{"total":169,"rows":[{"id":"2111.02387","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","created":"2021-11-03","cited_by_count":271,"area":null},{"id":"2303.09556","title":"Efficient Diffusion Training via Min-SNR Weighting Strategy","created":"2023-03-16","cited_by_count":246,"area":"diffusion"},{"id":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222,"area":null},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215,"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":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151,"area":null},{"id":"2202.01374","title":"mSLAM: Massively multilingual joint pre-training for speech and text","created":"2022-02-03","cited_by_count":108,"area":null},{"id":"2111.10603","title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning","created":"2021-11-20","cited_by_count":101,"area":null},{"id":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98,"area":"moe"},{"id":"2402.02705","title":"Representation Surgery for Multi-Task Model Merging","created":"2024-02-05","cited_by_count":96,"area":null},{"id":"2103.02631","title":"RotoGrad: Gradient Homogenization in Multitask Learning","created":"2021-03-03","cited_by_count":83,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2405.11157","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","created":"2024-05-18","cited_by_count":72,"area":null},{"id":"2305.19000","title":"Independent Component Alignment for Multi-Task Learning","created":"2023-05-30","cited_by_count":70,"area":null},{"id":"2201.04122","title":"In Defense of the Unitary Scalarization for Deep Multi-Task Learning","created":"2022-01-11","cited_by_count":67,"area":null},{"id":"2109.09138","title":"Multi-Task Learning in Natural Language Processing: An Overview","created":"2021-09-19","cited_by_count":62,"area":null},{"id":"2104.14830","title":"Scaling End-to-End Models for Large-Scale Multilingual ASR","created":"2021-04-30","cited_by_count":61,"area":null},{"id":"2108.01621","title":"Domain Generalization via Gradient Surgery","created":"2021-08-03","cited_by_count":60,"area":null},{"id":"2209.11379","title":"Do Current Multi-Task Optimization Methods in Deep Learning Even Help?","created":"2022-09-23","cited_by_count":60,"area":null},{"id":"2402.19078","title":"Smooth Tchebycheff Scalarization for Multi-Objective Optimization","created":"2024-02-29","cited_by_count":54,"area":null},{"id":"2210.11653","title":"PaCo: Parameter-Compositional Multi-Task Reinforcement Learning","created":"2022-10-21","cited_by_count":46,"area":null},{"id":"2307.15324","title":"TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts","created":"2023-07-28","cited_by_count":45,"area":"moe"},{"id":"2410.03115","title":"X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale","created":"2024-10-04","cited_by_count":36,"area":null},{"id":"2402.15638","title":"Fair Resource Allocation in Multi-Task Learning","created":"2024-02-23","cited_by_count":35,"area":null},{"id":"2404.00986","title":"Make Continual Learning Stronger via C-Flat","created":"2024-04-01","cited_by_count":35,"area":null},{"id":"2211.03831","title":"Multi-Head Adapter Routing for Cross-Task Generalization","created":"2022-11-07","cited_by_count":33,"area":null},{"id":"2306.00354","title":"Addressing Negative Transfer in Diffusion Models","created":"2023-06-01","cited_by_count":33,"area":"diffusion"},{"id":"2408.10159","title":"Customizing Language Models with Instance-wise LoRA for Sequential Recommendation","created":"2024-08-19","cited_by_count":32,"area":"moe"},{"id":"2109.04778","title":"Improving Multilingual Translation by Representation and Gradient Regularization","created":"2021-09-10","cited_by_count":31,"area":null},{"id":"2410.22086","title":"Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate","created":"2024-10-29","cited_by_count":31,"area":"safety"},{"id":"2202.13914","title":"Combining Modular Skills in Multitask Learning","created":"2022-02-28","cited_by_count":28,"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":"2301.12618","title":"ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning","created":"2023-01-30","cited_by_count":28,"area":null},{"id":"2302.09650","title":"Scaling Laws for Multilingual Neural Machine Translation","created":"2023-02-19","cited_by_count":27,"area":null},{"id":"2308.12029","title":"Dual-Balancing for Multi-Task