{"list":"other","total":95,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"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":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"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":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"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":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1908.00709","title":"AutoML: A Survey of the State-of-the-Art","created":"2019-08-02","cited_by_count":390},{"id":"2401.15024","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","created":"2024-01-26","cited_by_count":385},{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"1703.01041","title":"Large-Scale Evolution of Image Classifiers","created":"2017-03-03","cited_by_count":348},{"id":"1902.09635","title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","created":"2019-02-25","cited_by_count":344},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"1903.10258","title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","created":"2019-03-25","cited_by_count":227},{"id":"1904.01186","title":"Data-Free Learning of Student Networks","created":"2019-04-02","cited_by_count":204},{"id":"1910.11858","title":"BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search","created":"2019-10-25","cited_by_count":179},{"id":"1507.00448","title":"Cross Modal Distillation for Supervision Transfer","created":"2015-07-02","cited_by_count":175},{"id":"2002.05715","title":"Self-Distillation Amplifies Regularization in Hilbert Space","created":"2020-02-13","cited_by_count":173},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162},{"id":"1909.11957","title":"Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks","created":"2019-09-26","cited_by_count":160},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139},{"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":"1912.00350","title":"Online Knowledge Distillation with Diverse Peers","created":"2019-12-01","cited_by_count":128},{"id":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127},{"id":"1905.09747","title":"Adversarially Robust Distillation","created":"2019-05-23","cited_by_count":125},{"id":"1909.08174","title":"Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks","created":"2019-09-18","cited_by_count":118},{"id":"2006.08509","title":"APQ: Joint Search for Network Architecture, Pruning and Quantization Policy","created":"2020-06-15","cited_by_count":99},{"id":"1906.06307","title":"A Signal Propagation Perspective for Pruning Neural Networks at Initialization","created":"2019-06-14","cited_by_count":96},{"id":"2104.01177","title":"How Powerful are Performance Predictors in Neural Architecture Search?","created":"2021-04-02","cited_by_count":90},{"id":"2101.00063","title":"EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets","created":"2020-12-31","cited_by_count":79},{"id":"2311.05657","title":"Agent Lumos: Unified and Modular Training for Open-Source Language Agents","created":"2023-11-09","cited_by_count":72},{"id":"2305.18395","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","created":"2023-05-28","cited_by_count":64},{"id":"2405.18886","title":"Compressing Large Language Models using Low Rank and Low Precision Decomposition","created":"2024-05-29","cited_by_count":59},{"id":"2003.13683","title":"DHP: Differentiable Meta Pruning via HyperNetworks","created":"2020-03-30","cited_by_count":57},{"id":"2402.10110","title":"Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning","created":"2024-02-15","cited_by_count":57},{"id":"2204.04588","title":"Robust Cross-Modal Representation Learning with Progressive Self-Distillation","created":"2022-04-10","cited_by_count":55},{"id":"2008.01475","title":"Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap","created":"2020-08-04","cited_by_count":50},{"id":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48},{"id":"2004.02164","title":"DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation","created":"2020-04-05","cited_by_count":47},{"id":"2009.14410","title":"Pruning Filter in Filter","created":"2020-09-30","cited_by_count":47},{"id":"1806.02639","title":"Path-Level Network Transformation for Efficient Architecture Search","created":"2018-06-07","cited_by_count":44},{"id":"2103.05861","title":"Manifold Regularized Dynamic Network Pruning","created":"2021-03-10","cited_by_count":43},{"id":"2402.05406","title":"Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes","created":"2024-02-08","cited_by_count":43},{"id":"2007.04965","title":"A Study on Encodings for Neural Architecture Search","created":"2020-07-09","cited_by_count":38},{"id":"2201.13396","title":"NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy","created":"2022-01-31","cited_by_count":36},{"id":"2411.02530","title":"A Comprehensive Study on Quantization Techniques for Large Language Models","created":"2024-10-30","cited_by_count":36},{"id":"2302.03773","title":"What Matters In The Structured Pruning of Generative Language Models?","created":"2023-02-07","cited_by_count":30},{"id":"1711.02613","title":"Moonshine: Distilling with Cheap Convolutions","created":"2017-11-07","cited_by_count":25},{"id":"2102.05610","title":"Searching for Fast Model Families on Datacenter Accelerators","created":"2021-02-10","cited_by_count":22},{"id":"2305.12356","title":"Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models","created":"2023-05-21","cited_by_count":19},{"id":"2001.07710","title":"An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices","created":"2020-01-20","cited_by_count":18},{"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":"2210.00944","title":"Attention Distillation: self-supervised vision transformer students need more guidance","created":"2022-10-03","cited_by_count":16},{"id":"2407.02068","title":"LPViT: Low-Power Semi-structured Pruning for Vision Transformers","created":"2024-07-02","cited_by_count":16},{"id":"2005.08110","title":"Generalized Bayesian Posterior Expectation Distillation for Deep Neural Networks","created":"2020-05-16","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":"2410.13056","title":"Channel-Wise Mixed-Precision Quantization for Large Language Models","created":"2024-10-16","cited_by_count":11},{"id":"2201.08539","title":"AutoDistill: an End-to-End Framework to Explore and Distill Hardware-Efficient Language Models","created":"2022-01-21","cited_by_count":7},{"id":"2111.04670","title":"Approximate Neural Architecture Search via Operation Distribution Learning","created":"2021-11-08","cited_by_count":6},{"id":"2403.13134","title":"Robust NAS under adversarial training: benchmark, theory, and beyond","created":"2024-03-19","cited_by_count":6},{"id":"2405.02749","title":"Sub-goal Distillation: A Method to Improve Small Language Agents","created":"2024-05-04","cited_by_count":6},{"id":"2112.11438","title":"Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":5},{"id":"2205.03960","title":"Neural Architecture Search using Property Guided Synthesis","created":"2022-05-08","cited_by_count":4},{"id":"1911.09817","title":"Graph Pruning for Model Compression","created":"2019-11-22","cited_by_count":3},{"id":"2409.02026","title":"Foundations of Large Language Model Compression -- Part 1: Weight Quantization","created":"2024-09-03","cited_by_count":2},{"id":"2409.11650","title":"Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview","created":"2024-09-18","cited_by_count":2}],"next_cursor":null}