{"total":23,"rows":[{"id":"2507.07955","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","created":"2025-07-10","cited_by_count":72,"area":null},{"id":"2603.15958","title":"Deriving Hyperparameter Scaling Laws via Modern Optimization Theory","created":"2026-03-16","cited_by_count":10,"area":null},{"id":"2511.16893","title":"Predicting the Emergence of Induction Heads in Language Model Pretraining","created":"2025-11-21","cited_by_count":7,"area":null},{"id":"2603.21191","title":"On the Role of Batch Size in Stochastic Conditional Gradient Methods","created":"2026-03-22","cited_by_count":7,"area":null},{"id":"2510.14717","title":"Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling","created":"2025-10-16","cited_by_count":6,"area":null},{"id":"2602.14208","title":"Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws","created":"2026-02-15","cited_by_count":6,"area":null},{"id":"2509.25049","title":"Efficient Hyperparameter Tuning via Trajectory Invariance Principle","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2606.08388","title":"The Spectral Dynamics and Noise Geometry of Muon","created":"2026-06-07","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":"2602.03001","title":"Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2606.19179","title":"Compute Efficiency and Serial Runtime Tradeoffs for Stochastic Momentum Methods","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2608.29296","title":"When Do Larger Batches Help Scale LLM Reinforcement Learning?","created":"2026-08-29","cited_by_count":2,"area":null},{"id":"2605.27564","title":"The Future of Facts: Tracing the Factual Generation-Verification Gap","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2607.27731","title":"Towards joint scaling laws with optimal batch size schedules","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.28308","title":"Deriving Scaling Laws for OpenEuroLLM Models: Learning Rate, Batch Size and Loss","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2605.28961","title":"Dynamics of Stochastic Momentum with Sparse Updates in High Dimensions","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.05610","title":"Predictable Scaling Laws of Optimal Hyperparameters for LLM Continued Pre-training","created":"2026-06-04","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":"2608.10296","title":"Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.27581","title":"Does Step Law Transfer to Small-Scale Language Models? An Empirical Recalibration Below 59M Parameters","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.39767","title":"How Does Local Landscape Geometry Evolve in Language Model Pre-Training?","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02355","title":"Why Does Adaptive Batching Help LLM Pretraining? A Perspective from Unbounded Variance","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.15965","title":"Scaling Repeated-Data Pretraining: Batch Size, Regularization, and GPU-Time Tradeoffs","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}