{"total":28,"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":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204,"area":null},{"id":"2406.02214","title":"SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining","created":"2024-06-04","cited_by_count":45,"area":null},{"id":"2407.08296","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","created":"2024-07-11","cited_by_count":38,"area":null},{"id":"2412.13148","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","created":"2024-12-17","cited_by_count":20,"area":null},{"id":"2310.10699","title":"Reusing Pretrained Models by Multi-linear Operators for Efficient Training","created":"2023-10-16","cited_by_count":15,"area":null},{"id":"2302.07937","title":"The Expressive Power of Tuning Only the Normalization Layers","created":"2023-02-15","cited_by_count":13,"area":null},{"id":"2508.02668","title":"LOST: Low-rank and Sparse Pre-training for Large Language Models","created":"2025-08-04","cited_by_count":10,"area":null},{"id":"2406.17296","title":"BlockLLM: Memory-Efficient Adaptation of LLMs by Selecting and Optimizing the Right Coordinate Blocks","created":"2024-06-25","cited_by_count":9,"area":null},{"id":"2505.12455","title":"AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2509.18993","title":"CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure","created":"2025-09-23","cited_by_count":7,"area":null},{"id":"2505.21732","title":"LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2403.06138","title":"BSDA: Bayesian Random Semantic Data Augmentation for Medical Image Classification","created":"2024-03-10","cited_by_count":5,"area":null},{"id":"2505.22922","title":"Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2407.00765","title":"Structured and Balanced Multi-Component and Multi-Layer Neural Networks","created":"2024-06-30","cited_by_count":3,"area":null},{"id":"2309.16592","title":"Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2512.12131","title":"BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models","created":"2025-12-13","cited_by_count":2,"area":null},{"id":"2311.11093","title":"Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2502.13811","title":"On the Duality between Gradient Transformations and Adapters","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2511.04485","title":"Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2606.28932","title":"DLR: Zero-Inference-Cost Latent Residuals for Low-Rank Pre-Training","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2607.08754","title":"SLORR: Simple and Efficient In-Training Low-Rank Regularization","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2309.12996","title":"Point Cloud Network: An Order of Magnitude Improvement in Linear Layer Parameter Count","created":"2023-09-22","cited_by_count":0,"area":null},{"id":"2410.24106","title":"On Sampling Strategies for Spectral Model Sharding","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2503.20694","title":"A Low-complexity Structured Neural Network Approach to Intelligently Realize Wideband Multi-beam Beamformers","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2510.01718","title":"Accelerating Attention with Basis Decomposition","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2605.03667","title":"ELAS: Efficient Pre-Training of Low-Rank Large Language Models via 2:4 Activation Sparsity","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.28573","title":"Efficient Pre-Training of LLMs through Truncated SVD Representations","created":"2026-05-27","cited_by_count":0,"area":null}],"next_cursor":null}