{"total":61,"rows":[{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2303.00980","title":"Learning to Grow Pretrained Models for Efficient Transformer Training","created":"2023-03-02","cited_by_count":83,"area":null},{"id":"2201.05125","title":"GradMax: Growing Neural Networks using Gradient Information","created":"2022-01-13","cited_by_count":66,"area":null},{"id":"2102.08574","title":"Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks","created":"2021-02-17","cited_by_count":49,"area":null},{"id":"2203.06211","title":"Staged Training for Transformer Language Models","created":"2022-03-11","cited_by_count":49,"area":null},{"id":"2211.09703","title":"EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones","created":"2022-11-17","cited_by_count":43,"area":null},{"id":"2203.14509","title":"Automated Progressive Learning for Efficient Training of Vision Transformers","created":"2022-03-28","cited_by_count":37,"area":null},{"id":"2305.02869","title":"Masked Structural Growth for 2x Faster Language Model Pre-training","created":"2023-05-04","cited_by_count":33,"area":null},{"id":"2103.16547","title":"The Elastic Lottery Ticket Hypothesis","created":"2021-03-30","cited_by_count":23,"area":null},{"id":"2202.08539","title":"When, where, and how to add new neurons to ANNs","created":"2022-02-17","cited_by_count":18,"area":null},{"id":"2204.07554","title":"Efficient Architecture Search for Diverse Tasks","created":"2022-04-15","cited_by_count":18,"area":null},{"id":"2405.08768","title":"EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training","created":"2024-05-14","cited_by_count":18,"area":null},{"id":"2310.11451","title":"Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective","created":"2023-10-17","cited_by_count":17,"area":null},{"id":"2202.07242","title":"Neural Architecture Search for Dense Prediction Tasks in Computer Vision","created":"2022-02-15","cited_by_count":12,"area":null},{"id":"2110.00908","title":"GROWN: GRow Only When Necessary for Continual Learning","created":"2021-10-03","cited_by_count":11,"area":null},{"id":"2203.12868","title":"DyRep: Bootstrapping Training with Dynamic Re-parameterization","created":"2022-03-24","cited_by_count":11,"area":null},{"id":"2211.01778","title":"Progressive Transformation Learning for Leveraging Virtual Images in Training","created":"2022-11-03","cited_by_count":10,"area":null},{"id":"2401.13330","title":"NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks","created":"2024-01-24","cited_by_count":9,"area":null},{"id":"2204.12726","title":"PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Search","created":"2022-04-27","cited_by_count":8,"area":null},{"id":"2210.05484","title":"Equivariance-aware Architectural Optimization of Neural Networks","created":"2022-10-11","cited_by_count":8,"area":null},{"id":"2306.12700","title":"Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation","created":"2023-06-22","cited_by_count":8,"area":null},{"id":"2301.04020","title":"Quant 4.0: Engineering Quantitative Investment with Automated, Explainable and Knowledge-driven Artificial Intelligence","created":"2022-12-13","cited_by_count":6,"area":null},{"id":"2101.07945","title":"Beyond Fine-tuning: Classifying High Resolution Mammograms using Function-Preserving Transformations","created":"2021-01-20","cited_by_count":5,"area":null},{"id":"2112.03395","title":"Manas: Mining Software Repositories to Assist AutoML","created":"2021-12-06","cited_by_count":5,"area":null},{"id":"2205.09219","title":"A Classification of $G$-invariant Shallow Neural Networks","created":"2022-05-18","cited_by_count":5,"area":null},{"id":"2502.13794","title":"LESA: Learnable LLM Layer Scaling-Up","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2106.08748","title":"Input Invex Neural Network","created":"2021-06-16","cited_by_count":4,"area":null},{"id":"2205.03960","title":"Neural Architecture Search using Property Guided Synthesis","created":"2022-05-08","cited_by_count":4,"area":null},{"id":"2306.11903","title":"Deep Fusion: Efficient Network Training via Pre-trained Initializations","created":"2023-06-20","cited_by_count":4,"area":null},{"id":"2406.02469","title":"Landscape-Aware Growing: The Power of a Little LAG","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2410.11878","title":"Neural Metamorphosis","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2508.08011","title":"Optimal Transport Depth Up-Scaling","created":"2025-08-11","cited_by_count":4,"area":null},{"id":"2111.07722","title":"Stacked BNAS: Rethinking Broad Convolutional Neural Network for Neural Architecture Search","created":"2021-11-15","cited_by_count":3,"area":null},{"id":"2401.03104","title":"When To Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks","created":"2024-01-06","cited_by_count":3,"area":null},{"id":"2102.12985","title":"A Novel Framework for Neural Architecture Search in the Hill Climbing Domain","created":"2021-02-22","cited_by_count":2,"area":null},{"id":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2212.14049","title":"Differentiable Search of Accurate and Robust Architectures","created":"2022-12-28","cited_by_count":2,"area":null},{"id":"2307.15621","title":"Shrink-Perturb Improves Architecture Mixing during Population Based Training for Neural Architecture Search","created":"2023-07-28","cited_by_count":2,"area":null},{"id":"2403.11173","title":"Multi-Objective Evolutionary Neural Architecture Search for Recurrent Neural Networks","created":"2024-03-17","cited_by_count":2,"area":null},{"id":"2106.07211","title":"Differentiable Neural Architecture Search with Morphism-based Transformable Backbone Architectures","created":"2021-06-14","cited_by_count":1,"area":null},{"id":"2301.12187","title":"Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming","created":"2023-01-28","cited_by_count":1,"area":null},{"id":"2311.15995","title":"SensLI: Sensitivity-Based Layer Insertion for Neural Networks","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2404.13515","title":"FedTrans: Efficient Federated Learning via Multi-Model Transformation","created":"2024-04-21","cited_by_count":1,"area":null},{"id":"2410.11038","title":"Towards a More Complete Theory of Function Preserving Transforms","created":"2024-10-14","cited_by_count":1,"area":null},{"id":"2603.08647","title":"Grow, Don't Overwrite: Fine-tuning Without Forgetting","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2604.04281","title":"Preservation Is Not Enough for Width Growth: Regime-Sensitive Selection of Dense LM Warm Starts","created":"2026-04-05","cited_by_count":1,"area":null},{"id":"2110.08857","title":"Growing Representation Learning","created":"2021-10-17","cited_by_count":0,"area":null},{"id":"2303.02733","title":"Reparameterization through Spatial Gradient Scaling","created":"2023-03-05","cited_by_count":0,"area":null},{"id":"2601.11618","title":"Architecture Before the Formula: Training-Dependent Computational Semantics in Transformers","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2602.23405","title":"Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.24313","title":"Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.13405","title":"When is Warmstarting Effective for Scaling Language Models?","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.15435","title":"On the Stability of Growth in Structural Plasticity: Forward-Active yet Backward-Starved","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.14346","title":"Squeeze-Release: Iterative Pruning with Exact Structural Minimization","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.14865","title":"GRAPE: Guided Parameter-Space Evolution for Compact Adversarial Robustness","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.16768","title":"Taming Curvature: Architecture Warm-Up for Stable Transformer Training","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.14571","title":"What Does Model Growth Really Add? Functional Capacity Beyond Parameter Count","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.14664","title":"Quantifying Depth Sufficiency in Residual Neural Networks: A First-Order Criterion","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.16485","title":"Certified Inference and Training for Deep Equilibrium Networks: A Continuation Framework with Polynomial Complexity Guarantees","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2610.00180","title":"Four Ways to Grow a Classifier and Why One of Them Cannot Learn","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.01649","title":"CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}