{"total":59,"rows":[{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868,"area":null},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459,"area":null},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215,"area":null},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195,"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":"2301.09790","title":"The Next Chapter: A Study of Large Language Models in Storytelling","created":"2023-01-24","cited_by_count":58,"area":null},{"id":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2302.11289","title":"Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning","created":"2023-02-22","cited_by_count":51,"area":null},{"id":"2105.07316","title":"From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding","created":"2021-05-15","cited_by_count":43,"area":null},{"id":"2204.03508","title":"A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods","created":"2022-04-07","cited_by_count":42,"area":null},{"id":"2104.01785","title":"Annotating Columns with Pre-trained Language Models","created":"2021-04-05","cited_by_count":37,"area":null},{"id":"2305.20057","title":"Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance","created":"2023-05-31","cited_by_count":36,"area":null},{"id":"2305.18409","title":"Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms","created":"2023-05-28","cited_by_count":34,"area":null},{"id":"2101.06720","title":"Deep Multi-Task Learning for Joint Localization, Perception, and Prediction","created":"2021-01-17","cited_by_count":22,"area":null},{"id":"2106.09063","title":"Specializing Multilingual Language Models: An Empirical Study","created":"2021-06-16","cited_by_count":21,"area":null},{"id":"2112.07868","title":"Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases","created":"2021-12-15","cited_by_count":21,"area":null},{"id":"2102.06841","title":"Collaborative Intelligence: Challenges and Opportunities","created":"2021-02-13","cited_by_count":19,"area":null},{"id":"2210.12624","title":"Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach","created":"2022-10-23","cited_by_count":14,"area":null},{"id":"2303.01980","title":"Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecycle","created":"2023-02-05","cited_by_count":14,"area":null},{"id":"2101.01476","title":"PhoNLP: A joint multi-task learning model for Vietnamese part-of-speech tagging, named entity recognition and dependency parsing","created":"2021-01-05","cited_by_count":13,"area":null},{"id":"2101.10368","title":"Meta-Learning for Effective Multi-task and Multilingual Modelling","created":"2021-01-25","cited_by_count":13,"area":null},{"id":"2212.06933","title":"Paraphrase Identification with Deep Learning: A Review of Datasets and Methods","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2401.10222","title":"Supervised Fine-tuning in turn Improves Visual Foundation Models","created":"2024-01-18","cited_by_count":13,"area":null},{"id":"2101.06514","title":"Linguistically-Enriched and Context-Aware Zero-shot Slot Filling","created":"2021-01-16","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":"2302.07372","title":"Same Same, But Different: Conditional Multi-Task Learning for Demographic-Specific Toxicity Detection","created":"2023-02-14","cited_by_count":10,"area":null},{"id":"2104.06129","title":"What's in your Head? Emergent Behaviour in Multi-Task Transformer Models","created":"2021-04-13","cited_by_count":9,"area":null},{"id":"2103.03296","title":"PVG at WASSA 2021: A Multi-Input, Multi-Task, Transformer-Based Architecture for Empathy and Distress Prediction","created":"2021-03-04","cited_by_count":7,"area":null},{"id":"2111.05013","title":"Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks","created":"2021-11-09","cited_by_count":6,"area":null},{"id":"2307.14785","title":"Improving Aspect-Based Sentiment with End-to-End Semantic Role Labeling Model","created":"2023-07-27","cited_by_count":5,"area":null},{"id":"2408.00981","title":"Cross-domain Named Entity Recognition via Graph Matching","created":"2024-08-02","cited_by_count":5,"area":null},{"id":"2101.11958","title":"Attention Guided Dialogue State Tracking with Sparse Supervision","created":"2021-01-28","cited_by_count":4,"area":null},{"id":"2310.00598","title":"A Novel Computational and Modeling Foundation for Automatic Coherence Assessment","created":"2023-10-01","cited_by_count":4,"area":null},{"id":"2109.13497","title":"Instance-Based Neural Dependency Parsing","created":"2021-09-28","cited_by_count":3,"area":null},{"id":"2308.00759","title":"Decomposition Ascribed Synergistic Learning for Unified Image Restoration","created":"2023-08-01","cited_by_count":3,"area":null},{"id":"2107.11435","title":"HierMUD: Hierarchical Multi-task Unsupervised Domain Adaptation between Bridges for Drive-by Damage Diagnosis","created":"2021-07-23","cited_by_count":2,"area":null},{"id":"2201.00490","title":"Learning with Latent Structures in Natural Language Processing: A Survey","created":"2022-01-03","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":"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":"2104.08635","title":"UPB at SemEval-2021 Task 5: Virtual Adversarial Training for Toxic Spans Detection","created":"2021-04-17","cited_by_count":1,"area":null},{"id":"2104.14781","title":"Out-of-Scope Domain and Intent Classification through Hierarchical Joint Modeling","created":"2021-04-30","cited_by_count":1,"area":null},{"id":"2105.14214","title":"Predictive Representation Learning for Language Modeling","created":"2021-05-29","cited_by_count":1,"area":null},{"id":"2107.00841","title":"ClueReader: Heterogeneous Graph Attention Network for Multi-hop Machine Reading Comprehension","created":"2021-07-02","cited_by_count":1,"area":null},{"id":"2109.06035","title":"Traffic Event Detection as a Slot Filling Problem","created":"2021-09-13","cited_by_count":1,"area":null},{"id":"2212.09400","title":"Medical Knowledge Graph QA for Drug-Drug Interaction Prediction based on Multi-hop Machine Reading Comprehension","created":"2022-12-19","cited_by_count":1,"area":null},{"id":"2309.01606","title":"Geo-Encoder: A Chunk-Argument Bi-Encoder Framework for Chinese Geographic Re-Ranking","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2405.05695","title":"Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost","created":"2024-05-09","cited_by_count":1,"area":null},{"id":"2503.04667","title":"An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2505.21438","title":"Measuring Fine-Grained Relatedness in Multitask Learning via Data Attribution","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2103.04290","title":"MTLHealth: A Deep Learning System for Detecting Disturbing Content in Student Essays","created":"2021-03-07","cited_by_count":0,"area":null},{"id":"2107.11778","title":"Learn to Focus: Hierarchical Dynamic Copy Network for Dialogue State Tracking","created":"2021-07-25","cited_by_count":0,"area":null},{"id":"2209.13444","title":"Design Perspectives of Multitask Deep Learning Models and Applications","created":"2022-09-27","cited_by_count":0,"area":null},{"id":"2303.15656","title":"Predicting Adverse Neonatal Outcomes for Preterm Neonates with Multi-Task Learning","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2310.03148","title":"Multi-Task Learning For Reduced Popularity Bias In Multi-Territory Video Recommendations","created":"2023-09-25","cited_by_count":0,"area":null},{"id":"2402.06224","title":"Adaptive multi-gradient methods for quasiconvex vector optimization and applications to multi-task learning","created":"2024-02-09","cited_by_count":0,"area":null},{"id":"2501.00823","title":"Decoupling Knowledge and Reasoning in Transformers: A Modular Architecture with Generalized Cross-Attention","created":"2025-01-01","cited_by_count":0,"area":null},{"id":"2511.05239","title":"Translation via Annotation: A Computational Study of Translating Classical Chinese into Japanese","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2601.21513","title":"Cascaded Transfer: Learning Many Tasks under Budget Constraints","created":"2026-01-29","cited_by_count":0,"area":null}],"next_cursor":null}