{"total":5166,"rows":[{"id":"2210.02186","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","created":"2022-10-05","cited_by_count":1058,"area":null},{"id":"2310.11324","title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting","created":"2023-10-17","cited_by_count":817,"area":null},{"id":"2106.11959","title":"Revisiting Deep Learning Models for Tabular Data","created":"2021-06-22","cited_by_count":740,"area":null},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715,"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":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632,"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":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491,"area":null},{"id":"2112.10510","title":"Transformers Can Do Bayesian Inference","created":"2021-12-20","cited_by_count":360,"area":null},{"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":"2502.05564","title":"TabICL: A Tabular Foundation Model for In-Context Learning on Large Data","created":"2025-02-08","cited_by_count":289,"area":null},{"id":"2210.10723","title":"TabLLM: Few-shot Classification of Tabular Data with Large Language Models","created":"2022-10-19","cited_by_count":277,"area":null},{"id":"2403.20150","title":"TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods","created":"2024-03-29","cited_by_count":249,"area":null},{"id":"2206.09426","title":"ADBench: Anomaly Detection Benchmark","created":"2022-06-19","cited_by_count":232,"area":null},{"id":"2204.04662","title":"FOSTER: Feature Boosting and Compression for Class-Incremental Learning","created":"2022-04-10","cited_by_count":229,"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":"2301.09633","title":"Prediction-Powered Inference","created":"2023-01-23","cited_by_count":220,"area":null},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208,"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":"2306.15794","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","created":"2023-06-27","cited_by_count":194,"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":"2310.09656","title":"Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space","created":"2023-10-14","cited_by_count":186,"area":"diffusion"},{"id":"2402.17944","title":"Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey","created":"2024-02-27","cited_by_count":159,"area":null},{"id":"2107.10356","title":"Reading Race: AI Recognises Patient's Racial Identity In Medical Images","created":"2021-07-21","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":"2107.05847","title":"Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges","created":"2021-07-13","cited_by_count":145,"area":null},{"id":"2210.13701","title":"Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence","created":"2022-10-25","cited_by_count":144,"area":null},{"id":"2205.09328","title":"TransTab: Learning Transferable Tabular Transformers Across Tables","created":"2022-05-19","cited_by_count":132,"area":null},{"id":"2511.08667","title":"TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models","created":"2025-11-11","cited_by_count":132,"area":null},{"id":"2107.07436","title":"FastSHAP: Real-Time Shapley Value Estimation","created":"2021-07-15","cited_by_count":125,"area":null},{"id":"2311.01453","title":"PPI++: Efficient Prediction-Powered Inference","created":"2023-11-02","cited_by_count":117,"area":null},{"id":"2112.06409","title":"Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective","created":"2021-12-13","cited_by_count":116,"area":null},{"id":"2410.16032","title":"TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis","created":"2024-10-21","cited_by_count":116,"area":null},{"id":"2207.07605","title":"Algorithms to estimate Shapley value feature attributions","created":"2022-07-15","cited_by_count":115,"area":null},{"id":"2502.16681","title":"Are Sparse Autoencoders Useful? A Case Study in Sparse Probing","created":"2025-02-23","cited_by_count":115,"area":"mechinterp"},{"id":"2106.02584","title":"Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning","created":"2021-06-04","cited_by_count":113,"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":"2410.24210","title":"TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling","created":"2024-10-31","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":"2405.01147","title":"Why Tabular Foundation Models Should Be a Research Priority","created":"2024-05-02","cited_by_count":106,"area":null},{"id":"2110.04361","title":"SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning","created":"2021-10-08","cited_by_count":104,"area":null},{"id":"2104.12199","title":"Sampling Permutations for Shapley Value Estimation","created":"2021-04-25","cited_by_count":102,"area":null},{"id":"2304.05206","title":"The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting","created":"2023-04-11","cited_by_count":101,"area":null},{"id":"2107.00793","title":"The Causal-Neural Connection: Expressiveness, Learnability, and Inference","created":"2021-07-02","cited_by_count":98,"area":null},{"id":"2407.20060","title":"RelBench: A Benchmark for Deep Learning on Relational Databases","created":"2024-07-29","cited_by_count":96,"area":null},{"id":"2403.00131","title":"UniTS: A Unified Multi-Task Time Series Model","created":"2024-02-29","cited_by_count":94,"area":null},{"id":"2104.01177","title":"How Powerful are Performance Predictors in Neural Architecture Search?","created":"2021-04-02","cited_by_count":90,"area":null},{"id":"2401.17644","title":"BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems","created":"2024-01-31","cited_by_count":87,"area":"inference"},{"id":"2405.09783","title":"LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery","created":"2024-05-16","cited_by_count":86,"area":"lr"},{"id":"2305.06090","title":"XTab: Cross-table Pretraining for Tabular Transformers","created":"2023-05-10","cited_by_count":81,"area":null},{"id":"2404.09491","title":"Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning","created":"2024-04-15","cited_by_count":81,"area":null},{"id":"2210.13291","title":"NVIDIA FLARE: Federated Learning from Simulation to Real-World","created":"2022-10-24","cited_by_count":80,"area":null},{"id":"2303.06833","title":"Transformer-based Planning for Symbolic