{"list":"other","total":53,"rows":[{"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":"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":"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":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"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":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"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":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"1507.00504","title":"Optimal Transport for Domain Adaptation","created":"2015-07-02","cited_by_count":463},{"id":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"id":"2002.01808","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","created":"2020-02-05","cited_by_count":319},{"id":"2003.13216","title":"Learning to Learn Single Domain Generalization","created":"2020-03-30","cited_by_count":296},{"id":"1804.06516","title":"Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization","created":"2018-04-18","cited_by_count":294},{"id":"1804.10745","title":"Generalizing Across Domains via Cross-Gradient Training","created":"2018-04-28","cited_by_count":268},{"id":"1909.00889","title":"Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data","created":"2019-09-02","cited_by_count":246},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232},{"id":"2003.06054","title":"Deep Domain-Adversarial Image Generation for Domain Generalisation","created":"2020-03-12","cited_by_count":231},{"id":"2010.07922","title":"Representation Learning via Invariant Causal Mechanisms","created":"2020-10-15","cited_by_count":199},{"id":"2103.08493","title":"How Many Data Points is a Prompt Worth?","created":"2021-03-15","cited_by_count":198},{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115},{"id":"2012.00417","title":"Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification","created":"2020-12-01","cited_by_count":110},{"id":"1810.10093","title":"Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data","created":"2018-10-23","cited_by_count":94},{"id":"2106.01899","title":"Adversarially Adaptive Normalization for Single Domain Generalization","created":"2021-06-01","cited_by_count":85},{"id":"2205.11961","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","created":"2022-05-24","cited_by_count":85},{"id":"2103.05327","title":"BERTese: Learning to Speak to BERT","created":"2021-03-09","cited_by_count":82},{"id":"2007.01807","title":"Continuously Indexed Domain Adaptation","created":"2020-07-03","cited_by_count":75},{"id":"2111.06719","title":"On Transferability of Prompt Tuning for Natural Language Processing","created":"2021-11-12","cited_by_count":75},{"id":"2103.15796","title":"Adaptive Methods for Real-World Domain Generalization","created":"2021-03-29","cited_by_count":66},{"id":"1809.01361","title":"A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation","created":"2018-09-05","cited_by_count":62},{"id":"2105.07029","title":"Learning a Universal Template for Few-shot Dataset Generalization","created":"2021-05-14","cited_by_count":61},{"id":"2206.04038","title":"Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting","created":"2022-06-08","cited_by_count":54},{"id":"2010.11988","title":"Meta-Learning for Domain Generalization in Semantic Parsing","created":"2020-10-22","cited_by_count":41},{"id":"2205.10664","title":"Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks","created":"2022-05-21","cited_by_count":33},{"id":"1903.07062","title":"AdaGraph: Unifying Predictive and Continuous Domain Adaptation through Graphs","created":"2019-03-17","cited_by_count":32},{"id":"2108.06721","title":"Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time","created":"2021-08-15","cited_by_count":28},{"id":"1811.05939","title":"Domain Randomization for Scene-Specific Car Detection and Pose Estimation","created":"2018-11-14","cited_by_count":23},{"id":"2003.04382","title":"Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay","created":"2020-03-09","cited_by_count":19},{"id":"2103.00229","title":"Neuron Coverage-Guided Domain Generalization","created":"2021-02-27","cited_by_count":19},{"id":"2002.05660","title":"Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization","created":"2020-02-13","cited_by_count":14},{"id":"2202.02403","title":"Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series","created":"2022-02-04","cited_by_count":14},{"id":"2011.07347","title":"Conditioned Natural Language Generation using only Unconditioned Language Model: An Exploration","created":"2020-11-14","cited_by_count":12},{"id":"2108.13597","title":"Self-balanced Learning For Domain Generalization","created":"2021-08-31","cited_by_count":5}],"next_cursor":null}