{"total":85,"rows":[{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284,"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":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115,"area":null},{"id":"2401.10491","title":"Knowledge Fusion of Large Language Models","created":"2024-01-19","cited_by_count":115,"area":null},{"id":"2110.03742","title":"Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference","created":"2021-09-24","cited_by_count":96,"area":"moe"},{"id":"2108.11353","title":"Multi-Task Self-Training for Learning General Representations","created":"2021-08-25","cited_by_count":85,"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":"2104.07163","title":"Annealing Knowledge Distillation","created":"2021-04-14","cited_by_count":61,"area":"distill"},{"id":"2110.06923","title":"Object DGCNN: 3D Object Detection using Dynamic Graphs","created":"2021-10-13","cited_by_count":58,"area":null},{"id":"2206.04674","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","created":"2022-06-09","cited_by_count":58,"area":"moe"},{"id":"2103.13841","title":"Universal Representation Learning from Multiple Domains for Few-shot Classification","created":"2021-03-25","cited_by_count":56,"area":null},{"id":"2108.06027","title":"PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval","created":"2021-08-13","cited_by_count":50,"area":null},{"id":"2210.05528","title":"Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems","created":"2022-10-11","cited_by_count":44,"area":null},{"id":"2303.02483","title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks","created":"2023-03-04","cited_by_count":38,"area":"mllm"},{"id":"2109.06939","title":"The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders","created":"2021-09-14","cited_by_count":32,"area":null},{"id":"2105.05912","title":"MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation","created":"2021-05-12","cited_by_count":27,"area":"distill"},{"id":"2408.05088","title":"UNIC: Universal Classification Models via Multi-teacher Distillation","created":"2024-08-09","cited_by_count":27,"area":"distill"},{"id":"2204.02744","title":"Universal Representations: A Unified Look at Multiple Task and Domain Learning","created":"2022-04-06","cited_by_count":23,"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":"2108.13873","title":"Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs","created":"2021-08-29","cited_by_count":18,"area":null},{"id":"2110.08532","title":"Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher","created":"2021-10-16","cited_by_count":17,"area":null},{"id":"2311.01755","title":"Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection","created":"2023-11-03","cited_by_count":15,"area":null},{"id":"2112.07074","title":"Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text","created":"2021-12-14","cited_by_count":14,"area":"distill"},{"id":"2106.02834","title":"MergeDistill: Merging Pre-trained Language Models using Distillation","created":"2021-06-05","cited_by_count":13,"area":null},{"id":"2302.07937","title":"The Expressive Power of Tuning Only the Normalization Layers","created":"2023-02-15","cited_by_count":13,"area":null},{"id":"2105.11223","title":"De-identification of Privacy-related Entities in Job Postings","created":"2021-05-24","cited_by_count":12,"area":null},{"id":"2105.13608","title":"Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax","created":"2021-05-28","cited_by_count":10,"area":null},{"id":"2105.14796","title":"Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning","created":"2021-05-31","cited_by_count":10,"area":null},{"id":"2205.00479","title":"Nearest Neighbor Knowledge Distillation for Neural Machine Translation","created":"2022-05-01","cited_by_count":10,"area":"distill"},{"id":"2211.12707","title":"Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?","created":"2022-11-23","cited_by_count":10,"area":null},{"id":"2302.11074","title":"Preventing Catastrophic Forgetting in Continual Learning of New Natural Language Tasks","created":"2023-02-22","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":"2208.10930","title":"FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification","created":"2022-08-23","cited_by_count":9,"area":null},{"id":"2502.13108","title":"Clinical QA 2.0: Multi-Task Learning for Answer Extraction and Categorization","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2104.07219","title":"Multitasking Inhibits Semantic Drift","created":"2021-04-15","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":"2303.01788","title":"Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving","created":"2023-03-03","cited_by_count":8,"area":null},{"id":"2104.08675","title":"Dual-View Distilled BERT for Sentence Embedding","created":"2021-04-18","cited_by_count":7,"area":null},{"id":"2110.06961","title":"Language Modelling via Learning to Rank","created":"2021-10-13","cited_by_count":7,"area":null},{"id":"2202.13663","title":"Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation","created":"2022-02-28","cited_by_count":7,"area":"distill"},{"id":"2211.04898","title":"Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token","created":"2022-11-09","cited_by_count":7,"area":null},{"id":"2305.16638","title":"Adversarial Multi-task Learning for End-to-end Metaphor Detection","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2402.15082","title":"PEMT: Multi-Task Correlation Guided Mixture-of-Experts Enables Parameter-Efficient Transfer Learning","created":"2024-02-23","cited_by_count":7,"area":"moe"},{"id":"2403.16685","title":"ToXCL: A Unified Framework for Toxic Speech