{"list":"other","total":81,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"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":"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":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"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":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"2002.10179","title":"HRank: Filter Pruning using High-Rank Feature Map","created":"2020-02-24","cited_by_count":292},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"id":"2111.15666","title":"HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing","created":"2021-11-30","cited_by_count":208},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203},{"id":"2301.12314","title":"Progressive Prompts: Continual Learning for Language Models","created":"2023-01-29","cited_by_count":197},{"id":"1707.01213","title":"Data-Driven Sparse Structure Selection for Deep Neural Networks","created":"2017-07-05","cited_by_count":181},{"id":"2104.07650","title":"KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction","created":"2021-04-15","cited_by_count":180},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173},{"id":"1810.11809","title":"Discrimination-aware Channel Pruning for Deep Neural Networks","created":"2018-10-28","cited_by_count":171},{"id":"2210.07225","title":"Unified Vision and Language Prompt Learning","created":"2022-10-13","cited_by_count":148},{"id":"1804.03230","title":"NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications","created":"2018-04-09","cited_by_count":147},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135},{"id":"1810.05749","title":"Graph HyperNetworks for Neural Architecture Search","created":"2018-10-12","cited_by_count":132},{"id":"2108.00708","title":"Group Fisher Pruning for Practical Network Compression","created":"2021-08-02","cited_by_count":131},{"id":"2303.10883","title":"Explicit Visual Prompting for Low-Level Structure Segmentations","created":"2023-03-20","cited_by_count":114},{"id":"2012.09243","title":"Neural Pruning via Growing Regularization","created":"2020-12-16","cited_by_count":97},{"id":"2012.06908","title":"The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models","created":"2020-12-12","cited_by_count":91},{"id":"2211.11635","title":"Understanding and Improving Visual Prompting: A Label-Mapping Perspective","created":"2022-11-21","cited_by_count":87},{"id":"2001.08565","title":"Channel Pruning via Automatic Structure Search","created":"2020-01-23","cited_by_count":85},{"id":"2202.02643","title":"The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training","created":"2022-02-05","cited_by_count":85},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84},{"id":"2010.03533","title":"Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win","created":"2020-10-07","cited_by_count":77},{"id":"2003.01794","title":"Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection","created":"2020-03-03","cited_by_count":70},{"id":"2210.01033","title":"LPT: Long-tailed Prompt Tuning for Image Classification","created":"2022-10-03","cited_by_count":69},{"id":"2303.04935","title":"X-Pruner: eXplainable Pruning for Vision Transformers","created":"2023-03-08","cited_by_count":68},{"id":"2003.13683","title":"DHP: Differentiable Meta Pruning via HyperNetworks","created":"2020-03-30","cited_by_count":57},{"id":"2205.01703","title":"Improving In-Context Few-Shot Learning via Self-Supervised Training","created":"2022-05-03","cited_by_count":57},{"id":"1911.08114","title":"Neural Network Pruning with Residual-Connections and Limited-Data","created":"2019-11-19","cited_by_count":52},{"id":"2208.08914","title":"Prompt Vision Transformer for Domain Generalization","created":"2022-08-18","cited_by_count":52},{"id":"2108.04657","title":"Differentiable Subset Pruning of Transformer Heads","created":"2021-08-10","cited_by_count":47},{"id":"1911.12491","title":"QKD: Quantization-aware Knowledge Distillation","created":"2019-11-28","cited_by_count":44},{"id":"2306.03805","title":"The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter","created":"2023-06-06","cited_by_count":42},{"id":"2110.11395","title":"SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning","created":"2021-10-19","cited_by_count":30},{"id":"2305.11186","title":"Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt","created":"2023-05-17","cited_by_count":28},{"id":"2305.19454","title":"Dynamic Sparsity Is Channel-Level Sparsity Learner","created":"2023-05-30","cited_by_count":18},{"id":"2101.07985","title":"Network Pruning using Adaptive Exemplar Filters","created":"2021-01-20","cited_by_count":16},{"id":"2202.07190","title":"Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters","created":"2022-02-15","cited_by_count":16},{"id":"2211.15335","title":"You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets","created":"2022-11-28","cited_by_count":14},{"id":"2305.19412","title":"Are Large Kernels Better Teachers than Transformers for ConvNets?","created":"2023-05-30","cited_by_count":8},{"id":"2005.13796","title":"A Feature-map Discriminant Perspective for Pruning Deep Neural Networks","created":"2020-05-28","cited_by_count":4}],"next_cursor":null}