{"total":62,"rows":[{"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":"2410.21306","title":"Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges","created":"2024-10-25","cited_by_count":42,"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":"2308.12029","title":"Dual-Balancing for Multi-Task Learning","created":"2023-08-23","cited_by_count":27,"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":"2205.10773","title":"A Domain-adaptive Pre-training Approach for Language Bias Detection in News","created":"2022-05-22","cited_by_count":16,"area":null},{"id":"2411.16815","title":"FREE-Merging: Fourier Transform for Efficient Model Merging","created":"2024-11-25","cited_by_count":13,"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":"2404.06486","title":"GO4Align: Group Optimization for Multi-Task Alignment","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2505.05279","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2204.03500","title":"Multi-Task Distributed Learning using Vision Transformer with Random Patch Permutation","created":"2022-04-07","cited_by_count":10,"area":null},{"id":"2306.15489","title":"Precursor-of-Anomaly Detection for Irregular Time Series","created":"2023-06-27","cited_by_count":9,"area":null},{"id":"2310.02973","title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","created":"2023-10-04","cited_by_count":9,"area":null},{"id":"2412.20662","title":"Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner","created":"2024-12-30","cited_by_count":9,"area":"lr"},{"id":"2505.22694","title":"MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2111.12146","title":"Sharing to learn and learning to share; Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning: A meta review","created":"2021-11-23","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":"2409.06622","title":"Exploring Italian sentence embeddings properties through multi-tasking","created":"2024-09-10","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":"2603.04772","title":"TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings","created":"2026-03-05","cited_by_count":6,"area":"lr"},{"id":"2302.08777","title":"Hate Speech and Offensive Language Detection using an Emotion-aware Shared Encoder","created":"2023-02-17","cited_by_count":5,"area":null},{"id":"2304.11408","title":"Lightweight Toxicity Detection in Spoken Language: A Transformer-based Approach for Edge Devices","created":"2023-04-22","cited_by_count":5,"area":"distill"},{"id":"2402.06443","title":"Explaining Veracity Predictions with Evidence Summarization: A Multi-Task Model Approach","created":"2024-02-09","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":"2502.11513","title":"MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2502.11533","title":"Be Cautious When Merging Unfamiliar LLMs: A Phishing Model Capable of Stealing Privacy","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2505.18644","title":"Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2210.17301","title":"Effective Cross-Task Transfer Learning for Explainable Natural Language Inference with T5","created":"2022-10-31","cited_by_count":2,"area":null},{"id":"2402.00474","title":"SA-MDKIF: A Scalable and Adaptable Medical Domain Knowledge Injection Framework for Large Language Models","created":"2024-02-01","cited_by_count":2,"area":null},{"id":"2504.16214","title":"Hexcute: A Compiler Framework for Automating Layout Synthesis in GPU Programs","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2505.20088","title":"Multi-Domain Explainability of Preferences","created":"2025-05-26","cited_by_count":2,"area":"alignment"},{"id":"2510.11222","title":"Fairness Metric Design Exploration in Multi-Domain Moral Sentiment Classification using Transformer-Based Models","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2510.18258","title":"NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2602.01594","title":"UV-M3TL: A Unified and Versatile Multimodal Multi-Task Learning Framework for Assistive Driving Perception","created":"2026-02-02","cited_by_count":2,"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":"2401.12923","title":"Deep multitask neural networks for solving some stochastic optimal control problems","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2405.09886","title":"MTLComb: multi-task learning combining regression and classification tasks for joint feature selection","created":"2024-05-16","cited_by_count":1,"area":null},{"id":"2502.19568","title":"PhenoProfiler: Advancing Phenotypic Learning for Image-based Drug Discovery","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2505.23538","title":"CLaC at SemEval-2025 Task 6: A Multi-Architecture Approach for Corporate Environmental Promise Verification","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2505.24185","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2507.07883","title":"SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2508.04461","title":"Small transformer architectures for task switching","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2511.04705","title":"POLIS-Bench: Towards Multi-Dimensional Evaluation of LLMs for Bilingual Policy Tasks in Governmental Scenarios","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2512.00088","title":"Semimage: HSV-Based Semantic Image Encoding for Disentangled Text Representation","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2605.18904","title":"Dynamic Model Merging Made Slim","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2404.11916","title":"Unplug and Play Language Models: Decomposing Experts in Language Models at Inference Time","created":"2024-04-18","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":"2410.10687","title":"Building a Multivariate Time Series Benchmarking Datasets Inspired by Natural Language Processing (NLP)","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2411.00437","title":"E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation","created":"2024-11-01","cited_by_count":0,"area":"rag"},{"id":"2412.13809","title":"Extreme Multi-label Completion for Semantic Document Labelling with Taxonomy-Aware Parallel Learning","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2502.18167","title":"Sharper Risk Bound for Multi-Task Learning with Multi-Graph Dependent Data","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2503.01268","title":"Multi-Level Collaboration in Model Merging","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2503.16047","title":"Temporal-Spatial Attention Network (TSAN) for DoS Attack Detection in Network Traffic","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2503.24116","title":"Multi-Task Learning for Extracting Menstrual Characteristics from Clinical Notes","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2505.06665","title":"MultiTaskVIF: Segmentation-oriented visible and infrared image fusion via multi-task learning","created":"2025-05-10","cited_by_count":0,"area":null},{"id":"2507.19741","title":"Basic Reading Distillation","created":"2025-07-26","cited_by_count":0,"area":"distill"},{"id":"2508.04422","title":"Efficient Inter-Task Attention for Multitask Transformer Models","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2509.11525","title":"DARD: Dice Adversarial Robustness Distillation against Adversarial Attacks","created":"2025-09-15","cited_by_count":0,"area":"distill"},{"id":"2602.19837","title":"Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent","created":"2026-02-23","cited_by_count":0,"area":"deeprl"},{"id":"2603.10466","title":"UniPINN: A Unified PINN Framework for Multi-task Learning of Diverse Navier-Stokes Equations","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.00533","title":"Toward Robust Open-set Adaptation: Synapse Consolidation Inspired by Rac1/MAPK Pathways","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2609.06406","title":"Hierarchical Wasserstein Merging for Multi-Domain Multi-Task Learning: From Specialists to a Generalist","created":"2026-09-06","cited_by_count":0,"area":null}],"next_cursor":null}