{"list":"other","total":100,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"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":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1906.03671","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","created":"2019-06-09","cited_by_count":610},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"1810.09502","title":"How to train your MAML","created":"2018-10-22","cited_by_count":309},{"id":"1904.09223","title":"ERNIE: Enhanced Representation through Knowledge Integration","created":"2019-04-19","cited_by_count":302},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"1812.09926","title":"SNAS: Stochastic Neural Architecture Search","created":"2018-12-24","cited_by_count":289},{"id":"1511.05641","title":"Net2Net: Accelerating Learning via Knowledge Transfer","created":"2015-11-18","cited_by_count":250},{"id":"2012.15828","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","created":"2020-12-31","cited_by_count":245},{"id":"1607.03250","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","created":"2016-07-12","cited_by_count":221},{"id":"1511.02680","title":"Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding","created":"2015-11-09","cited_by_count":218},{"id":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199},{"id":"1412.6115","title":"Compressing Deep Convolutional Networks using Vector Quantization","created":"2014-12-18","cited_by_count":195},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180},{"id":"2007.03051","title":"Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models","created":"2020-07-06","cited_by_count":169},{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169},{"id":"1802.09841","title":"Adversarial Active Learning for Deep Networks: a Margin Based Approach","created":"2018-02-27","cited_by_count":158},{"id":"2306.08543","title":"MiniLLM: On-Policy Distillation of Large Language Models","created":"2023-06-14","cited_by_count":139},{"id":"1907.01845","title":"FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search","created":"2019-07-03","cited_by_count":130},{"id":"1606.05535","title":"Tensor Ring Decomposition","created":"2016-06-17","cited_by_count":127},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122},{"id":"1507.06149","title":"Data-free parameter pruning for Deep Neural Networks","created":"2015-07-22","cited_by_count":112},{"id":"1802.00124","title":"Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers","created":"2018-02-01","cited_by_count":112},{"id":"1907.06347","title":"Discriminative Active Learning","created":"2019-07-15","cited_by_count":98},{"id":"2205.14141","title":"Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation","created":"2022-05-27","cited_by_count":93},{"id":"2203.13450","title":"A Comparative Survey of Deep Active Learning","created":"2022-03-25","cited_by_count":89},{"id":"2104.06022","title":"Lessons on Parameter Sharing across Layers in Transformers","created":"2021-04-13","cited_by_count":85},{"id":"1708.02383","title":"Learning how to Active Learn: A Deep Reinforcement Learning Approach","created":"2017-08-08","cited_by_count":79},{"id":"2101.00063","title":"EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets","created":"2020-12-31","cited_by_count":79},{"id":"2308.03279","title":"UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition","created":"2023-08-07","cited_by_count":72},{"id":"2305.05940","title":"Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment","created":"2023-05-10","cited_by_count":71},{"id":"2206.08082","title":"Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator","created":"2022-06-16","cited_by_count":68},{"id":"2201.05119","title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","created":"2022-01-13","cited_by_count":67},{"id":"2303.07839","title":"ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design","created":"2023-03-11","cited_by_count":66},{"id":"2304.04487","title":"Inference with Reference: Lossless Acceleration of Large Language Models","created":"2023-04-10","cited_by_count":65},{"id":"1810.13306","title":"Automated Machine Learning: From Principles to Practices","created":"2018-10-31","cited_by_count":62},{"id":"2205.01703","title":"Improving In-Context Few-Shot Learning via Self-Supervised Training","created":"2022-05-03","cited_by_count":57},{"id":"1611.03214","title":"Ultimate tensorization: compressing convolutional and FC layers alike","created":"2016-11-10","cited_by_count":56},{"id":"1403.1687","title":"Rigid-Motion Scattering for Texture Classification","created":"2014-03-07","cited_by_count":52},{"id":"1612.01543","title":"Towards the Limit of Network