Detection and Explanation","created":"2024-03-25","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":"2109.12662","title":"Improving Question Answering Performance Using Knowledge Distillation and Active Learning","created":"2021-09-26","cited_by_count":6,"area":"distill"},{"id":"2210.09803","title":"Sentiment-Aware Word and Sentence Level Pre-training for Sentiment Analysis","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2212.10522","title":"Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2104.10516","title":"Improving BERT Pretraining with Syntactic Supervision","created":"2021-04-21","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":"2402.01863","title":"DFML: Decentralized Federated Mutual Learning","created":"2024-02-02","cited_by_count":4,"area":null},{"id":"2410.01483","title":"Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2107.13054","title":"Exceeding the Limits of Visual-Linguistic Multi-Task Learning","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2212.05998","title":"Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization","created":"2022-12-12","cited_by_count":3,"area":"distill"},{"id":"2301.03416","title":"ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation Generalization","created":"2023-01-09","cited_by_count":3,"area":"distill"},{"id":"2311.04040","title":"Data exploitation: multi-task learning of object detection and semantic segmentation on partially annotated data","created":"2023-11-07","cited_by_count":3,"area":"distill"},{"id":"2509.23915","title":"Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysis","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2103.13584","title":"BERT4SO: Neural Sentence Ordering by Fine-tuning BERT","created":"2021-03-25","cited_by_count":2,"area":null},{"id":"2104.06045","title":"Structural analysis of an all-purpose question answering model","created":"2021-04-13","cited_by_count":2,"area":null},{"id":"2312.15112","title":"Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation","created":"2023-12-22","cited_by_count":2,"area":"distill"},{"id":"2501.16226","title":"The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model","created":"2025-01-27","cited_by_count":2,"area":"distill"},{"id":"2103.08809","title":"Robustly Optimized and Distilled Training for Natural Language Understanding","created":"2021-03-16","cited_by_count":1,"area":null},{"id":"2111.03715","title":"Leveraging Sentiment Analysis Knowledge to Solve Emotion Detection Tasks","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2202.06987","title":"ASC me to Do Anything: Multi-task Training for Embodied AI","created":"2022-02-14","cited_by_count":1,"area":null},{"id":"2208.09129","title":"Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding","created":"2022-08-19","cited_by_count":1,"area":null},{"id":"2301.01572","title":"Multi-Task Learning with Prior Information","created":"2023-01-04","cited_by_count":1,"area":null},{"id":"2301.10887","title":"Improving Text-based Early Prediction by Distillation from Privileged Time-Series Text","created":"2023-01-26","cited_by_count":1,"area":null},{"id":"2306.10058","title":"EM-Network: Oracle Guided Self-distillation for Sequence Learning","created":"2023-06-14","cited_by_count":1,"area":"distill"},{"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":"2310.03188","title":"Talking Models: Distill Pre-trained Knowledge to Downstream Models via Interactive Communication","created":"2023-10-04","cited_by_count":1,"area":null},{"id":"2312.12786","title":"Heterogeneous Transfer Learning for Building High-Dimensional Generalized Linear Models with Disparate Datasets","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2409.20498","title":"Enhancing Romanian Offensive Language Detection through Knowledge Distillation, Multi-Task Learning, and Data Augmentation","created":"2024-09-30","cited_by_count":1,"area":"distill"},{"id":"2505.24413","title":"Multi-task Learning for Heterogeneous Multi-source Block-Wise Missing Data","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2106.08898","title":"RefBERT: Compressing BERT by Referencing to Pre-computed Representations","created":"2021-06-11","cited_by_count":0,"area":null},{"id":"2112.01048","title":"From Consensus to Disagreement: Multi-Teacher Distillation for Semi-Supervised Relation Extraction","created":"2021-12-02","cited_by_count":0,"area":null},{"id":"2203.05248","title":"Look Backward and Forward: Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine Translation","created":"2022-03-10","cited_by_count":0,"area":"distill"},{"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":"2305.16521","title":"Label Agnostic Pre-training for Zero-shot Text Classification","created":"2023-05-25","cited_by_count":0,"area":null},{"id":"2407.05315","title":"Topological Persistence Guided Knowledge Distillation for Wearable Sensor Data","created":"2024-07-07","cited_by_count":0,"area":"distill"},{"id":"2503.18565","title":"Distil-xLSTM: Learning Attention Mechanisms through Recurrent Structures","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2508.18192","title":"Unraveling the cognitive patterns of Large Language Models through module communities","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2603.03535","title":"Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient Experts","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2608.00129","title":"Progressive$^2$: A Teacher-Student Progressive Co-Evolving Knowledge Distillation Method for Substantial Model Compression","created":"2026-07-31","cited_by_count":0,"area":"distill"}],"next_cursor":null}