{"total":205,"rows":[{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795,"area":null},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"area":null},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621,"area":null},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235,"area":null},{"id":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222,"area":null},{"id":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142,"area":null},{"id":"2105.03818","title":"Heterogeneous Risk Minimization","created":"2021-05-09","cited_by_count":90,"area":null},{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86,"area":"inference"},{"id":"2402.09997","title":"LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild","created":"2024-02-15","cited_by_count":68,"area":null},{"id":"2104.08247","title":"What to Pre-Train on? Efficient Intermediate Task Selection","created":"2021-04-16","cited_by_count":63,"area":null},{"id":"2103.13843","title":"OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations","created":"2021-03-25","cited_by_count":62,"area":null},{"id":"2206.03996","title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","created":"2022-06-08","cited_by_count":58,"area":null},{"id":"2205.13452","title":"Continual evaluation for lifelong learning: Identifying the stability gap","created":"2022-05-26","cited_by_count":56,"area":null},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52,"area":null},{"id":"2205.08303","title":"MulT: An End-to-End Multitask Learning Transformer","created":"2022-05-17","cited_by_count":48,"area":null},{"id":"2106.09362","title":"Frustratingly Easy Transferability Estimation","created":"2021-06-17","cited_by_count":45,"area":null},{"id":"2408.14608","title":"Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold","created":"2024-08-26","cited_by_count":43,"area":"diffusion"},{"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":"2111.06977","title":"Scalable Diverse Model Selection for Accessible Transfer Learning","created":"2021-11-12","cited_by_count":40,"area":null},{"id":"2304.14381","title":"$\\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation","created":"2023-04-27","cited_by_count":40,"area":null},{"id":"2210.16559","title":"Few-shot Image Generation via Adaptation-Aware Kernel Modulation","created":"2022-10-29","cited_by_count":33,"area":null},{"id":"2103.01439","title":"Fast Adaptation with Linearized Neural Networks","created":"2021-03-02","cited_by_count":32,"area":null},{"id":"2306.03900","title":"Model Spider: Learning to Rank Pre-Trained Models Efficiently","created":"2023-06-06","cited_by_count":32,"area":null},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2112.00054","title":"Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data","created":"2021-11-30","cited_by_count":26,"area":"synth"},{"id":"2208.11726","title":"Wasserstein Task Embedding for Measuring Task Similarities","created":"2022-08-24","cited_by_count":25,"area":null},{"id":"2110.08329","title":"Control Prefixes for Parameter-Efficient Text Generation","created":"2021-10-15","cited_by_count":24,"area":null},{"id":"2310.16484","title":"Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training","created":"2023-10-25","cited_by_count":23,"area":null},{"id":"2304.07574","title":"Exploring Incompatible Knowledge Transfer in Few-shot Image Generation","created":"2023-04-15","cited_by_count":19,"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":"2204.11117","title":"Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning","created":"2022-04-23","cited_by_count":17,"area":null},{"id":"2403.08370","title":"SMART: Submodular Data Mixture Strategy for Instruction Tuning","created":"2024-03-13","cited_by_count":17,"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":"2204.05133","title":"On the link between conscious function and general intelligence in humans and machines","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2303.01256","title":"Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance","created":"2023-03-02","cited_by_count":16,"area":null},{"id":"2503.17940","title":"FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation","created":"2025-03-23","cited_by_count":16,"area":null},{"id":"2206.04486","title":"Data-Efficient Brain Connectome Analysis via Multi-Task Meta-Learning","created":"2022-06-09","cited_by_count":15,"area":null},{"id":"2207.05510","title":"Transferability-Guided