{"total":23,"rows":[{"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":"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":"2503.04715","title":"Predictable Scale: Part I, Step Law -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining","created":"2025-03-06","cited_by_count":34,"area":null},{"id":"2503.05500","title":"EuroBERT: Scaling Multilingual Encoders for European Languages","created":"2025-03-07","cited_by_count":31,"area":null},{"id":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"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":"2410.17980","title":"Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study","created":"2024-10-23","cited_by_count":13,"area":null},{"id":"2508.01483","title":"Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler","created":"2025-08-02","cited_by_count":12,"area":null},{"id":"2410.05838","title":"Time Transfer: On Optimal Learning Rate and Batch Size In The Infinite Data Limit","created":"2024-10-08","cited_by_count":9,"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":"2510.03871","title":"Optimal Scaling Needs Optimal Norm","created":"2025-10-04","cited_by_count":8,"area":null},{"id":"2503.02844","title":"Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2501.06246","title":"A Partition Cover Approach to Tokenization","created":"2025-01-08","cited_by_count":5,"area":null},{"id":"2506.13274","title":"AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2507.16933","title":"SiLQ: Simple Large Language Model Quantization-Aware Training","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2505.06496","title":"xGen-small Technical Report","created":"2025-05-10","cited_by_count":1,"area":null},{"id":"2608.27370","title":"Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090","created":"2026-08-27","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":"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":"2607.10959","title":"WSqD: A Horizon-Free Learning Rate Schedule for Large Model Training","created":"2026-07-12","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":"2610.02839","title":"To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}