{"total":27,"rows":[{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57,"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":"2505.24749","title":"SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training","created":"2025-05-30","cited_by_count":19,"area":null},{"id":"2410.17881","title":"AdaRankGrad: Adaptive Gradient-Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuning","created":"2024-10-23","cited_by_count":17,"area":null},{"id":"2506.01260","title":"Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2506.10973","title":"Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning","created":"2025-06-12","cited_by_count":12,"area":null},{"id":"2511.13945","title":"Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers","created":"2025-11-17","cited_by_count":8,"area":null},{"id":"2311.03733","title":"Improved weight initialization for deep and narrow feedforward neural network","created":"2023-11-07","cited_by_count":7,"area":null},{"id":"2410.02242","title":"Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2502.13533","title":"Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2502.19571","title":"LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM","created":"2025-02-26","cited_by_count":5,"area":null},{"id":"2503.04626","title":"IDInit: A Universal and Stable Initialization Method for Neural Network Training","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2505.12909","title":"Sinusoidal Initialization, Time for a New Start","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2509.24218","title":"Conda: Column-Normalized Adam for Training Large Language Models Faster","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2205.02087","title":"Hypercomplex Image-to-Image Translation","created":"2022-05-04","cited_by_count":4,"area":null},{"id":"2303.04336","title":"QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms","created":"2023-03-08","cited_by_count":4,"area":null},{"id":"2405.13901","title":"Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2406.00348","title":"An Effective Weight Initialization Method for Deep Learning: Application to Satellite Image Classification","created":"2024-06-01","cited_by_count":1,"area":null},{"id":"2503.06385","title":"A Good Start Matters: Enhancing Continual Learning with Data-Driven Weight Initialization","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2506.01897","title":"MLorc: Momentum Low-rank Compression for Memory Efficient Large Language Model Adaptation","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2604.02505","title":"Optimal Projection-Free Adaptive SGD for Matrix Optimization","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2508.18826","title":"SWiFT: Soft-Mask Weight Fine-tuning for Bias Mitigation","created":"2025-08-26","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},{"id":"2603.28040","title":"Bit-Identical Medical Deep Learning via Structured Orthogonal Initialization","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2609.37631","title":"Procedural Core: A Compact Recurrent Initialization for Vision Transformers","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}