Cross-Domain Cross-Task Transfer Learning","created":"2022-07-12","cited_by_count":14,"area":null},{"id":"2308.12372","title":"Vision Transformer Adapters for Generalizable Multitask Learning","created":"2023-08-23","cited_by_count":14,"area":null},{"id":"2406.16989","title":"Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning","created":"2024-06-24","cited_by_count":14,"area":"rag"},{"id":"2507.18807","title":"Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator","created":"2025-07-24","cited_by_count":14,"area":null},{"id":"2112.04895","title":"Latent Space Explanation by Intervention","created":"2021-12-09","cited_by_count":13,"area":null},{"id":"2203.03059","title":"Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?","created":"2022-03-06","cited_by_count":13,"area":null},{"id":"2402.15231","title":"Which Model to Transfer? A Survey on Transferability Estimation","created":"2024-02-23","cited_by_count":13,"area":null},{"id":"2404.02415","title":"What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases","created":"2024-04-03","cited_by_count":13,"area":"mllm"},{"id":"2103.04032","title":"CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks","created":"2021-03-06","cited_by_count":12,"area":null},{"id":"2205.12701","title":"Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts","created":"2022-05-25","cited_by_count":12,"area":"moe"},{"id":"2405.05588","title":"Model Inversion Robustness: Can Transfer Learning Help?","created":"2024-05-09","cited_by_count":12,"area":null},{"id":"2303.13251","title":"A Bag-of-Prototypes Representation for Dataset-Level Applications","created":"2023-03-23","cited_by_count":11,"area":null},{"id":"2305.13256","title":"TaskWeb: Selecting Better Source Tasks for Multi-task NLP","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2307.00823","title":"Understanding the Transferability of Representations via Task-Relatedness","created":"2023-07-03","cited_by_count":11,"area":null},{"id":"2308.15074","title":"Exploring Model Transferability through the Lens of Potential Energy","created":"2023-08-29","cited_by_count":11,"area":null},{"id":"2206.08138","title":"Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification","created":"2022-06-15","cited_by_count":10,"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":"2311.01075","title":"Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2501.18901","title":"Lightspeed Geometric Dataset Distance via Sliced Optimal Transport","created":"2025-01-31","cited_by_count":10,"area":null},{"id":"2204.05941","title":"Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search","created":"2022-04-12","cited_by_count":9,"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":"2308.05986","title":"Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variance","created":"2023-08-11","cited_by_count":9,"area":null},{"id":"2110.02399","title":"Task Affinity with Maximum Bipartite Matching in Few-Shot Learning","created":"2021-10-05","cited_by_count":8,"area":null},{"id":"2201.11576","title":"Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation","created":"2022-01-27","cited_by_count":8,"area":null},{"id":"2210.06989","title":"Multi-Task Meta Learning: learn how to adapt to unseen tasks","created":"2022-10-13","cited_by_count":8,"area":null},{"id":"2302.11709","title":"Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes","created":"2023-02-23","cited_by_count":8,"area":null},{"id":"2303.07669","title":"AutoTransfer: AutoML with Knowledge Transfer -- An Application to Graph Neural Networks","created":"2023-03-14","cited_by_count":8,"area":null},{"id":"2308.02408","title":"Evaluating the structure of cognitive tasks with transfer learning","created":"2023-07-28","cited_by_count":8,"area":null},{"id":"2310.18713","title":"Episodic Multi-Task Learning with Heterogeneous Neural Processes","created":"2023-10-28","cited_by_count":8,"area":null},{"id":"2310.19297","title":"On Measuring Fairness in Generative Models","created":"2023-10-30","cited_by_count":8,"area":null},{"id":"2101.11201","title":"Similarity of Classification Tasks","created":"2021-01-27","cited_by_count":7,"area":null},{"id":"2103.12827","title":"Fisher Task Distance and Its Application in Neural Architecture Search","created":"2021-03-23","cited_by_count":7,"area":null},{"id":"2210.11705","title":"Efficiently Tuned Parameters