{"total":84,"rows":[{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177,"area":null},{"id":"2405.18392","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","created":"2024-05-28","cited_by_count":170,"area":null},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133,"area":null},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130,"area":null},{"id":"2407.13623","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","created":"2024-07-18","cited_by_count":118,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2403.15796","title":"Understanding Emergent Abilities of Language Models from the Loss Perspective","created":"2024-03-23","cited_by_count":94,"area":null},{"id":"2406.19146","title":"Resolving Discrepancies in Compute-Optimal Scaling of Language Models","created":"2024-06-27","cited_by_count":88,"area":null},{"id":"2405.20541","title":"Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models","created":"2024-05-30","cited_by_count":84,"area":null},{"id":"2409.15254","title":"Archon: An Architecture Search Framework for Inference-Time Techniques","created":"2024-09-23","cited_by_count":60,"area":null},{"id":"2407.12854","title":"Scaling Retrieval-Based Language Models with a Trillion-Token Datastore","created":"2024-07-09","cited_by_count":56,"area":null},{"id":"2404.00725","title":"The Larger the Better? Improved LLM Code-Generation via Budget Reallocation","created":"2024-03-31","cited_by_count":43,"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":"2412.04403","title":"Establishing Task Scaling Laws via Compute-Efficient Model Ladders","created":"2024-12-05","cited_by_count":35,"area":null},{"id":"2407.07890","title":"Training on the Test Task Confounds Evaluation and Emergence","created":"2024-07-10","cited_by_count":34,"area":null},{"id":"2507.00885","title":"Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check","created":"2025-07-01","cited_by_count":29,"area":null},{"id":"2501.18512","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","created":"2025-01-30","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":"2503.09799","title":"Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo","created":"2025-03-12","cited_by_count":27,"area":null},{"id":"2508.13144","title":"Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation","created":"2025-08-18","cited_by_count":26,"area":null},{"id":"2412.06540","title":"Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families","created":"2024-12-09","cited_by_count":24,"area":null},{"id":"2407.20177","title":"AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs","created":"2024-07-29","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":"2507.12466","title":"Language Models Improve When Pretraining Data Matches Target Tasks","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2505.14302","title":"Scaling Law for Quantization-Aware Training","created":"2025-05-20","cited_by_count":17,"area":null},{"id":"2501.18107","title":"Scaling Inference-Efficient Language Models","created":"2025-01-30","cited_by_count":16,"area":null},{"id":"2504.12427","title":"Position: The Most Expensive Part of an LLM should be its Training Data","created":"2025-04-16","cited_by_count":16,"area":null},{"id":"2411.12925","title":"Loss-to-Loss Prediction: Scaling Laws for All Datasets","created":"2024-11-19","cited_by_count":15,"area":null},{"id":"2412.16326","title":"When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization","created":"2024-12-20","cited_by_count":15,"area":null},{"id":"2506.14761","title":"From Bytes to Ideas: Language Modeling with Autoregressive U-Nets","created":"2025-06-17","cited_by_count":15,"area":null},{"id":"2601.10684","title":"On the origin of neural scaling laws: from random graphs to natural language","created":"2026-01-15","cited_by_count":14,"area":null},{"id":"2603.16127","title":"Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning","created":"2026-03-17","cited_by_count":13,"area":null},{"id":"2405.08707","title":"Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory","created":"2024-05-14","cited_by_count":12,"area":null},{"id":"2507.05195","title":"Train-before-Test Harmonizes Language Model Rankings","created":"2025-07-07","cited_by_count":12,"area":null},{"id":"2605.01640","title":"Prescriptive Scaling Laws for Data Constrained Training","created":"2026-05-02","cited_by_count":12,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2410.01692","title":"U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2604.08510","title":"What do Language Models Learn and When? The Implicit Curriculum Hypothesis","created":"2026-04-09","cited_by_count":10,"area":null},{"id":"2406.10806","title":"ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language","created":"2024-06-16","cited_by_count":8,"area":null},{"id":"2502.17262","title":"Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2512.08894","title":"Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training","created":"2025-12-09","cited_by_count":6,"area":null},{"id":"2504.00019","title":"ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding","created":"2025-03-27","cited_by_count":4,"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":"2606.24998","title":"Internal