{"list":"other","total":72,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"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":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"1905.03222","title":"Conformalized Quantile Regression","created":"2019-05-08","cited_by_count":629},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"id":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414},{"id":"2003.06505","title":"AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data","created":"2020-03-13","cited_by_count":383},{"id":"1902.09635","title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","created":"2019-02-25","cited_by_count":344},{"id":"2402.17764","title":"The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits","created":"2024-02-27","cited_by_count":308},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263},{"id":"1902.07638","title":"Random Search and Reproducibility for Neural Architecture Search","created":"2019-02-20","cited_by_count":254},{"id":"2305.02997","title":"When Do Neural Nets Outperform Boosted Trees on Tabular Data?","created":"2023-05-04","cited_by_count":223},{"id":"1910.04732","title":"Structured Pruning of Large Language Models","created":"2019-10-10","cited_by_count":203},{"id":"1810.05934","title":"A System for Massively Parallel Hyperparameter Tuning","created":"2018-10-13","cited_by_count":202},{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186},{"id":"1901.11117","title":"The Evolved Transformer","created":"2019-01-30","cited_by_count":180},{"id":"2006.05078","title":"Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization","created":"2020-06-09","cited_by_count":179},{"id":"2007.04074","title":"Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning","created":"2020-07-08","cited_by_count":174},{"id":"2103.16378","title":"End-to-End Constrained Optimization Learning: A Survey","created":"2021-03-30","cited_by_count":157},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139},{"id":"2005.14187","title":"HAT: Hardware-Aware Transformers for Efficient Natural Language Processing","created":"2020-05-28","cited_by_count":136},{"id":"2004.03844","title":"On the Effect of Dropping Layers of Pre-trained Transformer Models","created":"2020-04-08","cited_by_count":118},{"id":"2312.11983","title":"Fluctuation-based Adaptive Structured Pruning for Large Language Models","created":"2023-12-19","cited_by_count":111},{"id":"1805.12168","title":"A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scalarizations","created":"2018-05-30","cited_by_count":99},{"id":"1809.04184","title":"Searching for Efficient Multi-Scale Architectures for Dense Image Prediction","created":"2018-09-11","cited_by_count":96},{"id":"2403.02181","title":"Not All Layers of LLMs Are Necessary During Inference","created":"2024-03-04","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":"2103.10584","title":"HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark","created":"2021-03-19","cited_by_count":84},{"id":"2402.02834","title":"Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods","created":"2024-02-05","cited_by_count":82},{"id":"2203.10705","title":"Compression of Generative Pre-trained Language Models via Quantization","created":"2022-03-21","cited_by_count":79},{"id":"2011.09588","title":"Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantification","created":"2020-11-18","cited_by_count":78},{"id":"2007.10396","title":"NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search","created":"2020-07-20","cited_by_count":76},{"id":"1912.12522","title":"NAS evaluation is frustratingly hard","created":"2019-12-28","cited_by_count":70},{"id":"2008.06120","title":"Can weight sharing outperform random architecture search? An investigation with TuNAS","created":"2020-08-13","cited_by_count":68},{"id":"2008.09777","title":"Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks","created":"2020-08-22","cited_by_count":67},{"id":"2011.09011","title":"AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling","created":"2020-11-18","cited_by_count":66},{"id":"2111.05754","title":"Prune Once for All: Sparse Pre-Trained Language Models","created":"2021-11-10","cited_by_count":66},{"id":"2001.10422","title":"NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search","created":"2020-01-28","cited_by_count":64},{"id":"2109.05472","title":"Compute and Energy Consumption Trends in Deep Learning Inference","created":"2021-09-12","cited_by_count":61},{"id":"2006.07116","title":"NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processing","created":"2020-06-12","cited_by_count":60},{"id":"2105.11871","title":"TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search","created":"2021-05-25","cited_by_count":58},{"id":"2207.12560","title":"AMLB: an AutoML Benchmark","created":"2022-07-25","cited_by_count":55},{"id":"2109.15082","title":"Towards Efficient Post-training Quantization of Pre-trained Language Models","created":"2021-09-30","cited_by_count":39},{"id":"2312.17244","title":"The LLM Surgeon","created":"2023-12-28","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":"2311.02971","title":"TabRepo: A Large Scale Repository of Tabular Model Evaluations and its AutoML Applications","created":"2023-11-06","cited_by_count":33},{"id":"2110.05668","title":"NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks","created":"2021-10-12","cited_by_count":32},{"id":"2108.01289","title":"AdvRush: Searching for Adversarially Robust Neural Architectures","created":"2021-08-03","cited_by_count":28},{"id":"2210.09943","title":"Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition","created":"2022-10-18","cited_by_count":26},{"id":"2106.12639","title":"Multi-objective Asynchronous Successive Halving","created":"2021-06-23","cited_by_count":23},{"id":"2111.03602","title":"NAS-Bench-x11 and the Power of Learning Curves","created":"2021-11-05","cited_by_count":20},{"id":"2106.05680","title":"A multi-objective perspective on jointly tuning hardware and hyperparameters","created":"2021-06-10","cited_by_count":12},{"id":"2403.05064","title":"Unsupervised Graph Neural Architecture Search with Disentangled Self-supervision","created":"2024-03-08","cited_by_count":5},{"id":"2405.02267","title":"Structural Pruning of Pre-trained Language Models via Neural Architecture Search","created":"2024-05-03","cited_by_count":5},{"id":"2305.08852","title":"Python Tool for Visualizing Variability of Pareto Fronts over Multiple Runs","created":"2023-05-15","cited_by_count":4}],"next_cursor":null}