Learning","created":"2023-08-23","cited_by_count":27,"area":null},{"id":"2203.14338","title":"LibMTL: A Python Library for Multi-Task Learning","created":"2022-03-27","cited_by_count":25,"area":null},{"id":"2212.07530","title":"Causes and Cures for Interference in Multilingual Translation","created":"2022-12-14","cited_by_count":23,"area":null},{"id":"2312.01397","title":"Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective","created":"2023-12-03","cited_by_count":23,"area":null},{"id":"2310.00344","title":"HarmonyDream: Task Harmonization Inside World Models","created":"2023-09-30","cited_by_count":22,"area":"wm"},{"id":"2306.10460","title":"Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models","created":"2023-06-18","cited_by_count":20,"area":null},{"id":"2109.02284","title":"Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training","created":"2021-09-06","cited_by_count":19,"area":null},{"id":"2310.08910","title":"Scalarization for Multi-Task and Multi-Domain Learning at Scale","created":"2023-10-13","cited_by_count":19,"area":null},{"id":"2404.11201","title":"Neuron Specialization: Leveraging intrinsic task modularity for multilingual machine translation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2109.04020","title":"Distributionally Robust Multilingual Machine Translation","created":"2021-09-09","cited_by_count":18,"area":null},{"id":"2403.15389","title":"DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data","created":"2024-03-22","cited_by_count":18,"area":"diffusion"},{"id":"2410.03735","title":"Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2501.10945","title":"Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond","created":"2025-01-19","cited_by_count":18,"area":null},{"id":"2311.13250","title":"FedHCA$^2$: Towards Hetero-Client Federated Multi-Task Learning","created":"2023-11-22","cited_by_count":17,"area":null},{"id":"2110.02600","title":"Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning","created":"2021-10-06","cited_by_count":16,"area":null},{"id":"2110.06997","title":"Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits","created":"2021-10-13","cited_by_count":16,"area":null},{"id":"2406.08811","title":"Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models","created":"2024-06-13","cited_by_count":16,"area":null},{"id":"2104.07639","title":"Robust Optimization for Multilingual Translation with Imbalanced Data","created":"2021-04-15","cited_by_count":15,"area":null},{"id":"2211.13723","title":"Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2411.11188","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","created":"2024-11-17","cited_by_count":15,"area":"deeprl"},{"id":"2306.10155","title":"Fairness in Multi-Task Learning via Wasserstein Barycenters","created":"2023-06-16","cited_by_count":14,"area":null},{"id":"2602.05547","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","created":"2026-02-05","cited_by_count":14,"area":"lr"},{"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":"2407.08056","title":"Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2203.04695","title":"Structured Multi-task Learning for Molecular Property Prediction","created":"2022-02-22","cited_by_count":12,"area":null},{"id":"2301.13501","title":"Auxiliary Learning as an Asymmetric Bargaining Game","created":"2023-01-31","cited_by_count":12,"area":null},{"id":"2406.09679","title":"Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters","created":"2024-06-14","cited_by_count":12,"area":null},{"id":"2410.14389","title":"SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery","created":"2024-10-18","cited_by_count":12,"area":null},{"id":"2402.04005","title":"Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2110.05838","title":"Balancing Average and Worst-case Accuracy in Multitask Learning","created":"2021-10-12","cited_by_count":10,"area":null},{"id":"2501.19400","title":"Vintix: Action Model via In-Context Reinforcement Learning","created":"2025-01-31","cited_by_count":10,"area":"deeprl"},{"id":"2211.02077","title":"Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization","created":"2022-11-03","cited_by_count":9,"area":null},{"id":"2501.15556","title":"Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2502.00089","title":"Ensembles of Low-Rank Expert Adapters","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2602.02301","title":"Advancing General-Purpose Reasoning Models with Modular Gradient