{"total":45,"rows":[{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"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":"2109.14723","title":"BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief","created":"2021-09-29","cited_by_count":57,"area":null},{"id":"2201.04182","title":"HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning","created":"2022-01-11","cited_by_count":55,"area":null},{"id":"2107.07261","title":"Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills","created":"2021-07-15","cited_by_count":39,"area":null},{"id":"2104.08142","title":"Supervising Model Attention with Human Explanations for Robust Natural Language Inference","created":"2021-04-16","cited_by_count":29,"area":null},{"id":"2203.08304","title":"Hyperdecoders: Instance-specific decoders for multi-task NLP","created":"2022-03-15","cited_by_count":22,"area":null},{"id":"2310.16686","title":"Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies","created":"2023-10-25","cited_by_count":20,"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":"2211.09783","title":"UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization","created":"2022-11-17","cited_by_count":15,"area":null},{"id":"2109.10274","title":"The Trade-offs of Domain Adaptation for Neural Language Models","created":"2021-09-21","cited_by_count":14,"area":null},{"id":"2305.09299","title":"UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning","created":"2023-05-16","cited_by_count":13,"area":null},{"id":"2404.06486","title":"GO4Align: Group Optimization for Multi-Task Alignment","created":"2024-04-09","cited_by_count":11,"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":"2110.06223","title":"Investigating the Effect of Natural Language Explanations on Out-of-Distribution Generalization in Few-shot NLI","created":"2021-10-12","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":"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":"2110.02056","title":"Are Training Resources Insufficient? Predict First Then Explain!","created":"2021-08-29","cited_by_count":5,"area":null},{"id":"2307.07742","title":"SINC: Self-Supervised In-Context Learning for Vision-Language Tasks","created":"2023-07-15","cited_by_count":4,"area":null},{"id":"2401.17838","title":"A Cross-View Hierarchical Graph Learning Hypernetwork for Skill Demand-Supply Joint Prediction","created":"2024-01-31","cited_by_count":4,"area":null},{"id":"2409.19308","title":"Designing Domain-Specific Large Language Models: The Critical Role of Fine-Tuning in Public Opinion Simulation","created":"2024-09-28","cited_by_count":4,"area":null},{"id":"2111.02188","title":"BERT-DRE: BERT with Deep Recursive Encoder for Natural Language Sentence Matching","created":"2021-11-03","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":"2307.02849","title":"NatLogAttack: A Framework for Attacking Natural Language Inference Models with Natural Logic","created":"2023-07-06","cited_by_count":3,"area":null},{"id":"2307.01446","title":"On Conditional and Compositional Language Model Differentiable Prompting","created":"2023-07-04","cited_by_count":2,"area":null},{"id":"2310.01217","title":"ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale","created":"2023-10-02","cited_by_count":2,"area":null},{"id":"2502.12195","title":"GeneralizeFormer: Layer-Adaptive Model Generation across Test-Time Distribution Shifts","created":"2025-02-15","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":"2105.03775","title":"NLP-IIS@UT at SemEval-2021 Task 4: Machine Reading Comprehension using the Long Document Transformer","created":"2021-05-08","cited_by_count":1,"area":null},{"id":"2109.06308","title":"Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translation","created":"2021-09-13","cited_by_count":1,"area":null},{"id":"2111.06012","title":"Kronecker Factorization for Preventing Catastrophic Forgetting in Large-scale Medical Entity Linking","created":"2021-11-11","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":"2106.05221","title":"Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning","created":"2021-06-08","cited_by_count":0,"area":null},{"id":"2110.04866","title":"CoRGi: Content-Rich Graph Neural Networks with Attention","created":"2021-10-10","cited_by_count":0,"area":null},{"id":"2111.10974","title":"Many Heads but One Brain: Fusion Brain -- a Competition and a Single Multimodal Multitask Architecture","created":"2021-11-22","cited_by_count":0,"area":null},{"id":"2205.10744","title":"All Birds with One Stone: Multi-task Text Classification for Efficient Inference with One Forward Pass","created":"2022-05-22","cited_by_count":0,"area":null},{"id":"2210.07453","title":"Using Graph Algorithms to Pretrain Graph Completion Transformers","created":"2022-10-14","cited_by_count":0,"area":null},{"id":"2306.04170","title":"From the One, Judge of the Whole: Typed Entailment Graph Construction with Predicate Generation","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2311.16965","title":"Natural Language Processing Through Transfer Learning: A Case Study on Sentiment Analysis","created":"2023-11-28","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":"2506.02753","title":"Multi-task Learning with Active Learning for Arabic Offensive Speech Detection","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2608.15325","title":"Logical Embeddings for Argument Analysis","created":"2026-08-15","cited_by_count":0,"area":null}],"next_cursor":null}