{"total":24,"rows":[{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2312.04528","title":"Using Large Language Models for Hyperparameter Optimization","created":"2023-12-07","cited_by_count":71,"area":null},{"id":"2308.00788","title":"An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning","created":"2023-08-01","cited_by_count":41,"area":null},{"id":"2207.02849","title":"Betty: An Automatic Differentiation Library for Multilevel Optimization","created":"2022-07-05","cited_by_count":27,"area":null},{"id":"2207.11719","title":"Gradient-based Bi-level Optimization for Deep Learning: A Survey","created":"2022-07-24","cited_by_count":26,"area":null},{"id":"2410.03735","title":"Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2207.07875","title":"On the Importance of Hyperparameters and Data Augmentation for Self-Supervised Learning","created":"2022-07-16","cited_by_count":16,"area":null},{"id":"2307.10923","title":"Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series","created":"2023-07-20","cited_by_count":16,"area":null},{"id":"2204.04360","title":"Data Augmentation for Electrocardiograms","created":"2022-04-09","cited_by_count":12,"area":null},{"id":"2212.00261","title":"Task Discovery: Finding the Tasks that Neural Networks Generalize on","created":"2022-12-01","cited_by_count":9,"area":null},{"id":"2112.14570","title":"Lyapunov Exponents for Diversity in Differentiable Games","created":"2021-12-24","cited_by_count":8,"area":null},{"id":"2208.12754","title":"Task Selection for AutoML System Evaluation","created":"2022-08-26","cited_by_count":7,"area":null},{"id":"2408.13237","title":"JacNet: Learning Functions with Structured Jacobians","created":"2024-08-23","cited_by_count":7,"area":null},{"id":"2312.11835","title":"Provably Convergent Federated Trilevel Learning","created":"2023-12-19","cited_by_count":6,"area":null},{"id":"2406.18630","title":"Improving Hyperparameter Optimization with Checkpointed Model Weights","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2601.08828","title":"Motion Attribution for Video Generation","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2508.02189","title":"Learning Dynamics of Meta-Learning in Small Model Pretraining","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2509.02160","title":"Meta-Pretraining for Zero-Shot Cross-Lingual Named Entity Recognition in Low-Resource Philippine Languages","created":"2025-09-02","cited_by_count":3,"area":null},{"id":"2209.04683","title":"Simple and Effective Gradient-Based Tuning of Sequence-to-Sequence Models","created":"2022-09-10","cited_by_count":2,"area":null},{"id":"2306.06082","title":"Augmentation-aware Self-supervised Learning with Conditioned Projector","created":"2023-05-31","cited_by_count":2,"area":null},{"id":"2203.04311","title":"Cluster Head Detection for Hierarchical UAV Swarm With Graph Self-supervised Learning","created":"2022-03-08","cited_by_count":1,"area":null},{"id":"2410.10006","title":"TapWeight: Reweighting Pretraining Objectives for Task-Adaptive Pretraining","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2207.08304","title":"HyperInvariances: Amortizing Invariance Learning","created":"2022-07-17","cited_by_count":0,"area":null},{"id":"2511.06774","title":"Bilevel Learning via Inexact Stochastic Gradient Descent","created":"2025-11-10","cited_by_count":0,"area":null}],"next_cursor":null}