{"total":99,"rows":[{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739,"area":null},{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252,"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":"2105.03790","title":"Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study","created":"2021-05-08","cited_by_count":168,"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":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121,"area":null},{"id":"2209.15240","title":"Universal Prompt Tuning for Graph Neural Networks","created":"2022-09-30","cited_by_count":100,"area":null},{"id":"2202.14037","title":"Understanding Contrastive Learning Requires Incorporating Inductive Biases","created":"2022-02-28","cited_by_count":96,"area":null},{"id":"2211.08073","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","created":"2022-11-15","cited_by_count":72,"area":null},{"id":"2203.00759","title":"HyperPrompt: Prompt-based Task-Conditioning of Transformers","created":"2022-03-01","cited_by_count":67,"area":null},{"id":"2310.00035","title":"LoRA ensembles for large language model fine-tuning","created":"2023-09-29","cited_by_count":67,"area":null},{"id":"2401.01219","title":"Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond","created":"2024-01-02","cited_by_count":60,"area":null},{"id":"2308.13985","title":"Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective","created":"2023-08-27","cited_by_count":51,"area":null},{"id":"2111.04578","title":"Improved Regularization and Robustness for Fine-tuning in Neural Networks","created":"2021-11-08","cited_by_count":45,"area":null},{"id":"2312.03731","title":"MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs","created":"2023-11-28","cited_by_count":40,"area":null},{"id":"2205.12673","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","created":"2022-05-25","cited_by_count":39,"area":null},{"id":"2204.04541","title":"KOBEST: Korean Balanced Evaluation of Significant Tasks","created":"2022-04-09","cited_by_count":37,"area":null},{"id":"2303.10720","title":"Trainable Projected Gradient Method for Robust Fine-tuning","created":"2023-03-19","cited_by_count":37,"area":null},{"id":"2106.02705","title":"Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning","created":"2021-06-04","cited_by_count":34,"area":null},{"id":"2202.05250","title":"Adaptive and Robust Multi-Task Learning","created":"2022-02-10","cited_by_count":34,"area":null},{"id":"2206.02659","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees","created":"2022-06-06","cited_by_count":34,"area":null},{"id":"2205.09797","title":"Improving Multi-Task Generalization via Regularizing Spurious Correlation","created":"2022-05-19","cited_by_count":28,"area":null},{"id":"2212.00926","title":"Fair Generative Models via Transfer Learning","created":"2022-12-02","cited_by_count":27,"area":null},{"id":"2303.14582","title":"Identification of Negative Transfers in Multitask Learning Using Surrogate Models","created":"2023-03-25","cited_by_count":20,"area":null},{"id":"2409.06091","title":"Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity","created":"2024-09-09","cited_by_count":20,"area":null},{"id":"2308.02066","title":"Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives","created":"2023-08-03","cited_by_count":18,"area":null},{"id":"2303.02320","title":"Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounders","created":"2023-03-04","cited_by_count":17,"area":null},{"id":"2306.10474","title":"A Universal Semantic-Geometric Representation for Robotic Manipulation","created":"2023-06-18","cited_by_count":16,"area":null},{"id":"2307.06887","title":"Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks","created":"2023-07-13","cited_by_count":16,"area":null},{"id":"2404.01143","title":"Condition-Aware Neural Network for Controlled Image Generation","created":"2024-04-01","cited_by_count":16,"area":null},{"id":"2306.14009","title":"Boosting Multitask Learning on Graphs through Higher-Order Task Affinities","created":"2023-06-24","cited_by_count":15,"area":null},{"id":"2203.02026","title":"Provable and Efficient Continual Representation Learning","created":"2022-03-03","cited_by_count":14,"area":null},{"id":"2210.06277","title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","created":"2022-10-12","cited_by_count":14,"area":null},{"id":"2302.00674","title":"Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data","created":"2023-02-01","cited_by_count":13,"area":null},{"id":"2311.00164","title":"Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis","created":"2023-10-31","cited_by_count":13,"area":null},{"id":"2409.19458","title":"Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach","created":"2024-09-28","cited_by_count":13,"area":null},{"id":"2110.08713","title":"Pareto