{"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"1905.03197","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","created":"2019-05-08","cited_by_count":670},{"id":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1602.01585","title":"Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering","created":"2016-02-04","cited_by_count":520},{"id":"1904.03758","title":"Meta-Learning with Differentiable Convex Optimization","created":"2019-04-07","cited_by_count":461},{"id":"1805.10123","title":"TADAM: Task dependent adaptive metric for improved few-shot learning","created":"2018-05-23","cited_by_count":408},{"id":"1805.08136","title":"Meta-learning with differentiable closed-form solvers","created":"2018-05-21","cited_by_count":397},{"id":"1909.09157","title":"Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML","created":"2019-09-19","cited_by_count":359},{"id":"1703.00837","title":"Meta Networks","created":"2017-03-02","cited_by_count":269},{"id":"2010.15980","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","created":"2020-10-29","cited_by_count":249},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"2108.02035","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","created":"2021-08-04","cited_by_count":183},{"id":"1903.05566","title":"Benchmarking Natural Language Understanding Services for building Conversational Agents","created":"2019-03-13","cited_by_count":166},{"id":"2111.01998","title":"OpenPrompt: An Open-source Framework for Prompt-learning","created":"2021-11-03","cited_by_count":148},{"id":"2004.03829","title":"Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning","created":"2020-04-08","cited_by_count":139},{"id":"2203.07281","title":"GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models","created":"2022-03-14","cited_by_count":127},{"id":"2108.13161","title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners","created":"2021-08-30","cited_by_count":115},{"id":"2010.13641","title":"Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification","created":"2020-10-26","cited_by_count":98},{"id":"2203.00759","title":"HyperPrompt: Prompt-based Task-Conditioning of Transformers","created":"2022-03-01","cited_by_count":67},{"id":"1908.06039","title":"Few-shot Text Classification with Distributional Signatures","created":"2019-08-16","cited_by_count":58},{"id":"2203.09770","title":"Prototypical Verbalizer for Prompt-based Few-shot Tuning","created":"2022-03-18","cited_by_count":53},{"id":"2205.11200","title":"BBTv2: Towards a Gradient-Free Future with Large Language Models","created":"2022-05-23","cited_by_count":53},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45},{"id":"2209.11429","title":"News Category Dataset","created":"2022-09-23","cited_by_count":43},{"id":"2102.07121","title":"Multi-Objective Meta Learning","created":"2021-02-14","cited_by_count":39},{"id":"2205.01543","title":"Learning to Transfer Prompts for Text Generation","created":"2022-05-03","cited_by_count":22},{"id":"2209.11486","title":"MetaPrompting: Learning to Learn Better Prompts","created":"2022-09-23","cited_by_count":19},{"id":"2107.12262","title":"Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification","created":"2021-07-26","cited_by_count":18},{"id":"2305.09269","title":"ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification","created":"2023-05-16","cited_by_count":17}],"next_cursor":null}