{"list":"other","total":57,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2010.09670","title":"RobustBench: a standardized adversarial robustness benchmark","created":"2020-10-19","cited_by_count":661},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1902.09635","title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","created":"2019-02-25","cited_by_count":344},{"id":"1506.06579","title":"Understanding Neural Networks Through Deep Visualization","created":"2015-06-22","cited_by_count":334},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260},{"id":"1702.04595","title":"Visualizing Deep Neural Network Decisions: Prediction Difference Analysis","created":"2017-02-15","cited_by_count":166},{"id":"1506.02078","title":"Visualizing and Understanding Recurrent Networks","created":"2015-06-05","cited_by_count":160},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147},{"id":"2002.06716","title":"Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data","created":"2020-02-17","cited_by_count":115},{"id":"2002.11448","title":"Predicting Neural Network Accuracy from Weights","created":"2020-02-26","cited_by_count":110},{"id":"2205.01580","title":"Better plain ViT baselines for ImageNet-1k","created":"2022-05-03","cited_by_count":98},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97},{"id":"2110.13100","title":"Parameter Prediction for Unseen Deep Architectures","created":"2021-10-25","cited_by_count":89},{"id":"1802.08241","title":"Hessian-based Analysis of Large Batch Training and Robustness to Adversaries","created":"2018-02-22","cited_by_count":87},{"id":"2209.12892","title":"Learning to Learn with Generative Models of Neural Network Checkpoints","created":"2022-09-26","cited_by_count":86},{"id":"2103.12718","title":"Self-Supervised Pretraining Improves Self-Supervised Pretraining","created":"2021-03-23","cited_by_count":82},{"id":"2205.13320","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","created":"2022-05-26","cited_by_count":81},{"id":"2002.05688","title":"Classifying the classifier: dissecting the weight space of neural networks","created":"2020-02-13","cited_by_count":65},{"id":"2209.14733","title":"Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights","created":"2022-09-29","cited_by_count":64},{"id":"2403.12143","title":"Graph Neural Networks for Learning Equivariant Representations of Neural Networks","created":"2024-03-18","cited_by_count":59},{"id":"2312.04501","title":"Graph Metanetworks for Processing Diverse Neural Architectures","created":"2023-12-07","cited_by_count":57},{"id":"1901.11058","title":"HyperGAN: A Generative Model for Diverse, Performant Neural Networks","created":"2019-01-30","cited_by_count":51},{"id":"2406.09997","title":"Towards Scalable and Versatile Weight Space Learning","created":"2024-06-14","cited_by_count":41},{"id":"2209.14764","title":"Model Zoos: A Dataset of Diverse Populations of Neural Network Models","created":"2022-09-29","cited_by_count":39},{"id":"2311.18823","title":"Initializing Models with Larger Ones","created":"2023-11-30","cited_by_count":39},{"id":"1904.05878","title":"Knowledge Flow: Improve Upon Your Teachers","created":"2019-04-11","cited_by_count":36},{"id":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34},{"id":"2201.00519","title":"Stochastic Weight Averaging Revisited","created":"2022-01-03","cited_by_count":26},{"id":"2402.05232","title":"Universal Neural Functionals","created":"2024-02-07","cited_by_count":26},{"id":"2410.04207","title":"Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models","created":"2024-10-05","cited_by_count":22},{"id":"2410.10811","title":"Deep Linear Probe Generators for Weight Space Learning","created":"2024-10-14","cited_by_count":17},{"id":"2205.10660","title":"Vision Transformers in 2022: An Update on Tiny ImageNet","created":"2022-05-21","cited_by_count":13},{"id":"2207.10951","title":"Hyper-Representations for Pre-Training and Transfer Learning","created":"2022-07-22","cited_by_count":12},{"id":"2210.09236","title":"ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization","created":"2022-10-17","cited_by_count":12},{"id":"2405.18432","title":"Unsupervised Model Tree Heritage Recovery","created":"2024-05-28","cited_by_count":11},{"id":"2406.11129","title":"Neural Lineage","created":"2024-06-17","cited_by_count":9},{"id":"2503.17138","title":"Structure Is Not Enough: Leveraging Behavior for Neural Network Weight Reconstruction","created":"2025-03-21","cited_by_count":6},{"id":"2304.13718","title":"Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models","created":"2023-04-26","cited_by_count":4},{"id":"2406.16988","title":"MD tree: a model-diagnostic tree grown on loss landscape","created":"2024-06-24","cited_by_count":3}],"next_cursor":null}