{"total":35,"rows":[{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54,"area":null},{"id":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38,"area":null},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2501.06842","title":"SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training","created":"2025-01-12","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":"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":"2410.15352","title":"CompAct: Compressed Activations for Memory-Efficient LLM Training","created":"2024-10-20","cited_by_count":15,"area":null},{"id":"2504.20437","title":"GaLore 2: Large-Scale LLM Pre-Training by Gradient Low-Rank Projection","created":"2025-04-29","cited_by_count":14,"area":null},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"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":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2506.16500","title":"SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity","created":"2025-06-19","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":"2412.04787","title":"Direct Quantized Training of Language Models with Stochastic Rounding","created":"2024-12-06","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":"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":"2603.05500","title":"POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation","created":"2026-03-05","cited_by_count":5,"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":"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":"2506.02939","title":"QKV Projections Require a Fraction of Their Memory","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2606.17526","title":"MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization","created":"2026-06-16","cited_by_count":2,"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":"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":"2512.07112","title":"FOAM: Blocked State Folding for Memory-Efficient LLM Training","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2605.04711","title":"Budget-aware Auto Optimizer Configurator","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.11396","title":"MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization","created":"2026-05-12","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":"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":"2607.04033","title":"OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.05872","title":"No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training","created":"2026-07-07","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":"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}],"next_cursor":null}