{"list":"other","total":59,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"1708.01547","title":"Lifelong Learning with Dynamically Expandable Networks","created":"2017-08-04","cited_by_count":694},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1910.07475","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","created":"2019-10-16","cited_by_count":340},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"2006.04884","title":"On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines","created":"2020-06-08","cited_by_count":255},{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214},{"id":"2210.11466","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","created":"2022-10-20","cited_by_count":205},{"id":"2010.15110","title":"Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel","created":"2020-10-28","cited_by_count":187},{"id":"1909.11957","title":"Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks","created":"2019-09-26","cited_by_count":160},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145},{"id":"1906.02337","title":"MNIST-C: A Robustness Benchmark for Computer Vision","created":"2019-06-05","cited_by_count":138},{"id":"2104.06979","title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning","created":"2021-04-14","cited_by_count":116},{"id":"2002.10365","title":"The Early Phase of Neural Network Training","created":"2020-02-24","cited_by_count":115},{"id":"2302.07011","title":"A Modern Look at the Relationship between Sharpness and Generalization","created":"2023-02-14","cited_by_count":92},{"id":"2211.14238","title":"Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time","created":"2022-11-25","cited_by_count":90},{"id":"2010.04925","title":"Regularizing Neural Networks via Adversarial Model Perturbation","created":"2020-10-10","cited_by_count":78},{"id":"2201.05125","title":"GradMax: Growing Neural Networks using Gradient Information","created":"2022-01-13","cited_by_count":66},{"id":"2012.14193","title":"Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization","created":"2020-12-28","cited_by_count":62},{"id":"2206.10654","title":"On the Maximum Hessian Eigenvalue and Generalization","created":"2022-06-21","cited_by_count":57},{"id":"1809.00388","title":"MTNT: A Testbed for Machine Translation of Noisy Text","created":"2018-09-02","cited_by_count":54},{"id":"1905.13277","title":"Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence","created":"2019-05-30","cited_by_count":54},{"id":"2010.12562","title":"On the Transformer Growth for Progressive BERT Training","created":"2020-10-23","cited_by_count":49},{"id":"2305.18761","title":"Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias","created":"2023-05-30","cited_by_count":44},{"id":"1810.09774","title":"Testing the Generalization Power of Neural Network Models Across NLI Benchmarks","created":"2018-10-23","cited_by_count":15},{"id":"2210.04643","title":"Critical Learning Periods for Multisensory Integration in Deep Networks","created":"2022-10-06","cited_by_count":14},{"id":"2303.01475","title":"Over-training with Mixup May Hurt Generalization","created":"2023-03-02","cited_by_count":13},{"id":"2308.12221","title":"Critical Learning Periods Emerge Even in Deep Linear Networks","created":"2023-08-23","cited_by_count":13},{"id":"2403.03375","title":"Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlations","created":"2024-03-05","cited_by_count":12},{"id":"2301.05487","title":"FUN with Fisher: Improving Generalization of Adapter-Based Cross-lingual Transfer with Scheduled Unfreezing","created":"2023-01-13","cited_by_count":8}],"next_cursor":null}