{"total":40,"rows":[{"id":"2506.04192","title":"Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise","created":"2025-06-04","cited_by_count":41,"area":null},{"id":"2509.15816","title":"On the Convergence of Muon and Beyond","created":"2025-09-19","cited_by_count":31,"area":null},{"id":"2510.25000","title":"What Really Matters in Matrix-Whitening Optimizers?","created":"2025-10-28","cited_by_count":16,"area":null},{"id":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13,"area":null},{"id":"2508.01483","title":"Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler","created":"2025-08-02","cited_by_count":12,"area":null},{"id":"2601.23000","title":"Mano: Restriking Manifold Optimization for LLM Training","created":"2026-01-30","cited_by_count":12,"area":null},{"id":"2603.10067","title":"HTMuon: Improving Muon via Heavy-Tailed Spectral Correction","created":"2026-03-10","cited_by_count":12,"area":null},{"id":"2411.19870","title":"DeMo: Decoupled Momentum Optimization","created":"2024-11-29","cited_by_count":11,"area":null},{"id":"2602.04669","title":"Delving into Muon and Beyond: Deep Analysis and Extensions","created":"2026-02-04","cited_by_count":9,"area":null},{"id":"2501.12243","title":"FOCUS: First Order Concentrated Updating Scheme","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2501.12391","title":"Physics of Skill Learning","created":"2025-01-21","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":"2602.22681","title":"Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement","created":"2026-02-26","cited_by_count":8,"area":null},{"id":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2510.24626","title":"Relative Scaling Laws for LLMs","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2506.05447","title":"Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2604.15297","title":"Benchmarking Optimizers for MLPs in Tabular Deep Learning","created":"2026-04-16","cited_by_count":5,"area":null},{"id":"2604.15416","title":"StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models","created":"2026-04-16","cited_by_count":5,"area":null},{"id":"2412.17107","title":"Grams: Gradient Descent with Adaptive Momentum Scaling","created":"2024-12-22","cited_by_count":4,"area":null},{"id":"2604.09258","title":"Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima","created":"2026-04-10","cited_by_count":4,"area":null},{"id":"2602.20360","title":"Momentum Guidance: Plug-and-Play Guidance for Flow Models","created":"2026-02-23","cited_by_count":3,"area":null},{"id":"2604.12968","title":"Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2605.18613","title":"SAME: A Semantically-Aligned Music Autoencoder","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2411.19647","title":"CAdam: Confidence-Based Optimization for Online Learning","created":"2024-11-29","cited_by_count":2,"area":null},{"id":"2509.18396","title":"Development of Deep Learning Optimizers: Approaches, Concepts, and Update Rules","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2512.06370","title":"Greedy Alignment Principle for Optimizer Selection","created":"2025-12-06","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":"2507.00792","title":"JAX-IK: Real-Time Inverse Kinematics for Generating Multi-Constrained Movements of Virtual Human Characters","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2509.08550","title":"ViewSparsifier: Killing Redundancy in Multi-View Plant Phenotyping","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2511.11030","title":"Algorithms Trained on Normal Chest X-rays Can Predict Health Insurance Types","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2601.14603","title":"Variance-Adaptive Muon: Pre-Orthogonalization Variance Modulation for Efficient Language Model Pretraining","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2607.03763","title":"FedACT: Federated Adaptive Coordinate Trust Modulation for Robust Transformer Training under Data Heterogeneity","created":"2026-07-04","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":"2607.09266","title":"LionVote: Per-Layer Learning Rate Adaptation for Lion","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.06597","title":"Cascading Through the Hierarchy: Regularizer-Induced Feature Detection as Phase Transitions in Deep Linear Neural Networks","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.28557","title":"Blog: Survey of Optimizers","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.36692","title":"Normalize-Then-Precondition: A Hierarchical Approach to Marginal Scale and Interaction Geometry for LLM Training","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37525","title":"Physical Muon: Orthogonalization as an Equilibrium Computation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.03940","title":"A Step Towards Forgetting: Optimiser History and the Loss of Answer Mass","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.13036","title":"Towards Easier-to-Tune Training Algorithms: New Results from AlgoPerf","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}