport Problems","created":"2016-10-20","cited_by_count":73},{"id":"2205.12647","title":"Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation","created":"2022-05-25","cited_by_count":62},{"id":"1911.03864","title":"Improving Transformer Models by Reordering their Sublayers","created":"2019-11-10","cited_by_count":52},{"id":"2102.12459","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","created":"2021-02-24","cited_by_count":34},{"id":"2106.13700","title":"ViTAS: Vision Transformer Architecture Search","created":"2021-06-25","cited_by_count":31},{"id":"2002.07106","title":"Controlling Computation versus Quality for Neural Sequence Models","created":"2020-02-17","cited_by_count":27},{"id":"2210.12517","title":"Exploring The Landscape of Distributional Robustness for Question Answering Models","created":"2022-10-22","cited_by_count":23},{"id":"2205.14107","title":"Spartan: Differentiable Sparsity via Regularized Transportation","created":"2022-05-27","cited_by_count":8}],"next_cursor":null}