{"list":"other","total":52,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"2404.19756","title":"KAN: Kolmogorov-Arnold Networks","created":"2024-04-30","cited_by_count":649},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"2011.15091","title":"Inductive Biases for Deep Learning of Higher-Level Cognition","created":"2020-11-30","cited_by_count":275},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269},{"id":"1509.06569","title":"Tensorizing Neural Networks","created":"2015-09-22","cited_by_count":250},{"id":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"2312.05821","title":"ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models","created":"2023-12-10","cited_by_count":169},{"id":"1511.06530","title":"Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications","created":"2015-11-20","cited_by_count":162},{"id":"1606.05535","title":"Tensor Ring Decomposition","created":"2016-06-17","cited_by_count":127},{"id":"2207.10551","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?","created":"2022-07-21","cited_by_count":103},{"id":"2002.09815","title":"Neuron Shapley: Discovering the Responsible Neurons","created":"2020-02-23","cited_by_count":98},{"id":"2102.13219","title":"Learning with invariances in random features and kernel models","created":"2021-02-25","cited_by_count":89},{"id":"2001.02522","title":"On Interpretability of Artificial Neural Networks: A Survey","created":"2020-01-08","cited_by_count":88},{"id":"1906.09777","title":"A Tensorized Transformer for Language Modeling","created":"2019-06-24","cited_by_count":86},{"id":"2008.05441","title":"Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network","created":"2020-08-12","cited_by_count":74},{"id":"2012.04030","title":"Statistical Mechanics of Deep Linear Neural Networks: The Back-Propagating Kernel Renormalization","created":"2020-12-07","cited_by_count":71},{"id":"2307.09542","title":"Can Neural Network Memorization Be Localized?","created":"2023-07-18","cited_by_count":69},{"id":"1901.02217","title":"Tree Tensor Networks for Generative Modeling","created":"2019-01-08","cited_by_count":64},{"id":"2411.07191","title":"The Super Weight in Large Language Models","created":"2024-11-11","cited_by_count":52},{"id":"1802.09052","title":"Wide Compression: Tensor Ring Nets","created":"2018-02-25","cited_by_count":50},{"id":"1710.04833","title":"Machine Learning by Unitary Tensor Network of Hierarchical Tree Structure","created":"2017-10-13","cited_by_count":40},{"id":"2302.09019","title":"Tensor Networks Meet Neural Networks: A Survey and Future Perspectives","created":"2023-01-22","cited_by_count":32},{"id":"2401.14109","title":"CompactifAI: Extreme Compression of Large Language Models using Quantum-Inspired Tensor Networks","created":"2024-01-25","cited_by_count":32},{"id":"1701.07148","title":"CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compression","created":"2017-01-25","cited_by_count":30},{"id":"1904.06194","title":"Compressing deep neural networks by matrix product operators","created":"2019-04-11","cited_by_count":28},{"id":"1905.10478","title":"Bayesian Tensorized Neural Networks with Automatic Rank Selection","created":"2019-05-24","cited_by_count":26},{"id":"1908.04471","title":"Einconv: Exploring Unexplored Tensor Network Decompositions for Convolutional Neural Networks","created":"2019-08-13","cited_by_count":25},{"id":"1808.05517","title":"Network Decoupling: From Regular to Depthwise Separable Convolutions","created":"2018-08-16","cited_by_count":18},{"id":"2303.11735","title":"Tensor networks for quantum machine learning","created":"2023-03-21","cited_by_count":17},{"id":"2305.19440","title":"Machine learning with tree tensor networks, CP rank constraints, and tensor dropout","created":"2023-05-30","cited_by_count":15},{"id":"2401.00867","title":"Tensor Networks for Explainable Machine Learning in Cybersecurity","created":"2023-12-29","cited_by_count":14},{"id":"2103.06872","title":"Tensor networks and efficient descriptions of classical data","created":"2021-03-11","cited_by_count":13},{"id":"2211.16749","title":"HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression","created":"2022-11-30","cited_by_count":9},{"id":"2503.04725","title":"L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling","created":"2025-03-06","cited_by_count":9},{"id":"2008.05437","title":"Adaptive Learning of Tensor Network Structures","created":"2020-08-12","cited_by_count":7},{"id":"2410.17397","title":"Quantum Large Language Models via Tensor Network Disentanglers","created":"2024-10-22","cited_by_count":7},{"id":"2007.00118","title":"Approximation Theory of Tree Tensor Networks: Tensorized Univariate Functions -- Part I","created":"2020-06-30","cited_by_count":6},{"id":"2108.04029","title":"Tensor Yard: One-Shot Algorithm of Hardware-Friendly Tensor-Train Decomposition for Convolutional Neural Networks","created":"2021-08-09","cited_by_count":3},{"id":"2401.01373","title":"Boosting Defect Detection in Manufacturing using Tensor Convolutional Neural Networks","created":"2023-12-29","cited_by_count":2},{"id":"2403.14379","title":"Tensor network compressibility of convolutional models","created":"2024-03-21","cited_by_count":2}],"next_cursor":null}