{"total":40,"rows":[{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54,"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":"2412.13148","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","created":"2024-12-17","cited_by_count":20,"area":null},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"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":"2502.01586","title":"SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training","created":"2025-02-03","cited_by_count":16,"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":"2411.07837","title":"FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training","created":"2024-11-12","cited_by_count":10,"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":"2502.06742","title":"Gradient Multi-Normalization for Stateless and Scalable LLM Training","created":"2025-02-10","cited_by_count":9,"area":null},{"id":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2505.24275","title":"GradPower: Powering Gradients for Faster Language Model Pre-Training","created":"2025-05-30","cited_by_count":8,"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":"2510.17802","title":"Unbiased Gradient Low-Rank Projection","created":"2025-10-20","cited_by_count":7,"area":null},{"id":"2602.12429","title":"Stabilizing Native Low-Rank LLM Pretraining","created":"2026-02-12","cited_by_count":6,"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":"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":"2509.24218","title":"Conda: Column-Normalized Adam for Training Large Language Models Faster","created":"2025-09-29","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":"2505.17967","title":"FFT-based Dynamic Subspace Selection for Low-Rank Adaptive Optimization of Large Language Models","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2506.01049","title":"Taming LLMs by Scaling Learning Rates with Gradient Grouping","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2602.09169","title":"Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2501.07237","title":"GWT: Scalable Optimizer State Compression for Large Language Model Training","created":"2025-01-13","cited_by_count":1,"area":null},{"id":"2505.01744","title":"Memory-Efficient LLM Training by Various-Grained Low-Rank Projection of Gradients","created":"2025-05-03","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":"2510.01878","title":"Geometrically Principled Randomized Optimization for Efficient LLM Training","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2512.07112","title":"FOAM: Blocked State Folding for Memory-Efficient LLM Training","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2602.23111","title":"PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2606.05484","title":"Learned Subspace Compression for Communication-Efficient Pipeline Parallelism","created":"2026-06-03","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":"2506.11042","title":"GenFT: A Generative Parameter-Efficient Fine-Tuning Method for Pretrained Foundation Models","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2602.01233","title":"Lotus: Efficient LLM Training by Randomized Low-Rank Gradient Projection with Adaptive Subspace Switching","created":"2026-02-01","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":"2609.05885","title":"One Rate Is Not Enough: Adaptive Anisotropic Learning Rates for LoRA Fine-Tuning","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.15037","title":"MoARa: Module-Aware Rank Allocation and Structure-Preserving Decomposition for Low-Rank LLM Pre-training","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.37027","title":"Beyond Low-Rank Parameterization: Narrowing the Gap Between LoRA and Full Fine-Tuning via Gradient Decomposition","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04204","title":"Clean: Second-order LLM Training at Linear Memory Cost via Nystr{\\\"o}m Sketching","created":"2026-10-03","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}