{"total":42,"rows":[{"id":"2407.11046","title":"A Survey on LoRA of Large Language Models","created":"2024-07-08","cited_by_count":67,"area":null},{"id":"2502.10940","title":"CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation","created":"2025-02-16","cited_by_count":28,"area":null},{"id":"2410.15352","title":"CompAct: Compressed Activations for Memory-Efficient LLM Training","created":"2024-10-20","cited_by_count":15,"area":null},{"id":"2506.16659","title":"Memory-Efficient LLM Pretraining via Minimalist Optimizer Design","created":"2025-06-20","cited_by_count":13,"area":null},{"id":"2507.08784","title":"Greedy Low-Rank Gradient Compression for Distributed Learning with Convergence Guarantees","created":"2025-07-11","cited_by_count":11,"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":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2502.05790","title":"Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining","created":"2025-02-09","cited_by_count":7,"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":"2501.02379","title":"TensorGRaD: Tensor Gradient Robust Decomposition for Memory-Efficient Neural Operator Training","created":"2025-01-04","cited_by_count":6,"area":null},{"id":"2502.01378","title":"CE-LoRA: Computation-Efficient LoRA Fine-Tuning for Language Models","created":"2025-02-03","cited_by_count":6,"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":"2601.23261","title":"TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training","created":"2026-01-30","cited_by_count":6,"area":null},{"id":"2602.21545","title":"MUON+: Towards More Effective Muon via One Additional Normalization Step for LLM Pre-training","created":"2026-02-25","cited_by_count":6,"area":null},{"id":"2504.00254","title":"ElaLoRA: Elastic & Learnable Low-Rank Adaptation for Efficient Model Fine-Tuning","created":"2025-03-31","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":"2603.05500","title":"POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2602.18116","title":"Cut Less, Fold More: Model Compression through the Lens of Projection Geometry","created":"2026-02-20","cited_by_count":4,"area":null},{"id":"2410.07771","title":"Full-Rank No More: Low-Rank Weight Training for Modern Speech Recognition Models","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2603.01376","title":"3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2604.21905","title":"Low-Rank Adaptation Redux for Large Models","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2506.02939","title":"QKV Projections Require a Fraction of Their Memory","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2511.11927","title":"Sparse corruption in low-rank matrix inference: the PCA benchmark","created":"2025-11-14","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":"2511.11641","title":"EcoSpa: Efficient Transformer Training with Coupled Sparsity","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2602.00942","title":"SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2605.05659","title":"Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks","created":"2026-05-07","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":"2607.09287","title":"Super-Tuning: From Activation-Aware Pruning to Sparse Fine-Tuning","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2509.07963","title":"Customizing the Inductive Biases of Softmax Attention using Structured Matrices","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2509.11254","title":"From PowerSGD to PowerSGD+: Low-Rank Gradient Compression for Distributed Optimization with Convergence Guarantees","created":"2025-09-14","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":"2601.07839","title":"Hierarchical Sparse Plus Low Rank Compression of LLM","created":"2025-12-19","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":"2605.10288","title":"BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.13652","title":"Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training","created":"2026-05-13","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},{"id":"2607.20214","title":"ELSAA: Efficient Low-Rank and Sparse Attention Approximation for Training Transformers","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2609.31975","title":"Model Casting and Low-Parameter Gating: Towards More Sparsely Activated FFNs","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36659","title":"On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.19844","title":"Memory-Efficient Subspace Optimization with Residual Correction: From Momentum SGD to Muon","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}