{"total":53,"rows":[{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"area":null},{"id":"2410.08527","title":"Scaling Laws for Predicting Downstream Performance in LLMs","created":"2024-10-11","cited_by_count":48,"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":"2503.09146","title":"Generative Frame Sampler for Long Video Understanding","created":"2025-03-12","cited_by_count":37,"area":null},{"id":"2502.10940","title":"CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation","created":"2025-02-16","cited_by_count":28,"area":null},{"id":"2410.11840","title":"A Hitchhiker's Guide to Scaling Law Estimation","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2410.12883","title":"Scaling Laws for Multilingual Language Models","created":"2024-10-15","cited_by_count":23,"area":null},{"id":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2411.02335","title":"Sparsing Law: Towards Large Language Models with Greater Activation Sparsity","created":"2024-11-04","cited_by_count":22,"area":null},{"id":"2412.01505","title":"Scaling Law for Language Models Training Considering Batch Size","created":"2024-12-02","cited_by_count":22,"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":"2502.06857","title":"Gemstones: A Model Suite for Multi-Faceted Scaling Laws","created":"2025-02-07","cited_by_count":20,"area":null},{"id":"2501.18107","title":"Scaling Inference-Efficient Language Models","created":"2025-01-30","cited_by_count":16,"area":null},{"id":"2407.02118","title":"Breaking Language Barriers: Cross-Lingual Continual Pre-Training at Scale","created":"2024-07-02","cited_by_count":15,"area":null},{"id":"2507.21184","title":"Can Language Models Discover Scaling Laws?","created":"2025-07-27","cited_by_count":13,"area":null},{"id":"2605.01640","title":"Prescriptive Scaling Laws for Data Constrained Training","created":"2026-05-02","cited_by_count":12,"area":null},{"id":"2411.16035","title":"Predicting Emergent Capabilities by Finetuning","created":"2024-11-25","cited_by_count":10,"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":"2408.09895","title":"Performance Law of Large Language Models","created":"2024-08-19","cited_by_count":6,"area":null},{"id":"2605.12715","title":"Scaling Laws for Mixture Pretraining Under Data Constraints","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2505.00985","title":"Position: Enough of Scaling LLMs! Lets Focus on Downscaling","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2510.18245","title":"Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2605.01188","title":"Compute Optimal Tokenization","created":"2026-05-02","cited_by_count":4,"area":null},{"id":"2411.01137","title":"Data movement limits to frontier model training","created":"2024-11-02","cited_by_count":3,"area":null},{"id":"2502.01804","title":"Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2512.23407","title":"Theoretical Foundations of Scaling Law in Familial Models","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2604.22753","title":"Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection","created":"2026-04-24","cited_by_count":3,"area":null},{"id":"2510.02721","title":"Hyperparameter Loss Surfaces Are Simple Near their Optima","created":"2025-10-03","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":"2603.25687","title":"On Neural Scaling Laws for Weather Emulation through Continual Training","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2607.23777","title":"Scale Weight Decay and Train Better","created":"2026-07-26","cited_by_count":2,"area":null},{"id":"2609.19107","title":"How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents","created":"2026-09-16","cited_by_count":2,"area":null},{"id":"2409.04069","title":"Online Residual Learning from Offline Experts for Pedestrian Tracking","created":"2024-09-06","cited_by_count":1,"area":null},{"id":"2504.18929","title":"Revisiting Transformers through the Lens of Low Entropy and Dynamic Sparsity","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2510.15893","title":"Accelerating Frontier MoE Training with 3D Integrated Optics","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2512.09723","title":"Mixture of Lookup Key-Value Experts","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2603.19149","title":"Optimal Splitting of Language Models from Mixtures to Specialized Domains","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.03260","title":"Why Attend to Everything? Focus is the Key","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.21724","title":"Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.23591","title":"Asymmetric Scaling Laws from Sparse Features","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2609.02672","title":"oHC: Orthogonal Hyper-Connections on SO(4) via Quaternions","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2505.04850","title":"ORXE: Orchestrating Experts for Dynamically Configurable Efficiency","created":"2025-05-07","cited_by_count":0,"area":null},{"id":"2509.15556","title":"Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining","created":"2025-09-19","cited_by_count":0,"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":"2603.28507","title":"Continued AI Scaling Requires Repeated Efficiency Doublings","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.24037","title":"A Limit Theory of Foundation Models: A Mathematical Approach to Understanding Emergent Intelligence and Scaling Laws","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.31397","title":"Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.04238","title":"Budgeting Bytes: A Windowed Storage Roofline and Dual-Budget Architecture Ablations for Storage-Bound LLM Decoding","created":"2026-07-29","cited_by_count":0,"area":null}],"next_cursor":null}