{"list":"other","total":51,"rows":[{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"1901.10159","title":"An Investigation into Neural Net Optimization via Hessian Eigenvalue Density","created":"2019-01-29","cited_by_count":292},{"id":"1706.04454","title":"Empirical Analysis of the Hessian of Over-Parametrized Neural Networks","created":"2017-06-14","cited_by_count":290},{"id":"1406.2572","title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","created":"2014-06-10","cited_by_count":289},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265},{"id":"2006.00719","title":"ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning","created":"2020-06-01","cited_by_count":202},{"id":"1611.07476","title":"Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond","created":"2016-11-22","cited_by_count":159},{"id":"1706.03662","title":"Practical Gauss-Newton Optimisation for Deep Learning","created":"2017-06-12","cited_by_count":142},{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137},{"id":"2403.08763","title":"Simple and Scalable Strategies to Continually Pre-train Large Language Models","created":"2024-03-13","cited_by_count":127},{"id":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124},{"id":"2505.16932","title":"The Polar Express: Optimal Matrix Sign Methods and Their Application to the Muon Algorithm","created":"2025-05-22","cited_by_count":110},{"id":"2510.05491","title":"NorMuon: Making Muon more efficient and scalable","created":"2025-10-07","cited_by_count":84},{"id":"2410.05192","title":"Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective","created":"2024-10-07","cited_by_count":81},{"id":"2507.11005","title":"AdaMuon: Adaptive Muon Optimizer","created":"2025-07-15","cited_by_count":67},{"id":"2505.21799","title":"PolarGrad: A Class of Matrix-Gradient Optimizers from a Unifying Preconditioning Perspective","created":"2025-05-27","cited_by_count":52},{"id":"2002.11803","title":"Disentangling Adaptive Gradient Methods from Learning Rates","created":"2020-02-26","cited_by_count":42},{"id":"2505.24749","title":"SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training","created":"2025-05-30","cited_by_count":19},{"id":"2506.07254","title":"A Stable Whitening Optimizer for Efficient Neural Network Training","created":"2025-06-08","cited_by_count":18},{"id":"2509.11983","title":"Low-rank Orthogonalization for Large-scale Matrix Optimization with Applications to Foundation Model Training","created":"2025-09-15","cited_by_count":18},{"id":"2604.01472","title":"The Newton-Muon Optimizer","created":"2026-04-01","cited_by_count":18},{"id":"2603.09697","title":"Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning","created":"2026-03-10","cited_by_count":17},{"id":"2603.28254","title":"MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration","created":"2026-03-30","cited_by_count":17},{"id":"2604.09967","title":"Muon$^2$: Boosting Muon via Adaptive Second-Moment Preconditioning","created":"2026-04-11","cited_by_count":17},{"id":"2510.25000","title":"What Really Matters in Matrix-Whitening Optimizers?","created":"2025-10-28","cited_by_count":16},{"id":"2603.20527","title":"RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization","created":"2026-03-20","cited_by_count":15},{"id":"2602.17080","title":"Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum","created":"2026-02-19","cited_by_count":14},{"id":"2505.02809","title":"Towards Quantifying the Hessian Structure of Neural Networks","created":"2025-05-05","cited_by_count":13},{"id":"2601.21750","title":"FISMO: Fisher-Structured Momentum-Orthogonalized Optimizer","created":"2026-01-29","cited_by_count":11},{"id":"2601.19400","title":"Improved Convergence Rates of Muon Optimizer for Nonconvex Optimization","created":"2026-01-27","cited_by_count":9},{"id":"2602.13498","title":"TrasMuon: Trust-Region Adaptive Scaling for Orthogonalized Momentum Optimizers","created":"2026-02-13","cited_by_count":6},{"id":"2605.10797","title":"Muown: Row-Norm Control for Muon Optimization","created":"2026-05-11","cited_by_count":6},{"id":"2605.03769","title":"Nora: Normalized Orthogonal Row Alignment for Scalable Matrix Optimizer","created":"2026-05-05","cited_by_count":5},{"id":"2605.13079","title":"Spectral Flattening Is All Muon Needs: How Orthogonalization Controls Learning Rate and Convergence","created":"2026-05-13","cited_by_count":5},{"id":"2410.00232","title":"Preconditioning for Accelerated Gradient Descent Optimization and Regularization","created":"2024-09-30","cited_by_count":4},{"id":"2602.06880","title":"Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix Optimization","created":"2026-02-06","cited_by_count":4},{"id":"2602.11185","title":"Spectra: Rethinking Optimizers for LLMs Under Spectral Anisotropy","created":"2026-01-30","cited_by_count":4},{"id":"2605.09176","title":"Navigating LLM Valley: From AdamW to Memory-Efficient and Matrix-Based Optimizers","created":"2026-05-09","cited_by_count":2}],"next_cursor":null}