Navigation Gradient Descent: a First-Order Algorithm for Optimization in Pareto Set","created":"2021-10-17","cited_by_count":12,"area":null},{"id":"2408.16939","title":"Theoretical Insights into Overparameterized Models in Multi-Task and Replay-Based Continual Learning","created":"2024-08-29","cited_by_count":11,"area":null},{"id":"2109.07591","title":"On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation","created":"2021-09-15","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":"2505.21930","title":"Efficient Ensemble for Fine-tuning Language Models on Multiple Datasets","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2310.02396","title":"Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2310.10318","title":"Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2403.03037","title":"A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives","created":"2024-03-05","cited_by_count":9,"area":null},{"id":"2506.12181","title":"Generative or Discriminative? Revisiting Text Classification in the Era of Transformers","created":"2025-06-13","cited_by_count":9,"area":null},{"id":"2303.09663","title":"Efficient Computation Sharing for Multi-Task Visual Scene Understanding","created":"2023-03-16","cited_by_count":8,"area":null},{"id":"2311.12048","title":"One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning","created":"2023-11-18","cited_by_count":8,"area":null},{"id":"2401.09716","title":"HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2508.19999","title":"Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimation","created":"2025-08-27","cited_by_count":8,"area":null},{"id":"2212.06864","title":"Task-Adaptive Meta-Learning Framework for Advancing Spatial Generalizability","created":"2022-12-10","cited_by_count":7,"area":null},{"id":"2302.07120","title":"PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embedding","created":"2023-02-14","cited_by_count":7,"area":null},{"id":"2403.01400","title":"Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks","created":"2024-03-03","cited_by_count":7,"area":null},{"id":"2208.03835","title":"On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks","created":"2022-08-07","cited_by_count":6,"area":null},{"id":"2305.08208","title":"Learning to Generalize for Cross-domain QA","created":"2023-05-14","cited_by_count":6,"area":null},{"id":"2106.10840","title":"Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling","created":"2021-06-21","cited_by_count":5,"area":null},{"id":"2207.01117","title":"Saliency-Regularized Deep Multi-Task Learning","created":"2022-07-03","cited_by_count":5,"area":null},{"id":"2509.17228","title":"Causal Representation Learning from Multimodal Clinical Records under Non-Random Modality Missingness","created":"2025-09-21","cited_by_count":5,"area":null},{"id":"2107.05377","title":"A Flexible Multi-Task Model for BERT Serving","created":"2021-07-12","cited_by_count":4,"area":null},{"id":"2201.06001","title":"GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation","created":"2022-01-16","cited_by_count":4,"area":null},{"id":"2201.11231","title":"Gap Minimization for Knowledge Sharing and Transfer","created":"2022-01-26","cited_by_count":4,"area":null},{"id":"2205.01757","title":"XLTime: A Cross-Lingual Knowledge Transfer Framework for Temporal Expression Extraction","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2410.12774","title":"Identifying Task Groupings for Multi-Task Learning Using Pointwise V-Usable Information","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2107.05445","title":"Disentangling Transfer and Interference in Multi-Domain Learning","created":"2021-07-02","cited_by_count":3,"area":null},{"id":"2112.05647","title":"Analysis and Prediction of NLP Models Via Task Embeddings","created":"2021-12-10","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":"2307.03374","title":"STG-MTL: Scalable Task Grouping for Multi-Task Learning Using Data Map","created":"2023-07-07","cited_by_count":3,"area":null},{"id":"2412.17023","title":"Parameter-Efficient Interventions for Enhanced Model Merging","created":"2024-12-22","cited_by_count":3,"area":null},{"id":"2101.12431","title":"Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs","created":"2021-01-29","cited_by_count":2,"area":null},{"id":"2104.07255","title":"Embedding Adaptation is Still Needed for Few-Shot Learning","created":"2021-04-15","cited_by_count":2,"area":null},{"id":"2110.00075","title":"Noise2Recon: Enabling Joint MRI Reconstruction and Denoising with Semi-Supervised and Self-Supervised