{"list":"other","total":51,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"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":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"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":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"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":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"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":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"1508.00305","title":"Compositional Semantic Parsing on Semi-Structured Tables","created":"2015-08-03","cited_by_count":515},{"id":"1908.08351","title":"Compositionality decomposed: how do neural networks generalise?","created":"2019-08-22","cited_by_count":265},{"id":"2010.05465","title":"COGS: A Compositional Generalization Challenge Based on Semantic Interpretation","created":"2020-10-12","cited_by_count":263},{"id":"2105.11259","title":"PTR: Prompt Tuning with Rules for Text Classification","created":"2021-05-24","cited_by_count":238},{"id":"2010.03093","title":"WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization","created":"2020-10-07","cited_by_count":154},{"id":"2110.07560","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","created":"2021-10-14","cited_by_count":144},{"id":"1905.05908","title":"Task-Driven Modular Networks for Zero-Shot Compositional Learning","created":"2019-05-15","cited_by_count":121},{"id":"1904.06037","title":"Direct speech-to-speech translation with a sequence-to-sequence model","created":"2019-04-12","cited_by_count":118},{"id":"2102.01987","title":"Learning Graph Embeddings for Compositional Zero-shot Learning","created":"2021-02-03","cited_by_count":112},{"id":"2204.03044","title":"Fusing finetuned models for better pretraining","created":"2022-04-06","cited_by_count":110},{"id":"1810.07942","title":"Semantic Parsing for Task Oriented Dialog using Hierarchical Representations","created":"2018-10-18","cited_by_count":101},{"id":"2204.03574","title":"Learning to Compose Soft Prompts for Compositional Zero-Shot Learning","created":"2022-04-07","cited_by_count":67},{"id":"2109.03630","title":"Discrete and Soft Prompting for Multilingual Models","created":"2021-09-08","cited_by_count":49},{"id":"2109.14076","title":"RAFT: A Real-World Few-Shot Text Classification Benchmark","created":"2021-09-28","cited_by_count":44},{"id":"2010.05647","title":"Improving Compositional Generalization in Semantic Parsing","created":"2020-10-12","cited_by_count":42},{"id":"2104.08692","title":"MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs","created":"2021-04-18","cited_by_count":41},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40},{"id":"2203.12515","title":"A Survey on Cross-Lingual Summarization","created":"2022-03-23","cited_by_count":38},{"id":"2104.05196","title":"StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer","created":"2021-04-12","cited_by_count":34},{"id":"2203.10652","title":"Continual Sequence Generation with Adaptive Compositional Modules","created":"2022-03-20","cited_by_count":31},{"id":"1309.4408","title":"Lambda Dependency-Based Compositional Semantics","created":"2013-09-17","cited_by_count":26},{"id":"2103.07607","title":"Solving Compositional Reinforcement Learning Problems via Task Reduction","created":"2021-03-13","cited_by_count":19},{"id":"1711.11289","title":"Learning to Compose Skills","created":"2017-11-30","cited_by_count":15},{"id":"2001.01871","title":"Attention over Parameters for Dialogue Systems","created":"2020-01-07","cited_by_count":14},{"id":"1906.04854","title":"Task-Aware Feature Generation for Zero-Shot Compositional Learning","created":"2019-06-11","cited_by_count":11},{"id":"1910.14033","title":"Plan Arithmetic: Compositional Plan Vectors for Multi-Task Control","created":"2019-10-30","cited_by_count":11},{"id":"2203.09982","title":"CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding","created":"2022-03-18","cited_by_count":7},{"id":"2204.00996","title":"Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension","created":"2022-04-03","cited_by_count":6},{"id":"2110.04647","title":"Learning to Follow Language Instructions with Compositional Policies","created":"2021-10-09","cited_by_count":3},{"id":"2010.04826","title":"On Task-Level Dialogue Composition of Generative Transformer Model","created":"2020-10-09","cited_by_count":1}],"next_cursor":null}