{"total":100,"rows":[{"id":"2510.05491","title":"NorMuon: Making Muon more efficient and scalable","created":"2025-10-07","cited_by_count":84,"area":null},{"id":"2511.00674","title":"Isotropic Curvature Model for Understanding Deep Learning Optimization: Is Gradient Orthogonalization Optimal?","created":"2025-11-01","cited_by_count":37,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2510.19933","title":"Beyond the Ideal: Analyzing the Inexact Muon Update","created":"2025-10-22","cited_by_count":27,"area":null},{"id":"2604.21106","title":"How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models","created":"2026-04-22","cited_by_count":24,"area":null},{"id":"2512.05620","title":"Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales","created":"2025-12-05","cited_by_count":21,"area":null},{"id":"2510.22980","title":"How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data","created":"2025-10-27","cited_by_count":19,"area":null},{"id":"2604.01472","title":"The Newton-Muon Optimizer","created":"2026-04-01","cited_by_count":18,"area":null},{"id":"2605.08678","title":"MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI","created":"2026-05-09","cited_by_count":17,"area":null},{"id":"2510.25000","title":"What Really Matters in Matrix-Whitening Optimizers?","created":"2025-10-28","cited_by_count":16,"area":null},{"id":"2606.16899","title":"Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization","created":"2026-06-15","cited_by_count":16,"area":null},{"id":"2603.20527","title":"RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization","created":"2026-03-20","cited_by_count":15,"area":null},{"id":"2603.26554","title":"Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory","created":"2026-03-27","cited_by_count":14,"area":null},{"id":"2605.11181","title":"Muon is Not That Special: Random or Inverted Spectra Work Just as Well","created":"2026-05-11","cited_by_count":14,"area":null},{"id":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13,"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":"2510.10777","title":"Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods","created":"2025-10-12","cited_by_count":11,"area":null},{"id":"2510.21800","title":"MARS-M: When Variance Reduction Meets Matrices","created":"2025-10-20","cited_by_count":10,"area":null},{"id":"2603.00742","title":"To Use or not to Use Muon: How Simplicity Bias in Optimizers Matters","created":"2026-02-28","cited_by_count":10,"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":"2510.03871","title":"Optimal Scaling Needs Optimal Norm","created":"2025-10-04","cited_by_count":8,"area":null},{"id":"2510.15262","title":"Robust Layerwise Scaling Rules by Proper Weight Decay Tuning","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2602.06797","title":"Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay","created":"2026-02-06","cited_by_count":8,"area":null},{"id":"2602.09314","title":"Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2510.19376","title":"Optimization Benchmark for Diffusion Models on Dynamical Systems","created":"2025-10-22","cited_by_count":7,"area":"diffusion"},{"id":"2509.23500","title":"Beyond Outliers: A Study of Optimizers Under Quantization","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2510.24626","title":"Relative Scaling Laws for LLMs","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2605.09238","title":"Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds","created":"2026-05-10","cited_by_count":6,"area":null},{"id":"2606.04662","title":"Why Muon Outperforms Adam: A Curvature Perspective","created":"2026-06-03","cited_by_count":6,"area":null},{"id":"2607.20548","title":"SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales","created":"2026-07-13","cited_by_count":6,"area":null},{"id":"2511.20584","title":"A Tale of Two Geometries: Adaptive Optimizers and Non-Euclidean Descent","created":"2025-11-25","cited_by_count":5,"area":null},{"id":"2601.22257","title":"Symmetry Breaking in Transformers for Efficient and Interpretable Training","created":"2026-01-29","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":"2605.03769","title":"Nora: Normalized Orthogonal Row Alignment for Scalable Matrix Optimizer","created":"2026-05-05","cited_by_count":5,"area":null},{"id":"2605.06654","title":"Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less","created":"2026-05-07","cited_by_count":5,"area":null},{"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,"area":null},{"id":"2608.26288","title":"Muon with Finite Newton-Schulz: The Smoothing Benefit in Nonsmooth Nonconvex Optimization","created":"2026-08-26","cited_by_count":5,"area":null},{"id":"2601.22137","title":"PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2602.01642","title":"The Effect of Mini-Batch Noise on the Implicit Bias of Adam","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2602.06079","title":"Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers","created":"2026-02-04","cited_by_count":4,"area":null},{"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,"area":null},{"id":"2602.11137","title":"Weight Decay Improves Language Model Plasticity","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2603.03597","title":"NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training","created":"2026-03-04","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":"2605.31371","title":"Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2606.04058","title":"Spectral Scaling Laws of Muon","created":"2026-06-02","cited_by_count":4,"area":null},{"id":"2512.06201","title":"K2-V2: A 360-Open, Reasoning-Enhanced LLM","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2602.05887","title":"Escaping Local Minima Provably in Non-convex Matrix Sensing: A Deterministic Framework via Simulated Lifting","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2604.27077","title":"Learning Rate Transfer in Normalized Transformers","created":"2026-04-29","cited_by_count":3,"area":null},{"id":"2605.17109","title":"DynMuon: A Dynamic Spectral Shaping View of