{"list":"other","total":91,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"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":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1807.05118","title":"Tune: A Research Platform for Distributed Model Selection and Training","created":"2018-07-13","cited_by_count":395},{"id":"2110.09348","title":"Understanding Dimensional Collapse in Contrastive Self-supervised Learning","created":"2021-10-18","cited_by_count":378},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1506.06579","title":"Understanding Neural Networks Through Deep Visualization","created":"2015-06-22","cited_by_count":334},{"id":"1803.00885","title":"Essentially No Barriers in Neural Network Energy Landscape","created":"2018-03-02","cited_by_count":330},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"1909.02729","title":"A Baseline for Few-Shot Image Classification","created":"2019-09-06","cited_by_count":298},{"id":"1511.05641","title":"Net2Net: Accelerating Learning via Knowledge Transfer","created":"2015-11-18","cited_by_count":250},{"id":"1705.07857","title":"Real Time Image Saliency for Black Box Classifiers","created":"2017-05-22","cited_by_count":246},{"id":"1306.0543","title":"Predicting Parameters in Deep Learning","created":"2013-06-03","cited_by_count":224},{"id":"1810.01075","title":"Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning","created":"2018-10-02","cited_by_count":215},{"id":"1706.08500","title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","created":"2017-06-26","cited_by_count":213},{"id":"1708.05344","title":"SMASH: One-Shot Model Architecture Search through HyperNetworks","created":"2017-08-17","cited_by_count":202},{"id":"1412.6544","title":"Qualitatively characterizing neural network optimization problems","created":"2014-12-19","cited_by_count":188},{"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":"1903.12436","title":"From Variational to Deterministic Autoencoders","created":"2019-03-29","cited_by_count":133},{"id":"1810.05749","title":"Graph HyperNetworks for Neural Architecture Search","created":"2018-10-12","cited_by_count":132},{"id":"1906.07697","title":"Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes","created":"2019-06-18","cited_by_count":131},{"id":"2011.02803","title":"Intriguing Properties of Contrastive Losses","created":"2020-11-05","cited_by_count":130},{"id":"1511.06422","title":"All you need is a good init","created":"2015-11-19","cited_by_count":124},{"id":"2109.05070","title":"Instance-Conditioned GAN","created":"2021-09-10","cited_by_count":121},{"id":"1810.00113","title":"Predicting the Generalization Gap in Deep Networks with Margin Distributions","created":"2018-09-28","cited_by_count":113},{"id":"2002.11448","title":"Predicting Neural Network Accuracy from Weights","created":"2020-02-26","cited_by_count":110},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110},{"id":"2301.12780","title":"Equivariant Architectures for Learning in Deep Weight Spaces","created":"2023-01-30","cited_by_count":107},{"id":"1606.05233","title":"Learning feed-forward one-shot learners","created":"2016-06-16","cited_by_count":93},{"id":"2110.13100","title":"Parameter Prediction for Unseen Deep Architectures","created":"2021-10-25","cited_by_count":89},{"id":"2209.12892","title":"Learning to Learn with Generative Models of Neural Network Checkpoints","created":"2022-09-26","cited_by_count":86},{"id":"2205.13320","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","created":"2022-05-26","cited_by_count":81},{"id":"2102.13042","title":"Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling","created":"2021-02-25","cited_by_count":75},{"id":"2302.14040","title":"Permutation Equivariant Neural Functionals","created":"2023-02-27","cited_by_count":70},{"id":"2209.14733","title":"Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights","created":"2022-09-29","cited_by_count":64},{"id":"2302.05438","title":"Deep Learning on Implicit Neural Representations of Shapes","created":"2023-02-10","cited_by_count":63},{"id":"2403.12143","title":"Graph Neural Networks for Learning Equivariant Representations of Neural Networks","created":"2024-03-18","cited_by_count":59},{"id":"2201.04182","title":"HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning","created":"2022-01-11","cited_by_count":55},{"id":"2106.03027","title":"Model Zoo: A Growing \"Brain\" That Learns Continually","created":"2021-06-06","cited_by_count":54},{"id":"1901.11058","title":"HyperGAN: A Generative Model for Diverse, Performant Neural Networks","created":"2019-01-30","cited_by_count":51},{"id":"2102.08098","title":"GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training","created":"2021-02-16","cited_by_count":44},{"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":"2306.06179","title":"Hidden symmetries of ReLU networks","created":"2023-06-09","cited_by_count":39},{"id":"2106.15434","title":"Zoo-Tuning: Adaptive Transfer from a Zoo of Models","created":"2021-06-29","cited_by_count":35},{"id":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34},{"id":"2311.02428","title":"Task Arithmetic with LoRA for Continual Learning","created":"2023-11-04","cited_by_count":32},{"id":"2303.04143","title":"Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?","created":"2023-03-07","cited_by_count":29},{"id":"2104.11044","title":"Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes","created":"2021-04-22","cited_by_count":28},{"id":"1806.10317","title":"Adversarial Distillation of Bayesian Neural Network Posteriors","created":"2018-06-27","cited_by_count":27},{"id":"2402.05232","title":"Universal Neural Functionals","created":"2024-02-07","cited_by_count":26},{"id":"2202.02842","title":"Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data","created":"2022-02-06","cited_by_count":19},{"id":"2403.11998","title":"Learning Useful Representations of Recurrent Neural Network Weight Matrices","created":"2024-03-18","cited_by_count":15},{"id":"2207.10951","title":"Hyper-Representations for Pre-Training and Transfer Learning","created":"2022-07-22","cited_by_count":12},{"id":"1801.01952","title":"Generating Neural Networks with Neural Networks","created":"2018-01-06","cited_by_count":10},{"id":"2007.12446","title":"Transferred Discrepancy: Quantifying the Difference Between Representations","created":"2020-07-24","cited_by_count":9},{"id":"2210.08942","title":"Meta-Learning via Classifier(-free) Diffusion Guidance","created":"2022-10-17","cited_by_count":9},{"id":"2305.16625","title":"Set-based Neural Network Encoding Without Weight Tying","created":"2023-05-26","cited_by_count":9},{"id":"1909.03611","title":"An Acceleration Framework for High Resolution Image Synthesis","created":"2019-09-09","cited_by_count":6},{"id":"1904.01399","title":"On Geometric Structure of Activation Spaces in Neural Networks","created":"2019-04-02","cited_by_count":4},{"id":"2304.13718","title":"Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models","created":"2023-04-26","cited_by_count":4},{"id":"1808.05377","title":"Neural Architecture Search: A Survey","created":"2018-08-16","cited_by_count":3},{"id":"2302.08183","title":"Singular Value Representation: A New Graph Perspective On Neural Networks","created":"2023-02-16","cited_by_count":3},{"id":"1901.00884","title":"Subspace Match Probably Does Not Accurately Assess the Similarity of Learned Representations","created":"2019-01-03","cited_by_count":2},{"id":"2307.12941","title":"On Privileged and Convergent Bases in Neural Network Representations","created":"2023-07-24","cited_by_count":2}],"next_cursor":null}