{"total":223,"rows":[{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896,"area":null},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719,"area":null},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320,"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":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230,"area":null},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214,"area":null},{"id":"2402.17193","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","created":"2024-02-27","cited_by_count":204,"area":null},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193,"area":null},{"id":"2106.03164","title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","created":"2021-06-06","cited_by_count":147,"area":null},{"id":"2205.06266","title":"Lifting the Curse of Multilinguality by Pre-training Modular Transformers","created":"2022-05-12","cited_by_count":146,"area":null},{"id":"2110.07560","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","created":"2021-10-14","cited_by_count":144,"area":null},{"id":"2305.18703","title":"Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey","created":"2023-05-30","cited_by_count":135,"area":null},{"id":"2105.09501","title":"Contrastive Learning for Many-to-many Multilingual Neural Machine Translation","created":"2021-05-20","cited_by_count":108,"area":null},{"id":"2302.07027","title":"AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models","created":"2023-02-14","cited_by_count":84,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2401.04151","title":"Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning","created":"2024-01-08","cited_by_count":82,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2407.18242","title":"LoRA-Pro: Are Low-Rank Adapters Properly Optimized?","created":"2024-07-25","cited_by_count":77,"area":null},{"id":"2104.08771","title":"Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation","created":"2021-04-18","cited_by_count":74,"area":null},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72,"area":null},{"id":"2106.01463","title":"Lightweight Adapter Tuning for Multilingual Speech Translation","created":"2021-06-02","cited_by_count":54,"area":null},{"id":"2107.05782","title":"Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task","created":"2021-07-12","cited_by_count":54,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2206.06122","title":"Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning","created":"2022-06-13","cited_by_count":50,"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":"2104.06951","title":"Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey","created":"2021-04-14","cited_by_count":46,"area":null},{"id":"2309.07098","title":"Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding","created":"2023-09-13","cited_by_count":42,"area":null},{"id":"2406.15079","title":"GOAL: A Generalist Combinatorial Optimization Agent Learner","created":"2024-06-21","cited_by_count":42,"area":null},{"id":"2104.08154","title":"Counter-Interference Adapter for Multilingual Machine Translation","created":"2021-04-16","cited_by_count":40,"area":null},{"id":"2312.10136","title":"Gradient-based Parameter Selection for Efficient Fine-Tuning","created":"2023-12-15","cited_by_count":40,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2401.07103","title":"Leveraging Large Language Models for NLG Evaluation: Advances and Challenges","created":"2024-01-13","cited_by_count":37,"area":null},{"id":"2105.11905","title":"Exploiting Adapters for Cross-lingual Low-resource Speech Recognition","created":"2021-05-18","cited_by_count":35,"area":null},{"id":"2110.06609","title":"MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators","created":"2021-10-13","cited_by_count":35,"area":null},{"id":"2105.07148","title":"Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter","created":"2021-05-15","cited_by_count":34,"area":null},{"id":"2303.11403","title":"eP-ALM: Efficient Perceptual Augmentation of Language Models","created":"2023-03-20","cited_by_count":34,"area":null},{"id":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","cited_by_count":34,"area":null},{"id":"2405.16156","title":"Mixture of In-Context Prompters for Tabular PFNs","created":"2024-05-25","cited_by_count":33,"area":null},{"id":"2112.08786","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","created":"2021-12-16","cited_by_count":32,"area":null},{"id":"2202.03218","title":"Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognition","created":"2022-02-07","cited_by_count":32,"area":null},{"id":"2109.06952","title":"Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech","created":"2021-09-14","cited_by_count":31,"area":null},{"id":"2308.11175","title":"MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation","created":"2023-08-22","cited_by_count":31,"area":null},{"id":"2305.02468","title":"Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System","created":"2023-05-04","cited_by_count":30,"area":null},{"id":"2205.00305","title":"AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks","created":"2022-04-30","cited_by_count":29,"area":null},{"id":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28,"area":null},{"id":"2311.09344","title":"Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization","created":"2023-11-15","cited_by_count":28,"area":null},{"id":"2103.11070","title":"Attribute Alignment: Controlling Text Generation from Pre-trained Language Models","created":"2021-03-20","cited_by_count":27,"area":null},{"id":"2109.04877","title":"Efficient Test Time Adapter Ensembling for Low-resource Language Varieties","created":"2021-09-10","cited_by_count":26,"area":null},{"id":"2204.02363","title":"Towards Best Practices for Training Multilingual Dense Retrieval Models","created":"2022-04-05","cited_by_count":26,"area":null},{"id":"2308.14316","title":"UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory","created":"2023-08-28","cited_by_count":26,"area":null},{"id":"2109.09991","title":"Learning Kernel-Smoothed Machine Translation with Retrieved Examples","created":"2021-09-21","cited_by_count":25,"area":null},{"id":"2305.16597","title":"Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models","created":"2023-05-26","cited_by_count":25,"area":null},{"id":"2212.10503","title":"Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow