{"list":"other","total":51,"rows":[{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551},{"id":"1902.09635","title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","created":"2019-02-25","cited_by_count":344},{"id":"2003.12206","title":"Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)","created":"2020-03-27","cited_by_count":322},{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236},{"id":"2109.09831","title":"SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization","created":"2021-09-20","cited_by_count":230},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229},{"id":"2103.03098","title":"Accounting for Variance in Machine Learning Benchmarks","created":"2021-03-01","cited_by_count":201},{"id":"1708.03731","title":"OpenML Benchmarking Suites","created":"2017-08-11","cited_by_count":178},{"id":"2107.05847","title":"Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges","created":"2021-07-13","cited_by_count":145},{"id":"1603.08785","title":"COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting","created":"2016-03-29","cited_by_count":138},{"id":"1605.07079","title":"Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets","created":"2016-05-23","cited_by_count":132},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115},{"id":"2109.06716","title":"HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO","created":"2021-09-14","cited_by_count":112},{"id":"1807.03341","title":"Troubling Trends in Machine Learning Scholarship","created":"2018-07-09","cited_by_count":108},{"id":"1401.3492","title":"ParamILS: An Automatic Algorithm Configuration Framework","created":"2014-01-15","cited_by_count":89},{"id":"2106.06257","title":"HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenML","created":"2021-06-11","cited_by_count":75},{"id":"2402.18041","title":"Datasets for Large Language Models: A Comprehensive Survey","created":"2024-02-28","cited_by_count":71},{"id":"2109.03670","title":"YAHPO Gym -- An Efficient Multi-Objective Multi-Fidelity Benchmark for Hyperparameter Optimization","created":"2021-09-08","cited_by_count":62},{"id":"2205.02894","title":"Interactive Model Cards: A Human-Centered Approach to Model Documentation","created":"2022-05-05","cited_by_count":61},{"id":"2207.12560","title":"AMLB: an AutoML Benchmark","created":"2022-07-25","cited_by_count":55},{"id":"1909.02453","title":"Best Practices for Scientific Research on Neural Architecture Search","created":"2019-09-05","cited_by_count":54},{"id":"2504.09737","title":"Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025","created":"2025-04-13","cited_by_count":47},{"id":"2205.13881","title":"Automated Dynamic Algorithm Configuration","created":"2022-05-27","cited_by_count":39},{"id":"2007.03488","title":"Benchmarking in Optimization: Best Practice and Open Issues","created":"2020-07-07","cited_by_count":38},{"id":"1506.02465","title":"ASlib: A Benchmark Library for Algorithm Selection","created":"2015-06-08","cited_by_count":37},{"id":"2006.16958","title":"Evaluating the Performance of Reinforcement Learning Algorithms","created":"2020-06-30","cited_by_count":36},{"id":"2201.13396","title":"NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy","created":"2022-01-31","cited_by_count":36},{"id":"2202.01651","title":"A Survey of Methods for Automated Algorithm Configuration","created":"2022-02-03","cited_by_count":30},{"id":"1810.05281","title":"IOHprofiler: A Benchmarking and Profiling Tool for Iterative Optimization Heuristics","created":"2018-10-11","cited_by_count":28},{"id":"2105.08541","title":"DACBench: A Benchmark Library for Dynamic Algorithm Configuration","created":"2021-05-18","cited_by_count":28},{"id":"1705.06058","title":"Pitfalls and Best Practices in Algorithm Configuration","created":"2017-05-17","cited_by_count":25},{"id":"2407.21530","title":"Data Contamination Report from the 2024 CONDA Shared Task","created":"2024-07-31","cited_by_count":20},{"id":"2405.02200","title":"Position: Why We Must Rethink Empirical Research in Machine Learning","created":"2024-05-03","cited_by_count":19},{"id":"2206.03493","title":"DeepCAVE: An Interactive Analysis Tool for Automated Machine Learning","created":"2022-06-07","cited_by_count":14},{"id":"2102.03380","title":"Reproducibility in Evolutionary Computation","created":"2021-02-05","cited_by_count":13},{"id":"2308.07832","title":"REFORMS: Reporting Standards for Machine Learning Based Science","created":"2023-08-15","cited_by_count":13},{"id":"2311.18807","title":"Pre-registration for Predictive Modeling","created":"2023-11-30","cited_by_count":13},{"id":"1811.09409","title":"Learning Multiple Defaults for Machine Learning Algorithms","created":"2018-11-23","cited_by_count":10},{"id":"2208.00220","title":"HPO X ELA: Investigating Hyperparameter Optimization Landscapes by Means of Exploratory Landscape Analysis","created":"2022-07-30","cited_by_count":10},{"id":"2104.11889","title":"OPTION: OPTImization Algorithm Benchmarking ONtology","created":"2021-04-24","cited_by_count":9},{"id":"2503.09159","title":"Unreflected Use of Tabular Data Repositories Can Undermine Research Quality","created":"2025-03-12","cited_by_count":9},{"id":"2202.11954","title":"XAutoML: A Visual Analytics Tool for Understanding and Validating Automated Machine Learning","created":"2022-02-24","cited_by_count":8},{"id":"2402.09800","title":"Large-scale Benchmarking of Metaphor-based Optimization Heuristics","created":"2024-02-15","cited_by_count":8},{"id":"2506.19540","title":"Overtuning in Hyperparameter Optimization","created":"2025-06-24","cited_by_count":5},{"id":"2505.07750","title":"The Pitfalls of Benchmarking in Algorithm Selection: What We Are Getting Wrong","created":"2025-05-12","cited_by_count":3},{"id":"2506.06143","title":"carps: A Framework for Comparing N Hyperparameter Optimizers on M Benchmarks","created":"2025-06-06","cited_by_count":3},{"id":"1803.09785","title":"Algorithm Configuration: Learning policies for the quick termination of poor performers","created":"2018-03-26","cited_by_count":1}],"next_cursor":null}