{"total":25,"rows":[{"id":"2502.05795","title":"The Curse of Depth in Large Language Models","created":"2025-02-09","cited_by_count":62,"area":null},{"id":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13,"area":null},{"id":"2603.14315","title":"Enhancing LLM Training via Spectral Clipping","created":"2026-03-15","cited_by_count":10,"area":null},{"id":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"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":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2502.11034","title":"AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping","created":"2025-02-16","cited_by_count":6,"area":null},{"id":"2502.17055","title":"GradientStabilizer:Fix the Norm, Not the Gradient","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2603.16731","title":"Understanding Quantization of Optimizer States in LLM Pre-training: Dynamics of State Staleness and Effectiveness of State Resets","created":"2026-03-17","cited_by_count":6,"area":null},{"id":"2505.22922","title":"Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2509.24218","title":"Conda: Column-Normalized Adam for Training Large Language Models Faster","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2605.25704","title":"PowLU: An Activation Function for Stable Pre-Training of LLMs","created":"2026-05-25","cited_by_count":4,"area":null},{"id":"2604.00726","title":"Exploring Silent Data Corruption as a Reliability Challenge in LLM Training","created":"2026-04-01","cited_by_count":3,"area":null},{"id":"2506.01049","title":"Taming LLMs by Scaling Learning Rates with Gradient Grouping","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2605.04711","title":"Budget-aware Auto Optimizer Configurator","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2608.19762","title":"Finite-Horizon Input-Output Dynamics of Minibatch Perturbations in AdamW","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2605.27733","title":"Can Entry-Wise Clipping Give Spectral Control of Stochastic Gradients?","created":"2026-05-26","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":"2606.00539","title":"GNMR: Runtime Stability Control for Low-Precision Large Language Model Training","created":"2026-05-30","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":"2606.07881","title":"Breaking the Bubble: Asynchronous Pipeline Parallel Training with Bounded Weight Inconsistency","created":"2026-06-05","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":"2608.02091","title":"One QK Channel, Many Sources: Tracing Low-Precision Attention Collapse","created":"2026-08-03","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":"2609.34681","title":"SOLAR: A State-Driven Online Learning Rate Scheduler for LLM Pretraining","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}