{"total":39,"rows":[{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132,"area":null},{"id":"2108.12284","title":"The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers","created":"2021-08-26","cited_by_count":117,"area":null},{"id":"2110.13100","title":"Parameter Prediction for Unseen Deep Architectures","created":"2021-10-25","cited_by_count":89,"area":null},{"id":"2110.09456","title":"NormFormer: Improved Transformer Pretraining with Extra Normalization","created":"2021-10-18","cited_by_count":83,"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":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2103.17268","title":"Fast Certified Robust Training with Short Warmup","created":"2021-03-31","cited_by_count":46,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2110.04369","title":"A Loss Curvature Perspective on Training Instability in Deep Learning","created":"2021-10-08","cited_by_count":40,"area":null},{"id":"2210.07240","title":"How to Train Vision Transformer on Small-scale Datasets?","created":"2022-10-13","cited_by_count":35,"area":null},{"id":"2303.04143","title":"Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2311.18363","title":"Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation","created":"2023-11-30","cited_by_count":29,"area":null},{"id":"2206.12755","title":"Training Your Sparse Neural Network Better with Any Mask","created":"2022-06-26","cited_by_count":26,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2305.02279","title":"Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models","created":"2023-05-03","cited_by_count":24,"area":null},{"id":"2501.08537","title":"Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers","created":"2025-01-15","cited_by_count":20,"area":null},{"id":"2405.05409","title":"Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing","created":"2024-05-08","cited_by_count":17,"area":null},{"id":"2211.08024","title":"NAR-Former: Neural Architecture Representation Learning towards Holistic Attributes Prediction","created":"2022-11-15","cited_by_count":13,"area":null},{"id":"2210.05956","title":"Towards Theoretically Inspired Neural Initialization Optimization","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2308.00574","title":"PVG: Progressive Vision Graph for Vision Recognition","created":"2023-08-01","cited_by_count":10,"area":null},{"id":"2401.08139","title":"Transferring Core Knowledge via Learngenes","created":"2024-01-16","cited_by_count":10,"area":null},{"id":"2510.06954","title":"From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics","created":"2025-10-08","cited_by_count":10,"area":null},{"id":"2112.09355","title":"From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization","created":"2021-12-17","cited_by_count":8,"area":null},{"id":"2305.02790","title":"BranchNorm: Robustly Scaling Extremely Deep Transformers","created":"2023-05-04","cited_by_count":6,"area":null},{"id":"2109.08958","title":"AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks","created":"2021-09-18","cited_by_count":5,"area":null},{"id":"2402.17440","title":"Principled Architecture-aware Scaling of Hyperparameters","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2410.05052","title":"Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes","created":"2024-10-07","cited_by_count":4,"area":null},{"id":"2105.10335","title":"Data-driven Weight Initialization with Sylvester Solvers","created":"2021-05-02","cited_by_count":3,"area":null},{"id":"2302.11446","title":"Singular value decomposition based matrix surgery","created":"2023-02-22","cited_by_count":3,"area":null},{"id":"2207.10049","title":"Pretraining a Neural Network before Knowing Its Architecture","created":"2022-07-20","cited_by_count":1,"area":null},{"id":"2304.11692","title":"The Disharmony between BN and ReLU Causes Gradient Explosion, but is Offset by the Correlation between Activations","created":"2023-04-23","cited_by_count":1,"area":null},{"id":"2502.07739","title":"HRP: High-Rank Preheating for Superior LoRA Initialization","created":"2025-02-11","cited_by_count":1,"area":null},{"id":"2210.02411","title":"Dynamical Isometry for Residual Networks","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2301.12193","title":"CyclicFL: A Cyclic Model Pre-Training Approach to Efficient Federated Learning","created":"2023-01-28","cited_by_count":0,"area":null},{"id":"2304.06959","title":"Convex Dual Theory Analysis of Two-Layer Convolutional Neural Networks with Soft-Thresholding","created":"2023-04-14","cited_by_count":0,"area":null},{"id":"2407.19044","title":"Advancing Neural Network Performance through Emergence-Promoting Initialization Scheme","created":"2024-07-26","cited_by_count":0,"area":null},{"id":"2410.05107","title":"Hyper-Representations: Learning from Populations of Neural Networks","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2508.05059","title":"Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2601.02105","title":"LION-DG: Layer-Informed Initialization with Deep Gradient Protocols for Accelerated Neural Network Training","created":"2026-01-05","cited_by_count":0,"area":null}],"next_cursor":null}