{"total":35,"rows":[{"id":"2403.16952","title":"Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance","created":"2024-03-25","cited_by_count":184,"area":null},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"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":"2406.01375","title":"D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models","created":"2024-06-03","cited_by_count":41,"area":null},{"id":"2409.19913","title":"Scaling Optimal LR Across Token Horizons","created":"2024-09-30","cited_by_count":40,"area":null},{"id":"2505.14669","title":"Quartet: Native FP4 Training Can Be Optimal for Large Language Models","created":"2025-05-20","cited_by_count":39,"area":null},{"id":"2404.11568","title":"On the Scalability of GNNs for Molecular Graphs","created":"2024-04-17","cited_by_count":36,"area":null},{"id":"2402.02314","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","created":"2024-02-04","cited_by_count":33,"area":null},{"id":"2504.17768","title":"The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs","created":"2025-04-24","cited_by_count":29,"area":null},{"id":"2502.18969","title":"(Mis)Fitting: A Survey of Scaling Laws","created":"2025-02-26","cited_by_count":26,"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":"2502.05003","title":"QuEST: Stable Training of LLMs with 1-Bit Weights and Activations","created":"2025-02-07","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":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","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":"2405.20935","title":"Effective Interplay between Sparsity and Quantization: From Theory to Practice","created":"2024-05-31","cited_by_count":19,"area":null},{"id":"2405.15743","title":"Sparse maximal update parameterization: A holistic approach to sparse training dynamics","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2508.12491","title":"Cost-Aware Contrastive Routing for LLMs","created":"2025-08-17","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":"2503.03862","title":"Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions","created":"2025-03-05","cited_by_count":12,"area":null},{"id":"2502.16440","title":"Compression Scaling Laws:Unifying Sparsity and Quantization","created":"2025-02-23","cited_by_count":11,"area":null},{"id":"2407.17880","title":"DAM: Towards A Foundation Model for Time Series Forecasting","created":"2024-07-25","cited_by_count":10,"area":null},{"id":"2501.12391","title":"Physics of Skill Learning","created":"2025-01-21","cited_by_count":8,"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":"2506.01863","title":"Unified Scaling Laws for Compressed Representations","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2406.04165","title":"Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe","created":"2024-06-06","cited_by_count":4,"area":null},{"id":"2311.17539","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2501.12486","title":"The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws","created":"2025-01-21","cited_by_count":2,"area":null},{"id":"2506.12932","title":"Complexity Scaling Laws for Neural Models using Combinatorial Optimization","created":"2025-06-15","cited_by_count":1,"area":null},{"id":"2604.23475","title":"Supernodes and Halos: Loss-Critical Hubs in LLM Feed-Forward Layers","created":"2026-04-26","cited_by_count":1,"area":null},{"id":"2502.12372","title":"Factual Inconsistency in Data-to-Text Generation Scales Exponentially with LLM Size: A Statistical Validation","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2503.04377","title":"How can representation dimension dominate structurally pruned LLMs?","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2504.05349","title":"Hyperflux: Pruning Reveals Importance","created":"2025-04-06","cited_by_count":0,"area":null},{"id":"2610.02462","title":"Capability Scaling-Down Laws for LLM Compression","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04093","title":"Beyond Masked Sparsity: SNACK Enables Truly Sparse Neural Networks on GPU","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}