{"list":"other","total":69,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2107.07511","title":"A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification","created":"2021-07-15","cited_by_count":792},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"2105.13626","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","created":"2021-05-28","cited_by_count":509},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"2101.02703","title":"Distribution-Free, Risk-Controlling Prediction Sets","created":"2021-01-07","cited_by_count":288},{"id":"2006.04152","title":"BERT Loses Patience: Fast and Robust Inference with Early Exit","created":"2020-06-07","cited_by_count":273},{"id":"2004.04037","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","created":"2020-04-08","cited_by_count":251},{"id":"1910.10073","title":"Depth-Adaptive Transformer","created":"2019-10-22","cited_by_count":236},{"id":"2004.02178","title":"FastBERT: a Self-distilling BERT with Adaptive Inference Time","created":"2020-04-05","cited_by_count":226},{"id":"2203.08913","title":"Memorizing Transformers","created":"2022-03-16","cited_by_count":226},{"id":"2203.17189","title":"Scaling Up Models and Data with $\\texttt{t5x}$ and $\\texttt{seqio}$","created":"2022-03-31","cited_by_count":187},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161},{"id":"2202.07282","title":"Adaptive Conformal Predictions for Time Series","created":"2022-02-15","cited_by_count":161},{"id":"2004.07453","title":"The Right Tool for the Job: Matching Model and Instance Complexities","created":"2020-04-16","cited_by_count":126},{"id":"2202.05265","title":"Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging","created":"2022-02-10","cited_by_count":107},{"id":"2006.10369","title":"Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation","created":"2020-06-18","cited_by_count":105},{"id":"2004.08900","title":"The Cost of Training NLP Models: A Concise Overview","created":"2020-04-19","cited_by_count":98},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98},{"id":"2110.03742","title":"Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference","created":"2021-09-24","cited_by_count":96},{"id":"1909.06694","title":"Beyond BLEU: Training Neural Machine Translation with Semantic Similarity","created":"2019-09-14","cited_by_count":84},{"id":"2010.07003","title":"Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search","created":"2020-10-14","cited_by_count":76},{"id":"2104.08803","title":"Consistent Accelerated Inference via Confident Adaptive Transformers","created":"2021-04-18","cited_by_count":74},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52},{"id":"2012.14682","title":"CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade","created":"2020-12-29","cited_by_count":47},{"id":"2110.07038","title":"Towards Efficient NLP: A Standard Evaluation and A Strong Baseline","created":"2021-10-13","cited_by_count":44},{"id":"2102.12459","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","created":"2021-02-24","cited_by_count":34},{"id":"2202.07650","title":"Conformal Prediction Sets with Limited False Positives","created":"2022-02-15","cited_by_count":28},{"id":"2002.07106","title":"Controlling Computation versus Quality for Neural Sequence Models","created":"2020-02-17","cited_by_count":27},{"id":"2202.11091","title":"Efficient and Differentiable Conformal Prediction with General Function Classes","created":"2022-02-22","cited_by_count":26},{"id":"2106.05784","title":"Programming Puzzles","created":"2021-06-10","cited_by_count":25},{"id":"2111.02592","title":"Conformal prediction for text infilling and part-of-speech prediction","created":"2021-11-04","cited_by_count":22},{"id":"2104.00749","title":"Anytime Dense Prediction with Confidence Adaptivity","created":"2021-04-01","cited_by_count":18},{"id":"2110.07661","title":"Distribution-Free Federated Learning with Conformal Predictions","created":"2021-10-14","cited_by_count":16},{"id":"1611.06188","title":"Variable Computation in Recurrent Neural Networks","created":"2016-11-18","cited_by_count":10},{"id":"2010.11358","title":"N-ODE Transformer: A Depth-Adaptive Variant of the Transformer Using Neural Ordinary Differential Equations","created":"2020-10-22","cited_by_count":9},{"id":"1712.00386","title":"Probabilistic Adaptive Computation Time","created":"2017-12-01","cited_by_count":4}],"next_cursor":null}