Muon","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2608.02502","title":"CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization","created":"2026-08-03","cited_by_count":3,"area":"diffusion"},{"id":"2509.13081","title":"Shaping Explanations: Semantic Reward Modeling with Encoder-Only Transformers for GRPO","created":"2025-09-16","cited_by_count":2,"area":"lr"},{"id":"2511.19035","title":"Changes in Gaza: DINOv3-Powered Multi-Class Change Detection for Damage Assessment in Conflict Zones","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2602.10300","title":"Configuration-to-Performance Scaling Law with Neural Ansatz","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2605.06615","title":"When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\\ell_1$-norm Lower Bounds","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.17787","title":"Revisiting the Adam-SGD Gap in LLM Pre-Training: The Role of Large Effective Learning Rates","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.18174","title":"Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.21803","title":"Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2606.03899","title":"Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.15268","title":"When to use what Schatten-$p$ norm in deep learning?","created":"2026-06-13","cited_by_count":2,"area":null},{"id":"2606.27216","title":"Hierarchical Muon: Tiled Newton-Schulz Updates for Efficient Muon Optimization","created":"2026-06-25","cited_by_count":2,"area":null},{"id":"2607.17620","title":"PoLoRA: A Preconditioned Orthogonalized LoRA Optimizer","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2607.19331","title":"ISO: An RLVR-Native Optimization Stack","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2608.01672","title":"Learning What to Remember: Test-Time Training via Context Distillation","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2609.19107","title":"How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents","created":"2026-09-16","cited_by_count":2,"area":null},{"id":"2512.04632","title":"Turbo-Muon: Almost-Orthogonal Pre-Conditioning for Fast Muon Updates","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2601.07326","title":"Convergence Rate Analysis of the AdamW-style Shampoo: Unifying One-Sided and Two-Sided Preconditioning","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2602.22437","title":"veScale-FSDP: Flexible and High-Performance FSDP at Scale","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2605.18999","title":"Distance-Aware Muon: Adaptive Step Scaling for Normalized Optimization","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.29387","title":"On the Optimizer Dependence of Neural Scaling Laws","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.06470","title":"PC Layer: Polynomial Weight Preconditioning for Improving LLM Pre-Training","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.23676","title":"Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2607.20486","title":"OPTScientist: Multi-Agent Discovery of Typed Optimizer Programs for Transformer Pretraining","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2608.25990","title":"Spectral Allocation: Why Muon Outperforms Adam, and How to Improve Muon","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2609.04577","title":"Optimizer Memory Schedules for Outscaling the Overtraining Axis","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2609.07597","title":"Beyond the Matrix Sign: Quadratic Spectral Descent","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2609.30063","title":"Self-Play Pretraining with Zero Data","created":"2026-09-24","cited_by_count":1,"area":"synth"},{"id":"2601.01306","title":"Towards a Principled Muon under $\\mu\\mathsf{P}$: Ensuring Spectral Conditions throughout Training","created":"2026-01-04","cited_by_count":0,"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":"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":"2604.01210","title":"CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discovery","created":"2026-04-01","cited_by_count":0,"area":"agents"},{"id":"2605.11850","title":"Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.17806","title":"AMO: Operator-level Adaptive Muon Orthogonalization","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.28585","title":"Outer-Momentum Restarting in High-Dimensional Two-Phase Optimization","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.30634","title":"One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining","created":"2026-06-29","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":"2608.16760","title":"On the Principles Behind Neural Network Optimizers","created":"2026-08-17","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":"2609.07017","title":"HyperTransfer: Understanding the Equivalence between Base Optimizer and Hyperball","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.23055","title":"Optimizers for Diffusion Models: A Controlled Benchmark","created":"2026-09-19","cited_by_count":0,"area":"diffusion"},{"id":"2609.25482","title":"Terminal Shrinkage Averaging Reveals a Schedule-Estimator Interaction in LLM Pretraining","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.26507","title":"The Ethics of Artificial Intelligence in Military Operations","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.33016","title":"Relative Generalization Invariance of LLM Pretraining","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.03432","title":"OptiSelect: How does the Optimizer Shape Data Curriculum?","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},{"id":"2610.14344","title":"On the Depth Transfer of Neural Optimizers via L-Smoothness","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.17285","title":"Which Geometry on Which Layer? Measured Sign-Spectral Assignment in Mixed-Optimizer Training","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18695","title":"A Refresh Interval Does Not Fully Specify a Refresh Schedule: Learning-Rate-Dependent Placement in Kronecker-Preconditioned Language Model Training","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19064","title":"How Inner Optimizers Shape Replica Scaling","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}