are Task Embeddings","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2210.17011","title":"A picture of the space of typical learnable tasks","created":"2022-10-31","cited_by_count":7,"area":null},{"id":"2101.11058","title":"Supervised Momentum Contrastive Learning for Few-Shot Classification","created":"2021-01-26","cited_by_count":6,"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":"2108.03434","title":"NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Models","created":"2021-08-07","cited_by_count":6,"area":null},{"id":"2201.10899","title":"Speeding up Heterogeneous Federated Learning with Sequentially Trained Superclients","created":"2022-01-26","cited_by_count":6,"area":null},{"id":"2211.05980","title":"Hardness-guided domain adaptation to recognise biomedical named entities under low-resource scenarios","created":"2022-11-11","cited_by_count":6,"area":null},{"id":"2306.13841","title":"Is Pre-training Truly Better Than Meta-Learning?","created":"2023-06-24","cited_by_count":6,"area":null},{"id":"2601.21795","title":"Effective LoRA Adapter Routing using Task Representations","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2107.08039","title":"Representation Consolidation for Training Expert Students","created":"2021-07-16","cited_by_count":5,"area":"distill"},{"id":"2202.01671","title":"Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets","created":"2022-02-03","cited_by_count":5,"area":null},{"id":"2202.01944","title":"Learning Representation from Neural Fisher Kernel with Low-rank Approximation","created":"2022-02-04","cited_by_count":5,"area":null},{"id":"2206.03950","title":"Transfer learning to decode brain states reflecting the relationship between cognitive tasks","created":"2022-06-07","cited_by_count":5,"area":null},{"id":"2210.01422","title":"Time-Varying Propensity Score to Bridge the Gap between the Past and Present","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2309.11013","title":"ModelGiF: Gradient Fields for Model Functional Distance","created":"2023-09-20","cited_by_count":5,"area":null},{"id":"2312.00656","title":"Simple Transferability Estimation for Regression Tasks","created":"2023-12-01","cited_by_count":5,"area":null},{"id":"2412.16364","title":"A High-Quality Text-Rich Image Instruction Tuning Dataset via Hybrid Instruction Generation","created":"2024-12-20","cited_by_count":5,"area":"mllm"},{"id":"2502.06544","title":"Sequence Transferability and Task Order Selection in Continual Learning","created":"2025-02-10","cited_by_count":5,"area":null},{"id":"2510.04564","title":"Conditional Representation Learning for Customized Tasks","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2601.23068","title":"ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2106.04802","title":"Probabilistic task modelling for meta-learning","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2106.09179","title":"Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation","created":"2021-06-17","cited_by_count":4,"area":null},{"id":"2107.04533","title":"Behavior Self-Organization Supports Task Inference for Continual Robot Learning","created":"2021-07-09","cited_by_count":4,"area":null},{"id":"2203.08399","title":"Privacy-preserving Online AutoML for Domain-Specific Face Detection","created":"2022-03-16","cited_by_count":4,"area":null},{"id":"2206.09386","title":"Scalable Neural Data Server: A Data Recommender for Transfer Learning","created":"2022-06-19","cited_by_count":4,"area":"moe"},{"id":"2302.11774","title":"Semantic-Fused Multi-Granularity Cross-City Traffic Prediction","created":"2023-02-23","cited_by_count":4,"area":null},{"id":"2304.12314","title":"Distilling from Similar Tasks for Transfer Learning on a Budget","created":"2023-04-24","cited_by_count":4,"area":null},{"id":"2404.18773","title":"A Universal Metric of Dataset Similarity for Cross-silo Federated Learning","created":"2024-04-29","cited_by_count":4,"area":null},{"id":"2406.06441","title":"Interpretability of Language Models via Task Spaces","created":"2024-06-10","cited_by_count":4,"area":"mechinterp"},{"id":"2410.07172","title":"Glider: Global and Local Instruction-Driven Expert Router","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2507.03175","title":"Understanding Knowledge Transferability for Transfer Learning: A Survey","created":"2025-07-03","cited_by_count":4,"area":null}],"next_cursor":"100"}