Learning","created":"2021-09-30","cited_by_count":2,"area":null},{"id":"2201.02305","title":"Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task","created":"2022-01-07","cited_by_count":2,"area":null},{"id":"2205.15882","title":"Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering","created":"2022-05-31","cited_by_count":2,"area":null},{"id":"2206.10027","title":"DNA: Proximal Policy Optimization with a Dual Network Architecture","created":"2022-06-20","cited_by_count":2,"area":null},{"id":"2308.12114","title":"Less is More -- Towards parsimonious multi-task models using structured sparsity","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2410.11227","title":"Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2101.06979","title":"Comparing Deep Learning strategies for paired but unregistered multimodal segmentation of the liver in T1 and T2-weighted MRI","created":"2021-01-18","cited_by_count":1,"area":null},{"id":"2106.01583","title":"Cross-Network Learning with Partially Aligned Graph Convolutional Networks","created":"2021-06-03","cited_by_count":1,"area":null},{"id":"2111.00328","title":"Multi-Task Learning based Convolutional Models with Curriculum Learning for the Anisotropic Reynolds Stress Tensor in Turbulent Duct Flow","created":"2021-10-30","cited_by_count":1,"area":null},{"id":"2308.08234","title":"Challenges and Opportunities of Using Transformer-Based Multi-Task Learning in NLP Through ML Lifecycle: A Survey","created":"2023-08-16","cited_by_count":1,"area":null},{"id":"2308.10293","title":"Privileged Anatomical and Protocol Discrimination in Trackerless 3D Ultrasound Reconstruction","created":"2023-08-20","cited_by_count":1,"area":null},{"id":"2311.08687","title":"An Eye on Clinical BERT: Investigating Language Model Generalization for Diabetic Eye Disease Phenotyping","created":"2023-11-15","cited_by_count":1,"area":null},{"id":"2409.09891","title":"Acquiring Pronunciation Knowledge from Transcribed Speech Audio via Multi-task Learning","created":"2024-09-15","cited_by_count":1,"area":null},{"id":"2503.05491","title":"Statistical Deficiency for Task Inclusion Estimation","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2510.10068","title":"Probabilistic Hyper-Graphs using Multiple Randomly Masked Autoencoders for Semi-supervised Multi-modal Multi-task Learning","created":"2025-10-11","cited_by_count":1,"area":null},{"id":"2512.24866","title":"Characterization of Transfer Using Multi-task Learning Curves","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2112.03032","title":"Transfer Learning in Conversational Analysis through Reusing Preprocessing Data as Supervisors","created":"2021-12-02","cited_by_count":0,"area":null},{"id":"2307.03377","title":"Mitigating Negative Transfer with Task Awareness for Sexism, Hate Speech, and Toxic Language Detection","created":"2023-07-07","cited_by_count":0,"area":null},{"id":"2405.07769","title":"$\\alpha$VIL: Learning to Leverage Auxiliary Tasks for Multitask Learning","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2411.18990","title":"USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2503.09144","title":"Efficient UAV Swarm-Based Multi-Task Federated Learning with Dynamic Task Knowledge Sharing","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2505.10347","title":"Uniform Loss vs. Specialized Optimization: A Comparative Analysis in Multi-Task Learning","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2507.16433","title":"Adaptive Multi-task Learning for Multi-sector Portfolio Optimization","created":"2025-07-22","cited_by_count":0,"area":null},{"id":"2512.02920","title":"Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2512.24708","title":"BandiK: Efficient Multi-Task Decomposition Using a Multi-Bandit Framework","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2602.23575","title":"CycleBEV: Regularizing View Transformation Networks via View Cycle Consistency for Bird's-Eye-View Semantic Segmentation","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.28739","title":"Expectation Error Bounds for Transfer Learning in Linear Regression and Linear Neural Networks","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.21235","title":"Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative Missingness","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2606.22181","title":"Residue-Level Attributions in Protein Language Models Do Not Recover Allergen Epitopes","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2610.02578","title":"High-Dimensional Asymptotics and Dataset Selection for Private Transfer Learning","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}