{"total":27,"rows":[{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137,"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":"2405.15593","title":"MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence","created":"2024-05-24","cited_by_count":19,"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":"2406.09958","title":"Memory-Efficient Optimization with Factorized Hamiltonian Descent","created":"2024-06-14","cited_by_count":11,"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":"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":"2505.16363","title":"AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2501.02406","title":"A Training-free Method for LLM Text Attribution","created":"2025-01-04","cited_by_count":5,"area":null},{"id":"2505.19084","title":"Jodi: Unification of Visual Generation and Understanding via Joint Modeling","created":"2025-05-25","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":"2501.11847","title":"A Survey on Memory-Efficient Transformer-Based Model Training in AI for Science","created":"2025-01-21","cited_by_count":3,"area":null},{"id":"2503.01843","title":"When Can You Get Away with Low Memory Adam?","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2510.09103","title":"AdaPM: a Partial Momentum Algorithm for LLM Training","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2602.01105","title":"OLion: Approaching the Hadamard Ideal by Intersecting Spectral and $\\ell_{\\infty}$ Implicit Biases","created":"2026-02-01","cited_by_count":3,"area":null},{"id":"2308.10252","title":"LMTuner: An user-friendly and highly-integrable Training Framework for fine-tuning Large Language Models","created":"2023-08-20","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":"2507.10855","title":"Sparse Fine-Tuning of Transformers for Generative Tasks","created":"2025-07-14","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":"2508.20577","title":"MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2510.08771","title":"LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution","created":"2025-10-09","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":"2512.17109","title":"Bridging Training and Merging Through Momentum-Aware Optimization","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2608.07524","title":"Training Variable Long Sequences with Data-Centric Parallel","created":"2026-07-14","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},{"id":"2610.02199","title":"TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-Tuning","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}