Surgery","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2606.24993","title":"The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order","created":"2026-06-23","cited_by_count":9,"area":"alignment"},{"id":"2104.07358","title":"Adaptive Sparse Transformer for Multilingual Translation","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2312.03248","title":"Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning","created":"2023-12-06","cited_by_count":8,"area":null},{"id":"2401.09257","title":"A First-Order Multi-Gradient Algorithm for Multi-Objective Bi-Level Optimization","created":"2024-01-17","cited_by_count":8,"area":null},{"id":"2502.06244","title":"PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2110.08975","title":"Deep Transfer Learning & Beyond: Transformer Language Models in Information Systems Research","created":"2021-10-18","cited_by_count":7,"area":null},{"id":"2204.13869","title":"Por Qu\\'e N\\~ao Utiliser Alla Spr{\\aa}k? Mixed Training with Gradient Optimization in Few-Shot Cross-Lingual Transfer","created":"2022-04-29","cited_by_count":7,"area":null},{"id":"2304.03216","title":"On the Pareto Front of Multilingual Neural Machine Translation","created":"2023-04-06","cited_by_count":7,"area":null},{"id":"2402.14430","title":"Robust Training of Federated Models with Extremely Label Deficiency","created":"2024-02-22","cited_by_count":7,"area":null},{"id":"2404.02392","title":"Low-resource neural machine translation with morphological modeling","created":"2024-04-03","cited_by_count":7,"area":null},{"id":"2410.06664","title":"Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning","created":"2024-10-09","cited_by_count":7,"area":"diffusion"},{"id":"2410.14633","title":"Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning","created":"2024-10-18","cited_by_count":7,"area":null},{"id":"2503.02312","title":"Go Beyond Your Means: Unlearning with Per-Sample Gradient Orthogonalization","created":"2025-03-04","cited_by_count":7,"area":"safety"},{"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":"2212.06645","title":"Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?","created":"2022-12-13","cited_by_count":6,"area":null},{"id":"2305.08328","title":"FedAds: A Benchmark for Privacy-Preserving CVR Estimation with Vertical Federated Learning","created":"2023-05-15","cited_by_count":6,"area":null},{"id":"2306.04519","title":"Sample-Level Weighting for Multi-Task Learning with Auxiliary Tasks","created":"2023-06-07","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":"2310.00840","title":"Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2310.10462","title":"Adaptive Neural Ranking Framework: Toward Maximized Business Goal for Cascade Ranking Systems","created":"2023-10-16","cited_by_count":6,"area":null},{"id":"2310.15269","title":"GradSim: Gradient-Based Language Grouping for Effective Multilingual Training","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2410.04407","title":"Lens: Rethinking Multilingual Enhancement for Large Language Models","created":"2024-10-06","cited_by_count":6,"area":"lr"},{"id":"2410.04579","title":"Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets","created":"2024-10-06","cited_by_count":6,"area":null},{"id":"2112.13619","title":"Parameter Differentiation based Multilingual Neural Machine Translation","created":"2021-12-27","cited_by_count":5,"area":null},{"id":"2210.10293","title":"Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning","created":"2022-10-19","cited_by_count":5,"area":null},{"id":"2212.06750","title":"FairRoad: Achieving Fairness for Recommender Systems with Optimized Antidote Data","created":"2022-12-13","cited_by_count":5,"area":null},{"id":"2305.14007","title":"When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2308.05996","title":"Deep Task-specific Bottom Representation Network for Multi-Task Recommendation","created":"2023-08-11","cited_by_count":5,"area":null},{"id":"2401.08256","title":"Multitask Learning in Minimally Invasive Surgical Vision: A Review","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2110.09930","title":"Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning","created":"2021-10-18","cited_by_count":4,"area":null},{"id":"2208.09130","title":"Personalizing Intervened Network for Long-tailed Sequential User Behavior Modeling","created":"2022-08-19","cited_by_count":4,"area":null}],"next_cursor":"100"}