Training","created":"2022-12-20","cited_by_count":24,"area":null},{"id":"2305.14224","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2105.06232","title":"Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters","created":"2021-05-13","cited_by_count":23,"area":null},{"id":"2107.06569","title":"Importance-based Neuron Allocation for Multilingual Neural Machine Translation","created":"2021-07-14","cited_by_count":23,"area":null},{"id":"2301.07851","title":"From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition","created":"2023-01-19","cited_by_count":23,"area":null},{"id":"2110.10472","title":"Multilingual Unsupervised Neural Machine Translation with Denoising Adapters","created":"2021-10-20","cited_by_count":22,"area":null},{"id":"2205.12148","title":"Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer","created":"2022-05-24","cited_by_count":22,"area":null},{"id":"2104.07908","title":"MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2110.09574","title":"Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters","created":"2021-10-18","cited_by_count":21,"area":null},{"id":"2205.12230","title":"Chunk-based Nearest Neighbor Machine Translation","created":"2022-05-24","cited_by_count":21,"area":null},{"id":"2212.10551","title":"Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation","created":"2022-12-20","cited_by_count":21,"area":null},{"id":"2109.06604","title":"Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation","created":"2021-09-14","cited_by_count":20,"area":null},{"id":"2404.11201","title":"Neuron Specialization: Leveraging intrinsic task modularity for multilingual machine translation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2303.17051","title":"Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation","created":"2023-03-29","cited_by_count":17,"area":null},{"id":"2309.06922","title":"Hydra: Multi-head Low-rank Adaptation for Parameter Efficient Fine-tuning","created":"2023-09-13","cited_by_count":17,"area":null},{"id":"2105.04512","title":"End-to-End Speech Translation with Pre-trained Models and Adapters: UPC at IWSLT 2021","created":"2021-05-10","cited_by_count":16,"area":null},{"id":"2107.04239","title":"A Survey on Low-Resource Neural Machine Translation","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2205.02170","title":"Efficient Few-Shot Fine-Tuning for Opinion Summarization","created":"2022-05-04","cited_by_count":16,"area":null},{"id":"2103.13678","title":"Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation","created":"2021-03-25","cited_by_count":15,"area":null},{"id":"2205.10835","title":"Multilingual Machine Translation with Hyper-Adapters","created":"2022-05-22","cited_by_count":15,"area":null},{"id":"2306.02767","title":"Cross-Lingual Transfer with Target Language-Ready Task Adapters","created":"2023-06-05","cited_by_count":15,"area":null},{"id":"2207.03509","title":"Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptation","created":"2022-07-07","cited_by_count":14,"area":null},{"id":"2209.15236","title":"Language-Family Adapters for Low-Resource Multilingual Neural Machine Translation","created":"2022-09-30","cited_by_count":14,"area":null},{"id":"2303.09128","title":"Exploring Distributional Shifts in Large Language Models for Code Analysis","created":"2023-03-16","cited_by_count":14,"area":null},{"id":"2310.16870","title":"MACP: Efficient Model Adaptation for Cooperative Perception","created":"2023-10-25","cited_by_count":14,"area":null},{"id":"2404.08417","title":"AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees","created":"2024-04-12","cited_by_count":14,"area":null},{"id":"2302.03194","title":"UDApter -- Efficient Domain Adaptation Using Adapters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2305.02665","title":"Learning Language-Specific Layers for Multilingual Machine Translation","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2409.19458","title":"Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach","created":"2024-09-28","cited_by_count":13,"area":null},{"id":"2105.03010","title":"Efficient Weight factorization for Multilingual Speech Recognition","created":"2021-05-07","cited_by_count":12,"area":null},{"id":"2110.10478","title":"Continual Learning in Multilingual NMT via Language-Specific Embeddings","created":"2021-10-20","cited_by_count":12,"area":null},{"id":"2205.01557","title":"Training Mixed-Domain Translation Models via Federated Learning","created":"2022-05-03","cited_by_count":12,"area":null},{"id":"2205.11211","title":"Non-Parametric Domain Adaptation for End-to-End Speech Translation","created":"2022-05-23","cited_by_count":12,"area":null},{"id":"2302.12188","title":"Simple and Scalable Nearest Neighbor Machine Translation","created":"2023-02-23","cited_by_count":12,"area":null},{"id":"2109.15254","title":"SlovakBERT: Slovak Masked Language Model","created":"2021-09-30","cited_by_count":11,"area":null},{"id":"2302.11521","title":"How Does In-Context Learning Help Prompt Tuning?","created":"2023-02-22","cited_by_count":11,"area":null},{"id":"2402.12279","title":"Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks","created":"2024-02-19","cited_by_count":11,"area":null},{"id":"2407.07523","title":"SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning","created":"2024-07-10","cited_by_count":11,"area":null},{"id":"2109.06679","title":"Efficient Inference for Multilingual Neural Machine Translation","created":"2021-09-14","cited_by_count":10,"area":null},{"id":"2210.15868","title":"Residual Adapters for Few-Shot Text-to-Speech Speaker Adaptation","created":"2022-10-28","cited_by_count":10,"area":null},{"id":"2212.11414","title":"Improving Automated Program Repair with Domain Adaptation","created":"2022-12-21","cited_by_count":10,"area":null},{"id":"2301.12596","title":"Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining","created":"2023-01-30","cited_by_count":10,"area":null},{"id":"2401.06072","title":"Chain of History: Learning and Forecasting with LLMs for Temporal Knowledge Graph Completion","created":"2024-01-11","cited_by_count":10,"area":null},{"id":"2411.01800","title":"Expanding Sparse Tuning for Low Memory Usage","created":"2024-11-04","cited_by_count":10,"area":null},{"id":"2506.23271","title":"Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation","created":"2025-06-29","cited_by_count":10,"area":null},{"id":"2108.07886","title":"Modulating Language Models with Emotions","created":"2021-08-17","cited_by_count":9,"area":null},{"id":"2205.12304","title":"Adaptive multilingual speech recognition with pretrained models","created":"2022-05-24","cited_by_count":9,"area":null}],"next_cursor":"100"}