{"list":"other","total":63,"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":"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":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"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":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"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":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"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":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"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":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"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":"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":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"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":"1607.03250","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","created":"2016-07-12","cited_by_count":221},{"id":"1705.07565","title":"Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon","created":"2017-05-22","cited_by_count":221},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177},{"id":"2010.05874","title":"Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models","created":"2020-10-12","cited_by_count":169},{"id":"2010.03058","title":"Characterising Bias in Compressed Models","created":"2020-10-06","cited_by_count":167},{"id":"2210.07225","title":"Unified Vision and Language Prompt Learning","created":"2022-10-13","cited_by_count":148},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135},{"id":"2303.10883","title":"Explicit Visual Prompting for Low-Level Structure Segmentations","created":"2023-03-20","cited_by_count":114},{"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":"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":"2111.05754","title":"Prune Once for All: Sparse Pre-Trained Language Models","created":"2021-11-10","cited_by_count":66},{"id":"2210.04092","title":"Advancing Model Pruning via Bi-level Optimization","created":"2022-10-08","cited_by_count":56},{"id":"2107.03356","title":"M-FAC: Efficient Matrix-Free Approximations of Second-Order Information","created":"2021-07-07","cited_by_count":54},{"id":"2208.08914","title":"Prompt Vision Transformer for Domain Generalization","created":"2022-08-18","cited_by_count":52},{"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":"2202.09844","title":"Sparsity Winning Twice: Better Robust Generalization from More Efficient Training","created":"2022-02-20","cited_by_count":41},{"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":"2202.04736","title":"Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets","created":"2022-02-09","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":"2208.03646","title":"A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipelining","created":"2022-08-07","cited_by_count":22},{"id":"2209.04766","title":"Towards Sparsification of Graph Neural Networks","created":"2022-09-11","cited_by_count":18},{"id":"2305.19454","title":"Dynamic Sparsity Is Channel-Level Sparsity Learner","created":"2023-05-30","cited_by_count":18},{"id":"2211.16667","title":"Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off","created":"2022-11-30","cited_by_count":15},{"id":"2108.04811","title":"Binary Complex Neural Network Acceleration on FPGA","created":"2021-08-10","cited_by_count":14},{"id":"2110.03252","title":"Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling","created":"2021-10-07","cited_by_count":14},{"id":"2110.07431","title":"Towards More Effective and Economic Sparsely-Activated Model","created":"2021-10-14","cited_by_count":11},{"id":"2306.14275","title":"Enhancing Adversarial Training via Reweighting Optimization Trajectory","created":"2023-06-25","cited_by_count":4}],"next_cursor":null}