{"total":62,"rows":[{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249,"area":null},{"id":"2206.07137","title":"Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt","created":"2022-06-14","cited_by_count":236,"area":null},{"id":"2204.08499","title":"DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning","created":"2022-04-18","cited_by_count":147,"area":null},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2107.03315","title":"Predicting with Confidence on Unseen Distributions","created":"2021-07-07","cited_by_count":116,"area":null},{"id":"2206.13089","title":"Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift","created":"2022-06-27","cited_by_count":94,"area":null},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75,"area":null},{"id":"2112.04660","title":"A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse","created":"2021-12-09","cited_by_count":53,"area":null},{"id":"2202.00395","title":"Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification","created":"2022-02-01","cited_by_count":26,"area":null},{"id":"2102.01065","title":"Do Question Answering Modeling Improvements Hold Across Benchmarks?","created":"2021-02-01","cited_by_count":20,"area":null},{"id":"2203.06498","title":"The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning","created":"2022-03-12","cited_by_count":17,"area":null},{"id":"2309.00570","title":"Mechanism of feature learning in convolutional neural networks","created":"2023-09-01","cited_by_count":17,"area":null},{"id":"2302.01381","title":"Effective Robustness against Natural Distribution Shifts for Models with Different Training Data","created":"2023-02-02","cited_by_count":13,"area":null},{"id":"2510.23191","title":"The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models","created":"2025-10-27","cited_by_count":13,"area":null},{"id":"2507.05195","title":"Train-before-Test Harmonizes Language Model Rankings","created":"2025-07-07","cited_by_count":12,"area":null},{"id":"2208.11870","title":"Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Data","created":"2022-08-25","cited_by_count":11,"area":null},{"id":"2209.10438","title":"A Measure of the Complexity of Neural Representations based on Partial Information Decomposition","created":"2022-09-21","cited_by_count":11,"area":null},{"id":"2311.13028","title":"DMLR: Data-centric Machine Learning Research -- Past, Present and Future","created":"2023-11-21","cited_by_count":11,"area":null},{"id":"2411.10023","title":"Model Inversion Attacks: A Survey of Approaches and Countermeasures","created":"2024-11-15","cited_by_count":11,"area":null},{"id":"2410.24100","title":"Benchmark Data Repositories for Better Benchmarking","created":"2024-10-31","cited_by_count":10,"area":null},{"id":"2107.02565","title":"Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version)","created":"2021-07-06","cited_by_count":7,"area":null},{"id":"2203.02711","title":"Meta Mirror Descent: Optimiser Learning for Fast Convergence","created":"2022-03-05","cited_by_count":7,"area":null},{"id":"2305.02995","title":"Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2401.04305","title":"Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions","created":"2024-01-09","cited_by_count":7,"area":null},{"id":"2404.01542","title":"Predicting the Performance of Foundation Models via Agreement-on-the-Line","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2505.18102","title":"CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2201.06648","title":"OmniPrint: A Configurable Printed Character Synthesizer","created":"2022-01-17","cited_by_count":5,"area":null},{"id":"2202.04052","title":"Decision boundaries and convex hulls in the feature space that deep learning functions learn from images","created":"2022-02-05","cited_by_count":5,"area":null},{"id":"2103.03574","title":"Extending Contrastive Learning to Unsupervised Coreset Selection","created":"2021-03-05","cited_by_count":4,"area":null},{"id":"2111.08014","title":"Tensor network to learn the wavefunction of data","created":"2021-11-15","cited_by_count":4,"area":null},{"id":"2203.03981","title":"End-to-end Multiple Instance Learning with Gradient Accumulation","created":"2022-03-08","cited_by_count":4,"area":null},{"id":"2304.05516","title":"Echo of Neighbors: Privacy Amplification for Personalized Private Federated Learning with Shuffle Model","created":"2023-04-11","cited_by_count":4,"area":null},{"id":"2111.05063","title":"Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search","created":"2021-11-09","cited_by_count":3,"area":null},{"id":"2408.10669","title":"Tensor tree learns hidden relational structures in data to construct generative models","created":"2024-08-20","cited_by_count":3,"area":null},{"id":"2603.08371","title":"Leaderboard Incentives: Model Rankings under Strategic Post-Training","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2210.11589","title":"Monotonic Risk Relationships under Distribution Shifts for Regularized Risk Minimization","created":"2022-10-20","cited_by_count":2,"area":null},{"id":"2407.06544","title":"Multiple Instance Verification","created":"2024-07-09","cited_by_count":2,"area":null},{"id":"2202.01783","title":"Oral cancer detection and interpretation: Deep multiple instance learning versus conventional deep single instance learning","created":"2022-02-03","cited_by_count":1,"area":null},{"id":"2304.11263","title":"Benchmarking Low-Shot Robustness to Natural Distribution Shifts","created":"2023-04-21","cited_by_count":1,"area":null},{"id":"2308.04137","title":"A Comprehensive Assessment Benchmark for Rigorously Evaluating Deep Learning Image Classifiers","created":"2023-08-08","cited_by_count":1,"area":null},{"id":"2312.03291","title":"Evaluation of human-model prediction difference on the Internet Scale of Data","created":"2023-12-06","cited_by_count":1,"area":null},{"id":"2411.06499","title":"Mitigating covariate shift in non-colocated data with learned parameter priors","created":"2024-11-10","cited_by_count":1,"area":null},{"id":"2506.11336","title":"The Sample Complexity of Parameter-Free Stochastic Convex Optimization","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2509.25933","title":"From MNIST to ImageNet: Understanding the Scalability Boundaries of Differentiable Logic Gate Networks","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2512.01881","title":"Unifying Sign and Magnitude for Optimizing Deep Vision Networks via ThermoLion","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2606.06335","title":"Bridging Domain Expertise and Generalization for Performance Estimation","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.27997","title":"Benchmarking on Tasks That Matter: Dataset Selection for Preserving Model Rankings","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2110.11736","title":"MANDERA: Malicious Node Detection in Federated Learning via Ranking","created":"2021-10-22","cited_by_count":0,"area":null},{"id":"2202.02278","title":"LTU Attacker for Membership Inference","created":"2022-02-04","cited_by_count":0,"area":"safety"},{"id":"2304.08855","title":"A Domain-Region Based Evaluation of ML Performance Robustness to Covariate Shift","created":"2023-04-18","cited_by_count":0,"area":null},{"id":"2310.09129","title":"Computing Marginal and Conditional Divergences between Decomposable Models with Applications","created":"2023-10-13","cited_by_count":0,"area":null},{"id":"2312.00268","title":"Academic competitions","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2405.03060","title":"Tree-based Ensemble Learning for Out-of-distribution Detection","created":"2024-05-05","cited_by_count":0,"area":null},{"id":"2406.13552","title":"Standardness Clouds Meaning: A Position Regarding the Informed Usage of Standard Datasets","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2410.08643","title":"SOAK: Same/Other/All K-fold cross-validation for estimating similarity of patterns in data subsets","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2508.21270","title":"Guess-and-Learn (G&L): Measuring the Cumulative Error Cost of Cold-Start Adaptation","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2510.03838","title":"Technical note on Fisher Information for Robust Federated Cross-Validation","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2510.09799","title":"Distributed clustering in partially overlapping feature spaces","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2512.00676","title":"Realistic Handwritten Multi-Digit Writer (MDW) Number Recognition Challenges","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2610.17722","title":"Representation Geometry and Inductive Biases in Quantum Classifiers across Classical Visual Benchmarks","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}