{"total":59,"rows":[{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235,"area":null},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"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":"2307.05845","title":"PIGEON: Predicting Image Geolocations","created":"2023-07-11","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":"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":"2210.16822","title":"Towards Versatile Embodied Navigation","created":"2022-10-30","cited_by_count":26,"area":null},{"id":"2110.14202","title":"Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning","created":"2021-10-27","cited_by_count":22,"area":null},{"id":"2501.06773","title":"Pareto Set Learning for Multi-Objective Reinforcement Learning","created":"2025-01-12","cited_by_count":20,"area":"deeprl"},{"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":"2104.08078","title":"To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning","created":"2021-04-16","cited_by_count":11,"area":null},{"id":"2201.00768","title":"Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions","created":"2022-01-03","cited_by_count":11,"area":null},{"id":"2205.06262","title":"FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue","created":"2022-05-12","cited_by_count":11,"area":null},{"id":"2101.11287","title":"Language Modelling as a Multi-Task Problem","created":"2021-01-27","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":"2301.05065","title":"Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks","created":"2023-01-12","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":"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":"2205.09898","title":"Let the Model Decide its Curriculum for Multitask Learning","created":"2022-05-19","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":"2109.05748","title":"GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks","created":"2021-09-13","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":"2104.09261","title":"Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection","created":"2021-04-19","cited_by_count":6,"area":null},{"id":"2307.14382","title":"When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review","created":"2023-07-25","cited_by_count":6,"area":null},{"id":"2412.11455","title":"Towards Better Multi-task Learning: A Framework for Optimizing Dataset Combinations in Large Language Models","created":"2024-12-16","cited_by_count":6,"area":null},{"id":"2103.02546","title":"Multi-task Learning by Leveraging the Semantic Information","created":"2021-03-03","cited_by_count":5,"area":null},{"id":"2306.13661","title":"Constructing Time-Series Momentum Portfolios with Deep Multi-Task Learning","created":"2023-06-08","cited_by_count":5,"area":null},{"id":"2106.16162","title":"Learning More for Free - A Multi Task Learning Approach for Improved Pathology Classification in Capsule Endoscopy","created":"2021-06-30","cited_by_count":4,"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":"2201.06239","title":"MT-GBM: A Multi-Task Gradient Boosting Machine with Shared Decision Trees","created":"2022-01-17","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":"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":"2403.07910","title":"MAGPIE: Multi-Task Media-Bias Analysis Generalization for Pre-Trained Identification of Expressions","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2410.07172","title":"Glider: Global and Local Instruction-Driven Expert Router","created":"2024-10-09","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":"2601.06672","title":"Will it Merge? On The Causes of Model Mergeability","created":"2026-01-10","cited_by_count":4,"area":null},{"id":"2106.04476","title":"One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasets","created":"2021-06-08","cited_by_count":3,"area":null},{"id":"2201.01164","title":"Interpretable Low-Resource Legal Decision Making","created":"2022-01-01","cited_by_count":3,"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":"2204.04544","title":"Efficient Extraction of Pathologies from C-Spine Radiology Reports using Multi-Task Learning","created":"2022-04-09","cited_by_count":2,"area":null},{"id":"2307.05741","title":"Towards Robust and Efficient Continual Language Learning","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2402.14522","title":"Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2506.02308","title":"MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2105.14214","title":"Predictive Representation Learning for Language Modeling","created":"2021-05-29","cited_by_count":1,"area":null},{"id":"2108.07871","title":"Contextualizing Variation in Text Style Transfer Datasets","created":"2021-08-17","cited_by_count":1,"area":null},{"id":"2203.01655","title":"On partitioning of an SHM problem and parallels with transfer learning","created":"2022-03-03","cited_by_count":1,"area":null},{"id":"2205.02979","title":"Explaining the Effectiveness of Multi-Task Learning for Efficient Knowledge Extraction from Spine MRI Reports","created":"2022-05-06","cited_by_count":1,"area":null},{"id":"2208.10250","title":"Multi-Task Learning for Depression Detection in Dialogs","created":"2022-07-21","cited_by_count":1,"area":null},{"id":"2301.02873","title":"\"It's a Match!\" -- A Benchmark of Task Affinity Scores for Joint Learning","created":"2023-01-07","cited_by_count":1,"area":null},{"id":"2503.18023","title":"Regularization of ML models for Earth systems by using longer model timesteps","created":"2025-03-23","cited_by_count":1,"area":null},{"id":"2202.01096","title":"Identifying Suitable Tasks for Inductive Transfer Through the Analysis of Feature Attributions","created":"2022-02-02","cited_by_count":0,"area":null},{"id":"2202.12093","title":"KESA: A Knowledge Enhanced Approach For Sentiment Analysis","created":"2022-02-24","cited_by_count":0,"area":null},{"id":"2210.04001","title":"Don't Waste Data: Transfer Learning to Leverage All Data for Machine-Learnt Climate Model Emulation","created":"2022-10-08","cited_by_count":0,"area":null},{"id":"2403.09451","title":"M&M: Multimodal-Multitask Model Integrating Audiovisual Cues in Cognitive Load Assessment","created":"2024-03-14","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":"2408.15406","title":"Intertwined Biases Across Social Media Spheres: Unpacking Correlations in Media Bias Dimensions","created":"2024-08-27","cited_by_count":0,"area":null},{"id":"2602.07218","title":"Collaborative and Efficient Fine-tuning: Leveraging Task Similarity","created":"2026-02-06","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":"2608.29790","title":"HiVe: Beyond Static Prompts for Multitask Learning via Hierarchy-based Vertical Mixture-of-Experts","created":"2026-08-30","cited_by_count":0,"area":"moe"}],"next_cursor":null}