{"total":526,"rows":[{"id":"2106.11959","title":"Revisiting Deep Learning Models for Tabular Data","created":"2021-06-22","cited_by_count":740,"area":null},{"id":"2207.01848","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","created":"2022-07-05","cited_by_count":674,"area":null},{"id":"2106.03253","title":"Tabular Data: Deep Learning is Not All You Need","created":"2021-06-06","cited_by_count":535,"area":null},{"id":"2209.15421","title":"TabDDPM: Modelling Tabular Data with Diffusion Models","created":"2022-09-30","cited_by_count":377,"area":"diffusion"},{"id":"2106.01342","title":"SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training","created":"2021-06-02","cited_by_count":319,"area":null},{"id":"2305.02997","title":"When Do Neural Nets Outperform Boosted Trees on Tabular Data?","created":"2023-05-04","cited_by_count":223,"area":null},{"id":"2207.08815","title":"Why do tree-based models still outperform deep learning on tabular data?","created":"2022-07-18","cited_by_count":199,"area":null},{"id":"2203.05556","title":"On Embeddings for Numerical Features in Tabular Deep Learning","created":"2022-03-10","cited_by_count":186,"area":null},{"id":"2106.15147","title":"SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption","created":"2021-06-29","cited_by_count":156,"area":null},{"id":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151,"area":null},{"id":"2311.12424","title":"Looped Transformers are Better at Learning Learning Algorithms","created":"2023-11-21","cited_by_count":149,"area":null},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148,"area":null},{"id":"2107.05847","title":"Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges","created":"2021-07-13","cited_by_count":145,"area":null},{"id":"2305.03403","title":"Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering","created":"2023-05-05","cited_by_count":127,"area":null},{"id":"2410.18164","title":"TabDPT: Scaling Tabular Foundation Models on Real Data","created":"2024-10-23","cited_by_count":113,"area":null},{"id":"2109.06716","title":"HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO","created":"2021-09-14","cited_by_count":112,"area":null},{"id":"2211.10873","title":"Interpretable Scientific Discovery with Symbolic Regression: A Review","created":"2022-11-20","cited_by_count":105,"area":null},{"id":"2205.13320","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","created":"2022-05-26","cited_by_count":81,"area":null},{"id":"2403.19546","title":"Croissant: A Metadata Format for ML-Ready Datasets","created":"2024-03-28","cited_by_count":81,"area":null},{"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,"area":null},{"id":"2204.11051","title":"$\\pi$BO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization","created":"2022-04-23","cited_by_count":70,"area":null},{"id":"2109.02596","title":"Scikit-dimension: a Python package for intrinsic dimension estimation","created":"2021-09-06","cited_by_count":68,"area":null},{"id":"2110.05802","title":"Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platform","created":"2021-10-12","cited_by_count":66,"area":null},{"id":"2304.14979","title":"MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks","created":"2023-04-28","cited_by_count":66,"area":null},{"id":"2109.03670","title":"YAHPO Gym -- An Efficient Multi-Objective Multi-Fidelity Benchmark for Hyperparameter Optimization","created":"2021-09-08","cited_by_count":62,"area":null},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2206.04771","title":"Joint Entropy Search for Maximally-Informed Bayesian Optimization","created":"2022-06-09","cited_by_count":55,"area":null},{"id":"2207.12560","title":"AMLB: an AutoML Benchmark","created":"2022-07-25","cited_by_count":55,"area":null},{"id":"2305.09696","title":"Generative Table Pre-training Empowers Models for Tabular Prediction","created":"2023-05-16","cited_by_count":55,"area":null},{"id":"2306.10577","title":"OpenDataVal: a Unified Benchmark for Data Valuation","created":"2023-06-18","cited_by_count":55,"area":null},{"id":"2107.02237","title":"Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination","created":"2021-07-05","cited_by_count":53,"area":null},{"id":"2312.12112","title":"Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes","created":"2023-12-19","cited_by_count":52,"area":null},{"id":"2203.09410","title":"A Framework and Benchmark for Deep Batch Active Learning for Regression","created":"2022-03-17","cited_by_count":49,"area":null},{"id":"2303.00918","title":"STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables","created":"2023-03-02","cited_by_count":49,"area":null},{"id":"2402.11137","title":"TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks","created":"2024-02-17","cited_by_count":47,"area":null},{"id":"2207.03208","title":"Revisiting