{"total":50,"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":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2505.21829","title":"In Search of Adam's Secret Sauce","created":"2025-05-27","cited_by_count":40,"area":null},{"id":"2410.19313","title":"COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training","created":"2024-10-25","cited_by_count":33,"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":"2410.08989","title":"Zeroth-Order Fine-Tuning of LLMs in Random Subspaces","created":"2024-10-11","cited_by_count":26,"area":null},{"id":"2405.17991","title":"VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2405.18144","title":"4-bit Shampoo for Memory-Efficient Network Training","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2406.17660","title":"Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients","created":"2024-06-25","cited_by_count":18,"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":"2502.01586","title":"SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training","created":"2025-02-03","cited_by_count":16,"area":null},{"id":"2409.10927","title":"Propulsion: Steering LLM with Tiny Fine-Tuning","created":"2024-09-17","cited_by_count":14,"area":null},{"id":"2406.09958","title":"Memory-Efficient Optimization with Factorized Hamiltonian Descent","created":"2024-06-14","cited_by_count":11,"area":null},{"id":"2503.01901","title":"Identifying Sensitive Weights via Post-quantization Integral","created":"2025-02-28","cited_by_count":11,"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":"2310.07147","title":"QFT: Quantized Full-parameter Tuning of LLMs with Affordable Resources","created":"2023-10-11","cited_by_count":10,"area":null},{"id":"2407.11722","title":"Exploring Quantization for Efficient Pre-Training of Transformer Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2410.08598","title":"Parameter-Efficient Fine-Tuning of Large Language Models using Semantic Knowledge Tuning","created":"2024-10-11","cited_by_count":10,"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":"2506.04430","title":"Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order","created":"2025-06-04","cited_by_count":9,"area":null},{"id":"2403.14958","title":"Adapprox: Adaptive Approximation in Adam Optimization via Randomized Low-Rank Matrices","created":"2024-03-22","cited_by_count":8,"area":null},{"id":"2412.11768","title":"No More Adam: Learning Rate Scaling at Initialization is All You Need","created":"2024-12-16","cited_by_count":8,"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":"2607.04422","title":"Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention","created":"2026-07-05","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":"2410.23261","title":"$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2603.16731","title":"Understanding Quantization of Optimizer States in LLM Pre-training: Dynamics of State Staleness and Effectiveness of State Resets","created":"2026-03-17","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":"2505.00347","title":"Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics","created":"2025-05-01","cited_by_count":5,"area":null},{"id":"2602.23349","title":"FlashOptim: Optimizers for Memory-Efficient Training","created":"2026-02-26","cited_by_count":5,"area":null},{"id":"2507.08091","title":"Low-rank Momentum Factorization for Memory Efficient Training","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2410.06364","title":"Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2411.07120","title":"Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2412.10663","title":"Memory-Efficient 4-bit Preconditioned Stochastic Optimization","created":"2024-12-14","cited_by_count":2,"area":null},{"id":"2511.00056","title":"MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling","created":"2025-10-28","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":"2509.22418","title":"Partial Parameter Updates for Efficient Distributed Training","created":"2025-09-26","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":"2606.13894","title":"Gefen: Optimized Stochastic Optimizer","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2607.10611","title":"M+Adam: Low-Precision Training via Additive-Multiplicative Optimization","created":"2026-07-12","cited_by_count":1,"area":null},{"id":"2501.12896","title":"Irrational Complex Rotations Empower Low-bit Optimizers","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2505.18758","title":"Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2506.12015","title":"EMLoC: Emulator-based Memory-efficient Fine-tuning with LoRA Correction","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2511.12376","title":"BitSnap: Checkpoint Sparsification and Quantization in LLM Training","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2512.13034","title":"Alada: Alternating Adaptation of Momentum Method for Memory-Efficient Matrix Optimization","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2602.13659","title":"Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2605.00539","title":"AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.10335","title":"PowerStep: Memory-Efficient Adaptive Optimization via $\\ell_p$-Norm Steepest Descent","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2608.22322","title":"Beyond Dense Adam States: Adaptive Log-Space Quantization for Memory-Efficient Optimizers","created":"2026-08-23","cited_by_count":0,"area":null}],"next_cursor":null}