Quantization","created":"2016-12-05","cited_by_count":50},{"id":"2302.12721","title":"LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version","created":"2023-02-24","cited_by_count":50},{"id":"1502.02072","title":"Massively Multitask Networks for Drug Discovery","created":"2015-02-06","cited_by_count":49},{"id":"2005.02161","title":"LambdaNet: Probabilistic Type Inference using Graph Neural Networks","created":"2020-04-29","cited_by_count":44},{"id":"1906.07975","title":"Batch Active Learning Using Determinantal Point Processes","created":"2019-06-19","cited_by_count":43},{"id":"2211.09703","title":"EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones","created":"2022-11-17","cited_by_count":43},{"id":"1906.03520","title":"Domain Adaptive Dialog Generation via Meta Learning","created":"2019-06-08","cited_by_count":41},{"id":"2110.07515","title":"Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision","created":"2021-10-14","cited_by_count":40},{"id":"1708.00489","title":"Active Learning for Convolutional Neural Networks: A Core-Set Approach","created":"2017-08-01","cited_by_count":36},{"id":"2302.09019","title":"Tensor Networks Meet Neural Networks: A Survey and Future Perspectives","created":"2023-01-22","cited_by_count":32},{"id":"2110.11395","title":"SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning","created":"2021-10-19","cited_by_count":30},{"id":"2304.02840","title":"NTK-SAP: Improving neural network pruning by aligning training dynamics","created":"2023-04-06","cited_by_count":30},{"id":"1905.07785","title":"Sparse Transfer Learning via Winning Lottery Tickets","created":"2019-05-19","cited_by_count":27},{"id":"2303.02141","title":"Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!","created":"2023-03-03","cited_by_count":27},{"id":"1707.03141","title":"A Simple Neural Attentive Meta-Learner","created":"2017-07-11","cited_by_count":23},{"id":"2007.08243","title":"Lottery Tickets in Linear Models: An Analysis of Iterative Magnitude Pruning","created":"2020-07-16","cited_by_count":23},{"id":"1412.5474","title":"Flattened Convolutional Neural Networks for Feedforward Acceleration","created":"2014-12-17","cited_by_count":20},{"id":"2308.06689","title":"Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training","created":"2023-08-13","cited_by_count":19},{"id":"2307.00526","title":"TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition","created":"2023-07-02","cited_by_count":17},{"id":"2207.12534","title":"Trainability Preserving Neural Pruning","created":"2022-07-25","cited_by_count":16},{"id":"1812.11800","title":"Regularized Binary Network Training","created":"2018-12-31","cited_by_count":14},{"id":"1906.10337","title":"COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning","created":"2019-06-25","cited_by_count":14},{"id":"2101.10552","title":"A Unified Paths Perspective for Pruning at Initialization","created":"2021-01-26","cited_by_count":14},{"id":"2308.04679","title":"Sci-CoT: Leveraging Large Language Models for Enhanced Knowledge Distillation in Small Models for Scientific QA","created":"2023-08-09","cited_by_count":13},{"id":"2302.13019","title":"A Unified Framework for Soft Threshold Pruning","created":"2023-02-25","cited_by_count":12},{"id":"2106.06955","title":"Towards Understanding Iterative Magnitude Pruning: Why Lottery Tickets Win","created":"2021-06-13","cited_by_count":11},{"id":"2307.13018","title":"The potential of LLMs for coding with low-resource and domain-specific programming languages","created":"2023-07-24","cited_by_count":11},{"id":"2309.04564","title":"When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale","created":"2023-09-08","cited_by_count":10},{"id":"2309.06626","title":"Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity","created":"2023-09-12","cited_by_count":10},{"id":"2103.01148","title":"E$^2$CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning","created":"2021-03-01","cited_by_count":8},{"id":"2009.14448","title":"Ask-n-Learn: Active Learning via Reliable Gradient Representations for Image Classification","created":"2020-09-30","cited_by_count":7},{"id":"2303.00973","title":"Image Labels Are All You Need for Coarse Seagrass Segmentation","created":"2023-03-02","cited_by_count":7},{"id":"2211.01071","title":"Gradient Knowledge Distillation for Pre-trained Language Models","created":"2022-11-02","cited_by_count":5},{"id":"2108.07670","title":"ImitAL: Learning Active Learning Strategies from Synthetic Data","created":"2021-08-17","cited_by_count":3},{"id":"1806.10332","title":"MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning","created":"2018-06-27","cited_by_count":2},{"id":"2112.12433","title":"Sparse-softmax: A Simpler and Faster Alternative Softmax Transformation","created":"2021-12-23","cited_by_count":2}],"next_cursor":null}