Pretraining Objectives for Tabular Deep Learning","created":"2022-07-07","cited_by_count":43,"area":null},{"id":"2111.02790","title":"LassoBench: A High-Dimensional Hyperparameter Optimization Benchmark Suite for Lasso","created":"2021-11-04","cited_by_count":41,"area":null},{"id":"2507.03971","title":"Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data","created":"2025-07-05","cited_by_count":41,"area":null},{"id":"2106.02029","title":"Off-Policy Evaluation via Adaptive Weighting with Data from Contextual Bandits","created":"2021-06-03","cited_by_count":40,"area":null},{"id":"2503.14434","title":"LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers","created":"2025-03-18","cited_by_count":38,"area":null},{"id":"2106.01350","title":"On Efficiently Explaining Graph-Based Classifiers","created":"2021-06-02","cited_by_count":37,"area":null},{"id":"2310.20447","title":"Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks","created":"2023-10-31","cited_by_count":37,"area":null},{"id":"2305.18446","title":"Trompt: Towards a Better Deep Neural Network for Tabular Data","created":"2023-05-29","cited_by_count":36,"area":null},{"id":"2404.06209","title":"Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models","created":"2024-04-09","cited_by_count":36,"area":null},{"id":"2111.04820","title":"Explaining Hyperparameter Optimization via Partial Dependence Plots","created":"2021-11-08","cited_by_count":35,"area":null},{"id":"2302.05738","title":"Cross-Modal Fine-Tuning: Align then Refine","created":"2023-02-11","cited_by_count":34,"area":null},{"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,"area":null},{"id":"2207.06503","title":"Randomly pivoted Cholesky: Practical approximation of a kernel matrix with few entry evaluations","created":"2022-07-13","cited_by_count":32,"area":null},{"id":"2111.02767","title":"RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning","created":"2021-11-04","cited_by_count":31,"area":"offlinerl"},{"id":"2302.08909","title":"Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification","created":"2023-02-16","cited_by_count":30,"area":null},{"id":"2407.03257","title":"Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later","created":"2024-07-03","cited_by_count":30,"area":null},{"id":"2305.08413","title":"Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward","created":"2023-05-15","cited_by_count":28,"area":null},{"id":"2407.05364","title":"PTaRL: Prototype-based Tabular Representation Learning via Space Calibration","created":"2024-07-07","cited_by_count":28,"area":null},{"id":"2206.13424","title":"Benchopt: Reproducible, efficient and collaborative optimization benchmarks","created":"2022-06-27","cited_by_count":27,"area":null},{"id":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2110.02376","title":"Foundations of Symbolic Languages for Model Interpretability","created":"2021-10-05","cited_by_count":26,"area":null},{"id":"2111.02705","title":"Benchmarking Multimodal AutoML for Tabular Data with Text Fields","created":"2021-11-04","cited_by_count":26,"area":null},{"id":"2107.08861","title":"VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition","created":"2021-07-19","cited_by_count":25,"area":null},{"id":"2111.05850","title":"Towards Green Automated Machine Learning: Status Quo and Future Directions","created":"2021-11-10","cited_by_count":25,"area":null},{"id":"2411.10634","title":"Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data","created":"2024-11-15","cited_by_count":25,"area":null},{"id":"2111.02508","title":"AlphaD3M: Machine Learning Pipeline Synthesis","created":"2021-11-03","cited_by_count":24,"area":null},{"id":"2208.14878","title":"Formalising the Robustness of Counterfactual Explanations for Neural Networks","created":"2022-08-31","cited_by_count":24,"area":null},{"id":"2410.20302","title":"Sequential Large Language Model-Based Hyper-parameter Optimization","created":"2024-10-27","cited_by_count":24,"area":null},{"id":"2203.10451","title":"On the Computation of Necessary and Sufficient Explanations","created":"2022-03-20","cited_by_count":23,"area":null},{"id":"2402.07198","title":"More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning","created":"2024-02-11","cited_by_count":23,"area":"offlinerl"},{"id":"2103.00083","title":"Flexible Model Aggregation for Quantile Regression","created":"2021-02-26","cited_by_count":22,"area":null},{"id":"2306.14101","title":"Language models are weak learners","created":"2023-06-25","cited_by_count":22,"area":null},{"id":"2104.00629","title":"Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features","created":"2021-04-01","cited_by_count":21,"area":null},{"id":"2105.02344","title":"Policy Learning with Adaptively Collected