{"list":"other","total":61,"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":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"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},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"2009.10297","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","created":"2020-09-22","cited_by_count":479},{"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":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361},{"id":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"2005.08025","title":"IntelliCode Compose: Code Generation Using Transformer","created":"2020-05-16","cited_by_count":227},{"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":"2303.15647","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","created":"2023-03-28","cited_by_count":173},{"id":"2106.03164","title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","created":"2021-06-06","cited_by_count":147},{"id":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141},{"id":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138},{"id":"2205.02022","title":"A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation","created":"2022-05-04","cited_by_count":98},{"id":"2202.07962","title":"Revisiting Parameter-Efficient Tuning: Are We Really There Yet?","created":"2022-02-16","cited_by_count":76},{"id":"2308.11396","title":"Towards an Understanding of Large Language Models in Software Engineering Tasks","created":"2023-08-22","cited_by_count":68},{"id":"2302.00438","title":"On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot","created":"2023-02-01","cited_by_count":64},{"id":"2212.08109","title":"An Empirical Study of Deep Learning Models for Vulnerability Detection","created":"2022-12-15","cited_by_count":46},{"id":"2112.02043","title":"Multilingual training for Software Engineering","created":"2021-12-03","cited_by_count":43},{"id":"2207.11680","title":"No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligence","created":"2022-07-24","cited_by_count":41},{"id":"2004.13651","title":"Fast and Memory-Efficient Neural Code Completion","created":"2020-04-28","cited_by_count":38},{"id":"2004.04881","title":"Improved Automatic Summarization of Subroutines via Attention to File Context","created":"2020-04-10","cited_by_count":34},{"id":"2204.09653","title":"On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages","created":"2022-04-05","cited_by_count":30},{"id":"2105.03953","title":"Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation","created":"2021-05-09","cited_by_count":29},{"id":"2112.02268","title":"Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding","created":"2021-12-04","cited_by_count":28},{"id":"2302.04026","title":"An Empirical Comparison of Pre-Trained Models of Source Code","created":"2023-02-08","cited_by_count":25},{"id":"2208.07120","title":"Compressing Pre-trained Models of Code into 3 MB","created":"2022-08-15","cited_by_count":21},{"id":"2304.05216","title":"Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyond","created":"2023-04-11","cited_by_count":20},{"id":"2209.10372","title":"WeLM: A Well-Read Pre-trained Language Model for Chinese","created":"2022-09-21","cited_by_count":19},{"id":"2303.15822","title":"One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization","created":"2023-03-28","cited_by_count":16},{"id":"2010.07987","title":"Empirical Study of Transformers for Source Code","created":"2020-10-15","cited_by_count":13},{"id":"2112.01184","title":"AST-Transformer: Encoding Abstract Syntax Trees Efficiently for Code Summarization","created":"2021-12-02","cited_by_count":11},{"id":"2302.04048","title":"Automating Code-Related Tasks Through Transformers: The Impact of Pre-training","created":"2023-02-08","cited_by_count":8},{"id":"2204.08653","title":"On The Cross-Modal Transfer from Natural Language to Code through Adapter Modules","created":"2022-04-19","cited_by_count":6},{"id":"2212.05901","title":"Parameter-Efficient Finetuning of Transformers for Source Code","created":"2022-12-12","cited_by_count":6},{"id":"2108.06614","title":"The SelectGen Challenge: Finding the Best Training Samples for Few-Shot Neural Text Generation","created":"2021-08-14","cited_by_count":5},{"id":"2007.11690","title":"Integrating Image Captioning with Rule-based Entity Masking","created":"2020-07-22","cited_by_count":4},{"id":"2303.06233","title":"Model-Agnostic Syntactical Information for Pre-Trained Programming Language Models","created":"2023-03-10","cited_by_count":4},{"id":"2109.11928","title":"Is the Number of Trainable Parameters All That Actually Matters?","created":"2021-09-24","cited_by_count":3}],"next_cursor":null}