{"total":37,"rows":[{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","cited_by_count":80,"area":null},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2505.13738","title":"Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training","created":"2025-05-19","cited_by_count":43,"area":null},{"id":"2409.19913","title":"Scaling Optimal LR Across Token Horizons","created":"2024-09-30","cited_by_count":40,"area":null},{"id":"2502.15938","title":"Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs","created":"2025-02-21","cited_by_count":35,"area":null},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29,"area":null},{"id":"2503.09799","title":"Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo","created":"2025-03-12","cited_by_count":27,"area":null},{"id":"2512.22382","title":"Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration","created":"2025-12-26","cited_by_count":27,"area":null},{"id":"2507.02119","title":"Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks","created":"2025-07-02","cited_by_count":22,"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":"2510.19093","title":"Weight Decay may matter more than muP for Learning Rate Transfer in Practice","created":"2025-10-21","cited_by_count":20,"area":null},{"id":"2505.23725","title":"MuLoCo: Muon is a practical inner optimizer for DiLoCo","created":"2025-05-29","cited_by_count":18,"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":"2510.06213","title":"Training Dynamics Impact Post-Training Quantization Robustness","created":"2025-10-07","cited_by_count":15,"area":null},{"id":"2410.03249","title":"How Much Can We Forget about Data Contamination?","created":"2024-10-04","cited_by_count":14,"area":null},{"id":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","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":"2510.15262","title":"Robust Layerwise Scaling Rules by Proper Weight Decay Tuning","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2604.12887","title":"VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2502.05967","title":"$\\mu$nit Scaling: Simple and Scalable FP8 LLM Training","created":"2025-02-09","cited_by_count":5,"area":null},{"id":"2509.25049","title":"Efficient Hyperparameter Tuning via Trajectory Invariance Principle","created":"2025-09-29","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":"2605.18898","title":"A Two-Parameter Weibull Framework for Diagnosing Transformer Weight Distributions","created":"2026-05-17","cited_by_count":3,"area":null},{"id":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","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":"2605.20441","title":"Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2606.29158","title":"On the Nonlinearity of Learning Rate Scaling for LLM Training","created":"2026-06-28","cited_by_count":2,"area":null},{"id":"2411.04285","title":"Robust Real-Time Mortality Prediction in the Intensive Care Unit using Temporal Difference Learning","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2512.08217","title":"Correction of Decoupled Weight Decay","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2605.15290","title":"GQA-{\\mu}P: The maximal parameterization update for grouped query attention","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2607.01487","title":"How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2608.23573","title":"Data Predictability Shapes Weibull Weight-Scale Growth in Transformer Training","created":"2026-06-27","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":"2510.02337","title":"CRACQ: A Multi-Dimensional Approach To Automated Document Assessment","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.22313","title":"Sentiment Analysis Of Shopee Product Reviews Using Distilbert","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2607.05019","title":"Beyond Modality Fusion: Deep Ensembles for Multimodal Classification","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.21024","title":"RODE: A Radial-Orthogonal Decoupled Engine for Optimization","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}