{"total":29,"rows":[{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2105.12002","title":"Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization","created":"2021-05-25","cited_by_count":56,"area":null},{"id":"2105.09259","title":"Learning Language Specific Sub-network for Multilingual Machine Translation","created":"2021-05-19","cited_by_count":48,"area":null},{"id":"2308.12029","title":"Dual-Balancing for Multi-Task Learning","created":"2023-08-23","cited_by_count":27,"area":null},{"id":"2403.04861","title":"A Survey of Lottery Ticket Hypothesis","created":"2024-03-07","cited_by_count":24,"area":null},{"id":"2311.08273","title":"Examining Modularity in Multilingual LMs via Language-Specialized Subnetworks","created":"2023-11-14","cited_by_count":13,"area":null},{"id":"2209.05735","title":"Learning ASR pathways: A sparse multilingual ASR model","created":"2022-09-13","cited_by_count":12,"area":null},{"id":"2210.07565","title":"Multitask Pre-training of Modular Prompt for Chinese Few-Shot Learning","created":"2022-10-14","cited_by_count":11,"area":null},{"id":"2301.10410","title":"One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NER","created":"2023-01-25","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":"2106.14126","title":"AdaptCL: Efficient Collaborative Learning with Dynamic and Adaptive Pruning","created":"2021-06-27","cited_by_count":4,"area":null},{"id":"2401.12756","title":"What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2309.13018","title":"Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model","created":"2023-09-22","cited_by_count":3,"area":null},{"id":"2412.13488","title":"Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models","created":"2024-12-18","cited_by_count":3,"area":null},{"id":"2101.12431","title":"Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs","created":"2021-01-29","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":"2211.00106","title":"Data-Efficient Cross-Lingual Transfer with Language-Specific Subnetworks","created":"2022-10-31","cited_by_count":2,"area":null},{"id":"2302.14312","title":"Auxiliary Task-based Deep Reinforcement Learning for Quantum Control","created":"2023-02-28","cited_by_count":2,"area":null},{"id":"2308.12114","title":"Less is More -- Towards parsimonious multi-task models using structured sparsity","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2408.03913","title":"AdapMTL: Adaptive Pruning Framework for Multitask Learning Model","created":"2024-08-07","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":"2309.04802","title":"CPMR: Context-Aware Incremental Sequential Recommendation with Pseudo-Multi-Task Learning","created":"2023-09-09","cited_by_count":1,"area":null},{"id":"2409.01544","title":"Learning Task-Specific Sampling Strategy for Sparse-View CT Reconstruction","created":"2024-09-03","cited_by_count":1,"area":null},{"id":"2205.05832","title":"NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition","created":"2022-05-12","cited_by_count":0,"area":null},{"id":"2301.11560","title":"Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2301.12029","title":"Multi-task Highly Adaptive Lasso","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2312.16917","title":"Unified Lattice Graph Fusion for Chinese Named Entity Recognition","created":"2023-12-28","cited_by_count":0,"area":null},{"id":"2501.12115","title":"Meta-Sparsity: Learning Optimal Sparse Structures in Multi-task Networks through Meta-learning","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2510.18431","title":"ScaleNet: Scaling up Pretrained Neural Networks with Incremental Parameters","created":"2025-10-21","cited_by_count":0,"area":null}],"next_cursor":null}