Data","created":"2021-05-05","cited_by_count":21,"area":null},{"id":"2310.18108","title":"Transductive conformal inference with adaptive scores","created":"2023-10-27","cited_by_count":21,"area":null},{"id":"2103.12906","title":"CSFCube -- A Test Collection of Computer Science Research Articles for Faceted Query by Example","created":"2021-03-24","cited_by_count":20,"area":null},{"id":"2106.06079","title":"A Nonmyopic Approach to Cost-Constrained Bayesian Optimization","created":"2021-06-10","cited_by_count":19,"area":null},{"id":"2202.12270","title":"Evaluating Feature Attribution Methods in the Image Domain","created":"2022-02-22","cited_by_count":19,"area":null},{"id":"2208.11111","title":"Integrative conformal p-values for powerful out-of-distribution testing with labeled outliers","created":"2022-08-23","cited_by_count":19,"area":null},{"id":"2211.09259","title":"The Missing Indicator Method: From Low to High Dimensions","created":"2022-11-16","cited_by_count":19,"area":null},{"id":"2403.06644","title":"Elephants Never Forget: Testing Language Models for Memorization of Tabular Data","created":"2024-03-11","cited_by_count":19,"area":null},{"id":"2405.02200","title":"Position: Why We Must Rethink Empirical Research in Machine Learning","created":"2024-05-03","cited_by_count":19,"area":null},{"id":"2105.05699","title":"Automating Data Science: Prospects and Challenges","created":"2021-05-12","cited_by_count":18,"area":null},{"id":"2211.11747","title":"NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research","created":"2022-11-15","cited_by_count":18,"area":null},{"id":"2505.18125","title":"TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fields","created":"2025-05-23","cited_by_count":18,"area":null},{"id":"2102.12810","title":"Hyperparameter Transfer Learning with Adaptive Complexity","created":"2021-02-25","cited_by_count":17,"area":null},{"id":"2203.03094","title":"SurvSet: An open-source time-to-event dataset repository","created":"2022-03-07","cited_by_count":17,"area":null},{"id":"2312.06564","title":"Promoting Counterfactual Robustness through Diversity","created":"2023-12-11","cited_by_count":17,"area":null},{"id":"2401.12406","title":"Enhancing In-context Learning via Linear Probe Calibration","created":"2024-01-22","cited_by_count":16,"area":"mechinterp"},{"id":"2405.15821","title":"Reinforcing Language Agents via Policy Optimization with Action Decomposition","created":"2024-05-23","cited_by_count":16,"area":"agents"},{"id":"2508.10053","title":"xRFM: Accurate, scalable, and interpretable feature learning models for tabular data","created":"2025-08-12","cited_by_count":16,"area":null},{"id":"2111.13914","title":"Fast and Informative Model Selection using Learning Curve Cross-Validation","created":"2021-11-27","cited_by_count":15,"area":null},{"id":"2112.14718","title":"Shallow decision trees for explainable $k$-means clustering","created":"2021-12-29","cited_by_count":15,"area":null},{"id":"2306.07923","title":"Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits","created":"2023-06-13","cited_by_count":15,"area":"offlinerl"},{"id":"2408.14817","title":"A Comprehensive Benchmark of Machine and Deep Learning Across Diverse Tabular Datasets","created":"2024-08-27","cited_by_count":15,"area":null},{"id":"2412.07507","title":"ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning","created":"2024-12-10","cited_by_count":15,"area":"deeprl"},{"id":"2506.05584","title":"TabFlex: Scaling Tabular Learning to Millions with Linear Attention","created":"2025-06-05","cited_by_count":15,"area":null},{"id":"2112.08524","title":"FLoRA: Single-shot Hyper-parameter Optimization for Federated Learning","created":"2021-12-15","cited_by_count":14,"area":null},{"id":"2403.11395","title":"Automated data processing and feature engineering for deep learning and big data applications: a survey","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2410.05016","title":"T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data","created":"2024-10-07","cited_by_count":14,"area":null},{"id":"2103.16700","title":"Trees, Forests, Chickens, and Eggs: When and Why to Prune Trees in a Random Forest","created":"2021-03-30","cited_by_count":13,"area":null},{"id":"2201.06834","title":"Hyper-Tune: Towards Efficient Hyper-parameter Tuning at Scale","created":"2022-01-18","cited_by_count":13,"area":null},{"id":"2206.02511","title":"Transfer Learning based Search Space Design for Hyperparameter Tuning","created":"2022-06-06","cited_by_count":13,"area":null},{"id":"2212.02934","title":"Yggdrasil Decision Forests: A Fast and Extensible Decision Forests Library","created":"2022-12-06","cited_by_count":13,"area":null},{"id":"2103.15147","title":"Symbolic regression outperforms other models for small data sets","created":"2021-03-28","cited_by_count":12,"area":null}],"next_cursor":"100"}