{"list":"other","total":54,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"2004.07211","title":"Dark Experience for General Continual Learning: a Strong, Simple Baseline","created":"2020-04-15","cited_by_count":911},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"1801.01423","title":"Overcoming catastrophic forgetting with hard attention to the task","created":"2018-01-04","cited_by_count":681},{"id":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"2211.13218","title":"CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning","created":"2022-11-23","cited_by_count":450},{"id":"1910.07104","title":"Orthogonal Gradient Descent for Continual Learning","created":"2019-10-15","cited_by_count":369},{"id":"2005.10200","title":"BERTweet: A pre-trained language model for English Tweets","created":"2020-05-20","cited_by_count":346},{"id":"1808.09602","title":"Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction","created":"2018-08-29","cited_by_count":322},{"id":"1904.00310","title":"Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting","created":"2019-03-31","cited_by_count":302},{"id":"2106.14413","title":"Co$^2$L: Contrastive Continual Learning","created":"2021-06-28","cited_by_count":244},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235},{"id":"2301.12314","title":"Progressive Prompts: Continual Learning for Language Models","created":"2023-01-29","cited_by_count":197},{"id":"1906.01076","title":"Episodic Memory in Lifelong Language Learning","created":"2019-06-03","cited_by_count":188},{"id":"1904.02232","title":"BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis","created":"2019-04-03","cited_by_count":176},{"id":"2110.03215","title":"Towards Continual Knowledge Learning of Language Models","created":"2021-10-07","cited_by_count":174},{"id":"1909.03329","title":"LAMOL: LAnguage MOdeling for Lifelong Language Learning","created":"2019-09-07","cited_by_count":160},{"id":"2103.07113","title":"Training Networks in Null Space of Feature Covariance for Continual Learning","created":"2021-03-12","cited_by_count":143},{"id":"2006.07114","title":"Knowledge Distillation Meets Self-Supervision","created":"2020-06-12","cited_by_count":142},{"id":"2203.14001","title":"Knowledge Distillation with the Reused Teacher Classifier","created":"2022-03-26","cited_by_count":141},{"id":"1902.09432","title":"Scalable and Order-robust Continual Learning with Additive Parameter Decomposition","created":"2019-02-25","cited_by_count":125},{"id":"1706.03466","title":"Few-Shot Image Recognition by Predicting Parameters from Activations","created":"2017-06-12","cited_by_count":122},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116},{"id":"2110.08534","title":"Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora","created":"2021-10-16","cited_by_count":115},{"id":"2110.07298","title":"LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5","created":"2021-10-14","cited_by_count":104},{"id":"2104.05489","title":"Continual Learning for Text Classification with Information Disentanglement Based Regularization","created":"2021-04-12","cited_by_count":86},{"id":"2205.09588","title":"How catastrophic can catastrophic forgetting be in linear regression?","created":"2022-05-19","cited_by_count":81},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75},{"id":"2203.06311","title":"ELLE: Efficient Lifelong Pre-training for Emerging Data","created":"2022-03-12","cited_by_count":70},{"id":"1905.05301","title":"Hierarchically Structured Meta-learning","created":"2019-05-13","cited_by_count":68},{"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":"2204.04763","title":"Information-theoretic Online Memory Selection for Continual Learning","created":"2022-04-10","cited_by_count":42},{"id":"2108.01958","title":"Learning Compatible Embeddings","created":"2021-08-04","cited_by_count":37},{"id":"2104.08808","title":"Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning","created":"2021-04-18","cited_by_count":35},{"id":"2110.15094","title":"Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data","created":"2021-10-27","cited_by_count":32},{"id":"2010.02123","title":"Lifelong Language Knowledge Distillation","created":"2020-10-05","cited_by_count":31},{"id":"2112.02714","title":"CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks","created":"2021-12-05","cited_by_count":29},{"id":"2109.07437","title":"Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative","created":"2021-09-15","cited_by_count":26},{"id":"2310.04993","title":"Prompt-augmented Temporal Point Process for Streaming Event Sequence","created":"2023-10-08","cited_by_count":24},{"id":"2301.08986","title":"Adapting a Language Model While Preserving its General Knowledge","created":"2023-01-21","cited_by_count":23}],"next_cursor":null}