{"total":33,"rows":[{"id":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222,"area":null},{"id":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63,"area":null},{"id":"2211.14343","title":"Less Data, More Knowledge: Building Next Generation Semantic Communication Networks","created":"2022-11-25","cited_by_count":62,"area":null},{"id":"2102.00084","title":"A linearized framework and a new benchmark for model selection for fine-tuning","created":"2021-01-29","cited_by_count":41,"area":null},{"id":"2106.05418","title":"Probing transfer learning with a model of synthetic correlated datasets","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2306.13840","title":"Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2502.11986","title":"Selective Task Group Updates for Multi-Task Optimization","created":"2025-02-17","cited_by_count":17,"area":null},{"id":"2208.01545","title":"The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence","created":"2022-08-02","cited_by_count":10,"area":null},{"id":"2305.00152","title":"Limits of Model Selection under Transfer Learning","created":"2023-04-29","cited_by_count":9,"area":null},{"id":"2305.01034","title":"Model-agnostic Measure of Generalization Difficulty","created":"2023-05-01","cited_by_count":7,"area":null},{"id":"2107.03949","title":"Task Fingerprinting for Meta Learning in Biomedical Image Analysis","created":"2021-07-08","cited_by_count":6,"area":null},{"id":"2203.08764","title":"X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2204.08324","title":"Hierarchical Optimal Transport for Comparing Histopathology Datasets","created":"2022-04-18","cited_by_count":6,"area":null},{"id":"2509.22445","title":"Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2207.12186","title":"On the Learnability of Physical Concepts: Can a Neural Network Understand What's Real?","created":"2022-07-25","cited_by_count":5,"area":null},{"id":"2211.00372","title":"Meta-Learning for Unsupervised Outlier Detection with Optimal Transport","created":"2022-11-01","cited_by_count":5,"area":null},{"id":"2310.16241","title":"Task Grouping for Automated Multi-Task Machine Learning via Task Affinity Prediction","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2212.09071","title":"Disentangling Learnable and Memorizable Data via Contrastive Learning for Semantic Communications","created":"2022-12-18","cited_by_count":3,"area":null},{"id":"2303.04338","title":"Provable Pathways: Learning Multiple Tasks over Multiple Paths","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2503.21419","title":"Neuroplasticity in Artificial Intelligence -- An Overview and Inspirations on Drop In & Out Learning","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2305.08126","title":"Semantic Communication of Learnable Concepts","created":"2023-05-14","cited_by_count":2,"area":null},{"id":"2412.08763","title":"Beyond Knowledge Silos: Task Fingerprinting for Democratization of Medical Imaging AI","created":"2024-12-11","cited_by_count":2,"area":null},{"id":"2505.21438","title":"Measuring Fine-Grained Relatedness in Multitask Learning via Data Attribution","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2509.05130","title":"The Advantage of Fine-Grained Training","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2511.15002","title":"Task Specific Sharpness Aware O-RAN Resource Management using Multi Agent Reinforcement Learning","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2512.24991","title":"Efficiently Estimating Data Efficiency for Language Model Fine-tuning","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2112.13121","title":"The Curse of Zero Task Diversity: On the Failure of Transfer Learning to Outperform MAML and their Empirical Equivalence","created":"2021-12-24","cited_by_count":0,"area":null},{"id":"2310.03865","title":"Model Complexity of Program Phases","created":"2023-10-05","cited_by_count":0,"area":null},{"id":"2407.11286","title":"CLAMS: A System for Zero-Shot Model Selection for Clustering","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2410.11366","title":"LargePiG: Your Large Language Model is Secretly a Pointer Generator","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2602.18591","title":"Ensemble Prediction of Task Affinity for Efficient Multi-Task Learning","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2605.12906","title":"Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2610.12737","title":"Kernelized Parameter Sensitivity Atlases for Amortized Conditional Interpretability","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}