{"list":"other","total":65,"rows":[{"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":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"1501.01571","title":"An Introduction to Matrix Concentration Inequalities","created":"2015-01-07","cited_by_count":397},{"id":"1803.00885","title":"Essentially No Barriers in Neural Network Energy Landscape","created":"2018-03-02","cited_by_count":330},{"id":"2104.08894","title":"The Intrinsic Dimension of Images and Its Impact on Learning","created":"2021-04-18","cited_by_count":315},{"id":"2110.06296","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","created":"2021-10-12","cited_by_count":291},{"id":"1905.12784","title":"Intrinsic dimension of data representations in deep neural networks","created":"2019-05-29","cited_by_count":282},{"id":"1806.00468","title":"Implicit Bias of Gradient Descent on Linear Convolutional Networks","created":"2018-06-01","cited_by_count":251},{"id":"1511.07543","title":"Convergent Learning: Do different neural networks learn the same representations?","created":"2015-11-24","cited_by_count":220},{"id":"1910.05653","title":"Model Fusion via Optimal Transport","created":"2019-10-12","cited_by_count":219},{"id":"1412.6544","title":"Qualitatively characterizing neural network optimization problems","created":"2014-12-19","cited_by_count":188},{"id":"2009.08576","title":"Pruning Neural Networks at Initialization: Why are We Missing the Mark?","created":"2020-09-18","cited_by_count":182},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154},{"id":"2105.12221","title":"Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances","created":"2021-05-25","cited_by_count":127},{"id":"2211.08403","title":"REPAIR: REnormalizing Permuted Activations for Interpolation Repair","created":"2022-11-15","cited_by_count":120},{"id":"2002.11448","title":"Predicting Neural Network Accuracy from Weights","created":"2020-02-26","cited_by_count":110},{"id":"1902.05040","title":"How do infinite width bounded norm networks look in function space?","created":"2019-02-13","cited_by_count":106},{"id":"1904.00687","title":"On the Power and Limitations of Random Features for Understanding Neural Networks","created":"2019-04-01","cited_by_count":103},{"id":"1307.1493","title":"Dropout Training as Adaptive Regularization","created":"2013-07-04","cited_by_count":93},{"id":"2009.02439","title":"Optimizing Mode Connectivity via Neuron Alignment","created":"2020-09-05","cited_by_count":86},{"id":"2002.05688","title":"Classifying the classifier: dissecting the weight space of neural networks","created":"2020-02-13","cited_by_count":65},{"id":"2205.14258","title":"On the Symmetries of Deep Learning Models and their Internal Representations","created":"2022-05-27","cited_by_count":64},{"id":"2209.14733","title":"Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights","created":"2022-09-29","cited_by_count":64},{"id":"2212.12042","title":"Re-basin via implicit Sinkhorn differentiation","created":"2022-12-22","cited_by_count":62},{"id":"2312.04501","title":"Graph Metanetworks for Processing Diverse Neural Architectures","created":"2023-12-07","cited_by_count":57},{"id":"2305.13546","title":"Neural Functional Transformers","created":"2023-05-22","cited_by_count":52},{"id":"2307.08286","title":"Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity","created":"2023-07-17","cited_by_count":50},{"id":"2206.06072","title":"Rank Diminishing in Deep Neural Networks","created":"2022-06-13","cited_by_count":47},{"id":"2306.06179","title":"Hidden symmetries of ReLU networks","created":"2023-06-09","cited_by_count":39},{"id":"1809.10749","title":"On the loss landscape of a class of deep neural networks with no bad local valleys","created":"2018-09-27","cited_by_count":38},{"id":"2310.05719","title":"Transformer Fusion with Optimal Transport","created":"2023-10-09","cited_by_count":36},{"id":"2506.13018","title":"Symmetry in Neural Network Parameter Spaces","created":"2025-06-16","cited_by_count":36},{"id":"2210.17216","title":"Symmetries, flat minima, and the conserved quantities of gradient flow","created":"2022-10-31","cited_by_count":35},{"id":"2310.13397","title":"Equivariant Deep Weight Space Alignment","created":"2023-10-20","cited_by_count":35},{"id":"2202.03038","title":"Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry","created":"2022-02-07","cited_by_count":28},{"id":"2205.10637","title":"Symmetry Teleportation for Accelerated Optimization","created":"2022-05-21","cited_by_count":25},{"id":"2310.19103","title":"Proving Linear Mode Connectivity of Neural Networks via Optimal Transport","created":"2023-10-29","cited_by_count":25},{"id":"2402.04081","title":"Improved Generalization of Weight Space Networks via Augmentations","created":"2024-02-06","cited_by_count":24},{"id":"2305.13404","title":"Improving Convergence and Generalization Using Parameter Symmetries","created":"2023-05-22","cited_by_count":23},{"id":"2307.06966","title":"Layer-wise Linear Mode Connectivity","created":"2023-07-13","cited_by_count":22},{"id":"2405.20231","title":"The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof","created":"2024-05-30","cited_by_count":21},{"id":"2405.17897","title":"$C^2M^3$: Cycle-Consistent Multi-Model Merging","created":"2024-05-28","cited_by_count":20},{"id":"2603.10090","title":"A Survey of Weight Space Learning: Understanding, Representation, and Generation","created":"2026-03-10","cited_by_count":18},{"id":"2410.10811","title":"Deep Linear Probe Generators for Weight Space Learning","created":"2024-10-14","cited_by_count":17},{"id":"2403.00986","title":"Merging Text Transformer Models from Different Initializations","created":"2024-03-01","cited_by_count":16},{"id":"2506.22712","title":"Generalized Linear Mode Connectivity for Transformers","created":"2025-06-28","cited_by_count":16},{"id":"2505.23681","title":"Understanding Mode Connectivity via Parameter Space Symmetry","created":"2025-05-29","cited_by_count":10},{"id":"2007.06737","title":"Representation Transfer by Optimal Transport","created":"2020-07-13","cited_by_count":8},{"id":"2408.15495","title":"Remove Symmetries to Control Model Expressivity and Improve Optimization","created":"2024-08-28","cited_by_count":8},{"id":"2506.02269","title":"A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models","created":"2025-06-02","cited_by_count":8},{"id":"2602.15727","title":"Spanning the Visual Analogy Space with a Weight Basis of LoRAs","created":"2026-02-17","cited_by_count":5},{"id":"2305.17559","title":"Pruning at Initialization -- A Sketching Perspective","created":"2023-05-27","cited_by_count":2},{"id":"2510.08023","title":"Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity","created":"2025-10-09","cited_by_count":2}],"next_cursor":null}