Regression","created":"2023-03-13","cited_by_count":79,"area":null},{"id":"2303.12799","title":"Time Series as Images: Vision Transformer for Irregularly Sampled Time Series","created":"2023-03-01","cited_by_count":79,"area":null},{"id":"2407.21124","title":"Zero Shot Health Trajectory Prediction Using Transformer","created":"2024-07-30","cited_by_count":77,"area":null},{"id":"2510.21204","title":"Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models","created":"2025-10-24","cited_by_count":77,"area":null},{"id":"2402.16785","title":"CARTE: Pretraining and Transfer for Tabular Learning","created":"2024-02-26","cited_by_count":76,"area":null},{"id":"2406.12031","title":"Large Scale Transfer Learning for Tabular Data via Language Modeling","created":"2024-06-17","cited_by_count":76,"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":"2406.09624","title":"DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks","created":"2024-06-13","cited_by_count":75,"area":null},{"id":"2307.14338","title":"TabR: Tabular Deep Learning Meets Nearest Neighbors in 2023","created":"2023-07-26","cited_by_count":74,"area":null},{"id":"2402.09205","title":"Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents","created":"2024-02-14","cited_by_count":74,"area":"agents"},{"id":"2305.17535","title":"PFNs4BO: In-Context Learning for Bayesian Optimization","created":"2023-05-27","cited_by_count":73,"area":null},{"id":"2102.03357","title":"Machine Learning for Electronic Design Automation: A Survey","created":"2021-01-10","cited_by_count":72,"area":null},{"id":"2202.06258","title":"Flowformer: Linearizing Transformers with Conservation Flows","created":"2022-02-13","cited_by_count":69,"area":null},{"id":"2203.00870","title":"Faith-Shap: The Faithful Shapley Interaction Index","created":"2022-03-02","cited_by_count":69,"area":null},{"id":"2402.03226","title":"FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion","created":"2024-02-05","cited_by_count":68,"area":"moe"},{"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":"2312.07577","title":"Benchmarking Distribution Shift in Tabular Data with TableShift","created":"2023-12-10","cited_by_count":66,"area":null},{"id":"2103.01907","title":"Fairness in Credit Scoring: Assessment, Implementation and Profit Implications","created":"2021-03-02","cited_by_count":65,"area":null},{"id":"2310.06213","title":"GeoLLM: Extracting Geospatial Knowledge from Large Language Models","created":"2023-10-10","cited_by_count":64,"area":null},{"id":"2402.01881","title":"Large Language Model Agent for Hyper-Parameter Optimization","created":"2024-02-02","cited_by_count":64,"area":"agents"},{"id":"2207.03579","title":"DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection","created":"2022-06-30","cited_by_count":63,"area":null},{"id":"2410.20626","title":"TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation","created":"2024-10-27","cited_by_count":63,"area":"diffusion"},{"id":"2106.00311","title":"What's a good imputation to predict with missing values?","created":"2021-06-01","cited_by_count":62,"area":null},{"id":"2209.04012","title":"From Shapley Values to Generalized Additive Models and back","created":"2022-09-08","cited_by_count":60,"area":null},{"id":"2405.09321","title":"ReconBoost: Boosting Can Achieve Modality Reconcilement","created":"2024-05-15","cited_by_count":60,"area":null},{"id":"2101.09864","title":"Applications of Deep Learning in Fundus Images: A Review","created":"2021-01-25","cited_by_count":59,"area":null},{"id":"2406.05207","title":"Retrieval & Fine-Tuning for In-Context Tabular Models","created":"2024-06-07","cited_by_count":59,"area":null},{"id":"2306.12251","title":"GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection","created":"2023-06-21","cited_by_count":58,"area":null},{"id":"2309.16598","title":"Cross-Prediction-Powered Inference","created":"2023-09-28","cited_by_count":58,"area":null},{"id":"2410.11802","title":"TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting","created":"2024-10-15","cited_by_count":58,"area":null},{"id":"2506.15692","title":"MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement","created":"2025-05-27","cited_by_count":58,"area":"agents"},{"id":"2304.14068","title":"Interpretable Neural-Symbolic Concept Reasoning","created":"2023-04-27","cited_by_count":57,"area":null},{"id":"2401.06091","title":"A Closer Look at AUROC and AUPRC under Class Imbalance","created":"2024-01-11","cited_by_count":57,"area":null},{"id":"2403.01841","title":"Making Pre-trained Language Models Great on Tabular Prediction","created":"2024-03-04","cited_by_count":57,"area":null},{"id":"2205.14120","title":"Neural Basis Models for Interpretability","created":"2022-05-27","cited_by_count":56,"area":null},{"id":"2312.04615","title":"Relational Deep Learning: Graph Representation Learning on Relational Databases","created":"2023-12-07","cited_by_count":56,"area":null},{"id":"2106.00641","title":"SpanNER: Named Entity Re-/Recognition as Span Prediction","created":"2021-06-01","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":"2102.07188","title":"Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces","created":"2021-02-14","cited_by_count":53,"area":null},{"id":"2206.15306","title":"Transfer Learning with Deep Tabular Models","created":"2022-06-30","cited_by_count":52,"area":null},{"id":"2211.12507","title":"OpenFE: Automated Feature Generation with Expert-level Performance","created":"2022-11-22","cited_by_count":52,"area":null},{"id":"2401.12970","title":"Raidar: geneRative AI Detection viA Rewriting","created":"2024-01-23","cited_by_count":52,"area":null},{"id":"2407.04057","title":"TALENT: A Tabular Analytics and Learning Toolbox","created":"2024-07-04","cited_by_count":52,"area":null},{"id":"2112.02962","title":"DANets: Deep Abstract Networks for Tabular Data Classification and Regression","created":"2021-12-06","cited_by_count":50,"area":null},{"id":"2112.03769","title":"Machine Learning in the Search for New Fundamental Physics","created":"2021-12-07","cited_by_count":50,"area":null},{"id":"2306.16424","title":"Realistic Synthetic Financial Transactions for Anti-Money Laundering Models","created":"2023-06-22","cited_by_count":50,"area":null},{"id":"2403.03208","title":"Active Statistical Inference","created":"2024-03-05","cited_by_count":50,"area":null}],"next_cursor":"100"}