{"total":36,"rows":[{"id":"2311.01933","title":"ForecastPFN: Synthetically-Trained Zero-Shot Forecasting","created":"2023-11-03","cited_by_count":104,"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":"2404.16795","title":"In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization","created":"2024-04-25","cited_by_count":26,"area":null},{"id":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2406.09334","title":"ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models","created":"2024-06-13","cited_by_count":20,"area":null},{"id":"2505.23947","title":"Position: The Future of Bayesian Prediction Is Prior-Fitted","created":"2025-05-29","cited_by_count":20,"area":null},{"id":"2410.09239","title":"Scaling Gaussian Processes for Learning Curve Prediction via Latent Kronecker Structure","created":"2024-10-11","cited_by_count":10,"area":null},{"id":"2410.01565","title":"Bayes' Power for Explaining In-Context Learning Generalizations","created":"2024-10-02","cited_by_count":8,"area":null},{"id":"2404.04111","title":"The Unreasonable Effectiveness Of Early Discarding After One Epoch In Neural Network Hyperparameter Optimization","created":"2024-04-05","cited_by_count":5,"area":null},{"id":"2412.15554","title":"Architecture-Aware Learning Curve Extrapolation via Graph Ordinary Differential Equation","created":"2024-12-20","cited_by_count":5,"area":null},{"id":"2407.15110","title":"Practical multi-fidelity machine learning: fusion of deterministic and Bayesian models","created":"2024-07-21","cited_by_count":4,"area":null},{"id":"2502.06684","title":"EquiTabPFN: A Target-Permutation Equivariant Prior Fitted Networks","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2405.17918","title":"Cost-Sensitive Multi-Fidelity Bayesian Optimization with Transfer of Learning Curve Extrapolation","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2508.10349","title":"FlexP-SFT: A Flexible Aggregation-Free Framework for On-Device Personalized Split Federated Fine-Tuning of LLMs","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2510.16743","title":"Zero-Shot Performance Prediction for Probabilistic Scaling Laws","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2510.21379","title":"Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2601.19831","title":"Neural Neural Scaling Laws","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2602.10300","title":"Configuration-to-Performance Scaling Law with Neural Ansatz","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2606.07134","title":"$\\alpha$-PFN: Fast Entropy Search via In-Context Learning","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2410.04560","title":"GAMformer: Bridging Tabular Foundation Models and Interpretable Machine Learning","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2502.03654","title":"Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2505.15657","title":"LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.23032","title":"Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2508.14818","title":"Successive Halving with Learning Curve Prediction via Latent Kronecker Gaussian Processes","created":"2025-08-20","cited_by_count":1,"area":null},{"id":"2509.20950","title":"Decoupled-Value Attention for Prior-Data Fitted Networks: GP Inference for Physical Equations","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2510.24318","title":"Transformers can do Bayesian Clustering","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2606.17660","title":"TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2609.11884","title":"CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search","created":"2026-09-10","cited_by_count":1,"area":null},{"id":"2410.07696","title":"Meta-Learning from Learning Curves for Budget-Limited Algorithm Selection","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2507.20369","title":"Clustering by Attention: Leveraging Prior Fitted Transformers for Data Partitioning","created":"2025-07-27","cited_by_count":0,"area":null},{"id":"2508.13657","title":"In-Context Decision Making for Optimizing Complex AutoML Pipelines","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2602.12082","title":"Empirical Gaussian Processes","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2602.12112","title":"Few-Shot Design Optimization by Exploiting Auxiliary Information","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2605.17234","title":"Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2609.05016","title":"Amortizing Scaling Law Construction Costs","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.12418","title":"RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Search","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}