Data Repetition Destroys Language Models","created":"2026-06-23","cited_by_count":4,"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":"2510.02228","title":"xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2602.20433","title":"Disentangling Geometry, Performance, and Training in Language Models","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2605.02364","title":"InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition","created":"2026-05-04","cited_by_count":3,"area":null},{"id":"2607.08077","title":"Modular Pretraining Enables Access Control","created":"2026-07-09","cited_by_count":3,"area":null},{"id":"2608.03624","title":"LoopMTP: A looped transformer guided by latent multi-token prediction","created":"2026-08-04","cited_by_count":3,"area":null},{"id":"2412.07111","title":"Predictable Emergent Abilities of LLMs: Proxy Tasks Are All You Need","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2509.04897","title":"PLaMo 2 Technical Report","created":"2025-09-05","cited_by_count":2,"area":null},{"id":"2509.23963","title":"Evaluating the Robustness of Chinchilla Compute-Optimal Scaling","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.14919","title":"Predicting Task Performance with Context-aware Scaling Laws","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2512.06553","title":"A Latent Variable Framework for Scaling Laws in Large Language Models","created":"2025-12-06","cited_by_count":2,"area":null},{"id":"2601.19831","title":"Neural Neural Scaling Laws","created":"2026-01-27","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":"2603.13381","title":"Beyond Linearity in Attention Projections: The Case for Nonlinear Queries","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2605.06546","title":"Efficient Pre-Training with Token Superposition","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2608.11859","title":"Small-Scale Experiments: Are We There Yet?","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2503.07603","title":"Should VLMs be Pre-trained with Image Data?","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2506.13216","title":"Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2511.06232","title":"Scaling Laws and In-Context Learning: A Unified Theoretical Framework","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2602.10657","title":"Benchmarks Are Not That Out of Distribution: Word Overlap Predicts Performance","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2602.15327","title":"Prescriptive Scaling Reveals the Evolution of Language Model Capabilities","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2603.08022","title":"Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2605.28179","title":"SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.06470","title":"PC Layer: Polynomial Weight Preconditioning for Improving LLM Pre-Training","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.29858","title":"Smooth Scaling Laws Hide Stepwise Token Learning","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2609.04577","title":"Optimizer Memory Schedules for Outscaling the Overtraining Axis","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2501.09631","title":"Empowering Large Language Models in Wireless Communication: A Novel Dataset and Fine-Tuning Framework","created":"2025-01-16","cited_by_count":0,"area":null},{"id":"2511.12188","title":"Scaling Law Analysis in Federated Learning: How to Select the Optimal Model Size?","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2604.13368","title":"TLoRA+: A Low-Rank Parameter-Efficient Fine-Tuning Method for Large Language Models","created":"2026-04-15","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":"2605.08541","title":"Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.09189","title":"Practical Scaling Laws: Converting Compute into Performance in a Data-Constrained World","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2609.09143","title":"Studying Image Tokenizers as Visual Languages in Unified Multimodal Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.35236","title":"Long-Horizon Scaling: How Model Capabilities Shape the Returns to Computation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36569","title":"From Checkpoint Variation to Selection Gains in Supervised Fine-Tuning","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.40295","title":"How Much Is an AI Token Worth? Scaling Laws for Wild AI-Generated Web Text","created":"2026-09-30","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":"2610.03087","title":"Zephon: Elastic Determinism for Online, Stateful Foundation Model Data Loading Pipelines","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.15028","title":"UltraBERT: Beyond the Limit of BERT Pre-Training","created":"2026-10-10","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}