{"total":16,"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":"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":"2410.03030","title":"Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness","created":"2024-10-03","cited_by_count":11,"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":"2406.00153","title":"$\\mu$LO: Compute-Efficient Meta-Generalization of Learned Optimizers","created":"2024-05-31","cited_by_count":7,"area":null},{"id":"2603.15389","title":"When Does Sparsity Mitigate the Curse of Depth in LLMs","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2605.21486","title":"Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2510.11598","title":"MeTA-LoRA: Data-Efficient Multi-Task Fine-Tuning for Large Language Models","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2606.10678","title":"One Step Closer to Ground Truth: A Multi-Scale Residual-Aware Representation Learning Pipeline for Predicting Time Series Data","created":"2026-06-09","cited_by_count":1,"area":null},{"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":"2605.13405","title":"When is Warmstarting Effective for Scaling Language Models?","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.00888","title":"Memory-Efficient LLM Training with Dynamic Sparsity: From Stability to Practical Scaling","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.04048","title":"Unlocking Feature Learning in Gated Delta Networks at Scale","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2610.01172","title":"Learning Rate Transfer for Hybrid Transformer-SSM Architectures","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}