{"list":"other","total":83,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"1801.01423","title":"Overcoming catastrophic forgetting with hard attention to the task","created":"2018-01-04","cited_by_count":681},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"2005.00052","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","created":"2020-04-30","cited_by_count":445},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"1905.07553","title":"Which Tasks Should Be Learned Together in Multi-task Learning?","created":"2019-05-18","cited_by_count":375},{"id":"2009.09796","title":"Multi-Task Learning with Deep Neural Networks: A Survey","created":"2020-09-10","cited_by_count":375},{"id":"1901.11504","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","created":"2019-01-31","cited_by_count":350},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"1909.03683","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","created":"2019-09-09","cited_by_count":280},{"id":"1906.00695","title":"Continual learning with hypernetworks","created":"2019-06-03","cited_by_count":273},{"id":"2105.11259","title":"PTR: Prompt Tuning with Rules for Text Classification","created":"2021-05-24","cited_by_count":238},{"id":"1806.08730","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","created":"2018-06-20","cited_by_count":236},{"id":"1907.12412","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","created":"2019-07-29","cited_by_count":231},{"id":"1810.12488","title":"Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines","created":"2018-10-30","cited_by_count":228},{"id":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","cited_by_count":224},{"id":"2002.12804","title":"UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training","created":"2020-02-28","cited_by_count":204},{"id":"2101.11038","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","created":"2021-01-26","cited_by_count":192},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161},{"id":"2011.09926","title":"Challenges in Deploying Machine Learning: a Survey of Case Studies","created":"2020-11-18","cited_by_count":152},{"id":"2005.00770","title":"Exploring and Predicting Transferability across NLP Tasks","created":"2020-05-02","cited_by_count":128},{"id":"2112.06409","title":"Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective","created":"2021-12-13","cited_by_count":116},{"id":"2005.00944","title":"Understanding and Improving Information Transfer in Multi-Task Learning","created":"2020-05-02","cited_by_count":114},{"id":"2004.08900","title":"The Cost of Training NLP Models: A Concise Overview","created":"2020-04-19","cited_by_count":98},{"id":"2112.02706","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","created":"2021-12-05","cited_by_count":91},{"id":"1706.05137","title":"One Model To Learn Them All","created":"2017-06-16","cited_by_count":87},{"id":"1907.04829","title":"BAM! Born-Again Multi-Task Networks for Natural Language Understanding","created":"2019-07-10","cited_by_count":85},{"id":"2211.12701","title":"Continual Learning of Natural Language Processing Tasks: A Survey","created":"2022-11-23","cited_by_count":83},{"id":"2203.00759","title":"HyperPrompt: Prompt-based Task-Conditioning of Transformers","created":"2022-03-01","cited_by_count":67},{"id":"2008.05221","title":"Compression of Deep Learning Models for Text: A Survey","created":"2020-08-12","cited_by_count":64},{"id":"2109.09138","title":"Multi-Task Learning in Natural Language Processing: An Overview","created":"2021-09-19","cited_by_count":62},{"id":"2110.10234","title":"Collaboration Challenges in Building ML-Enabled Systems: Communication, Documentation, Engineering, and Process","created":"2021-10-19","cited_by_count":56},{"id":"2102.07952","title":"A Survey of Machine Learning for Computer Architecture and Systems","created":"2021-02-16","cited_by_count":53},{"id":"1606.04038","title":"Trace Norm Regularised Deep Multi-Task Learning","created":"2016-06-13","cited_by_count":50},{"id":"2009.09139","title":"Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data","created":"2020-09-19","cited_by_count":50},{"id":"2112.03271","title":"Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks","created":"2021-12-06","cited_by_count":46},{"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},{"id":"1810.09583","title":"Model Selection Techniques -- An Overview","created":"2018-10-22","cited_by_count":36},{"id":"2104.08808","title":"Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning","created":"2021-04-18","cited_by_count":35},{"id":"2203.03903","title":"InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NER","created":"2022-03-08","cited_by_count":31},{"id":"1705.08142","title":"Latent Multi-task Architecture Learning","created":"2017-05-23","cited_by_count":29},{"id":"2007.16008","title":"Multi-task learning for natural language processing in the 2020s: where are we going?","created":"2020-07-22","cited_by_count":27},{"id":"1907.07804","title":"OmniNet: A unified architecture for multi-modal multi-task learning","created":"2019-07-17","cited_by_count":25},{"id":"1908.01707","title":"Learning a Unified Embedding for Visual Search at Pinterest","created":"2019-08-05","cited_by_count":25},{"id":"1810.09591","title":"Applying Deep Learning To Airbnb Search","created":"2018-10-22","cited_by_count":24},{"id":"1909.06434","title":"Adaptive Scheduling for Multi-Task Learning","created":"2019-09-13","cited_by_count":24},{"id":"1904.04153","title":"AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning","created":"2019-04-08","cited_by_count":22},{"id":"2007.01126","title":"A Brief Review of Deep Multi-task Learning and Auxiliary Task Learning","created":"2020-07-02","cited_by_count":18},{"id":"1806.08028","title":"Gradient Adversarial Training of Neural Networks","created":"2018-06-21","cited_by_count":17},{"id":"2204.07600","title":"In-BoXBART: Get Instructions into Biomedical Multi-Task Learning","created":"2022-04-15","cited_by_count":16},{"id":"1708.00260","title":"Deep Asymmetric Multi-task Feature Learning","created":"2017-08-01","cited_by_count":15},{"id":"2006.09762","title":"Maximum Roaming Multi-Task Learning","created":"2020-06-17","cited_by_count":11},{"id":"2006.08671","title":"To Pretrain or Not to Pretrain: Examining the Benefits of Pretraining on Resource Rich Tasks","created":"2020-06-15","cited_by_count":10},{"id":"1903.00278","title":"Continuous Integration of Machine Learning Models with ease.ml/ci: Towards a Rigorous Yet Practical Treatment","created":"2019-03-01","cited_by_count":9},{"id":"2210.00859","title":"Requirements Engineering for Machine Learning: A Review and Reflection","created":"2022-10-03","cited_by_count":7},{"id":"2111.12146","title":"Sharing to learn and learning to share; Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning: A meta review","created":"2021-11-23","cited_by_count":6},{"id":"2007.05891","title":"HyperGrid: Efficient Multi-Task Transformers with Grid-wise Decomposable Hyper Projections","created":"2020-07-12","cited_by_count":3},{"id":"2210.14606","title":"Analyzing Multi-Task Learning for Abstractive Text Summarization","created":"2022-10-26","cited_by_count":3},{"id":"2211.06409","title":"Capabilities for Better ML Engineering","created":"2022-11-11","cited_by_count":3}],"next_cursor":null}