{"total":38,"rows":[{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192,"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":"2401.10491","title":"Knowledge Fusion of Large Language Models","created":"2024-01-19","cited_by_count":115,"area":null},{"id":"2411.10438","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","created":"2024-11-15","cited_by_count":64,"area":null},{"id":"2409.03137","title":"The AdEMAMix Optimizer: Better, Faster, Older","created":"2024-09-05","cited_by_count":54,"area":null},{"id":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47,"area":null},{"id":"2405.15319","title":"Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training","created":"2024-05-24","cited_by_count":43,"area":null},{"id":"2407.07972","title":"Deconstructing What Makes a Good Optimizer for Language Models","created":"2024-07-10","cited_by_count":41,"area":null},{"id":"2410.07064","title":"Data Selection via Optimal Control for Language Models","created":"2024-10-09","cited_by_count":38,"area":null},{"id":"2312.17482","title":"MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining","created":"2023-12-29","cited_by_count":34,"area":null},{"id":"2402.02887","title":"Time-, Memory- and Parameter-Efficient Visual Adaptation","created":"2024-02-05","cited_by_count":28,"area":null},{"id":"2501.01956","title":"Metadata Conditioning Accelerates Language Model Pre-training","created":"2025-01-03","cited_by_count":22,"area":null},{"id":"2401.04301","title":"Setting the Record Straight on Transformer Oversmoothing","created":"2024-01-09","cited_by_count":21,"area":null},{"id":"2412.13148","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","created":"2024-12-17","cited_by_count":20,"area":null},{"id":"2510.25000","title":"What Really Matters in Matrix-Whitening Optimizers?","created":"2025-10-28","cited_by_count":16,"area":null},{"id":"2510.16882","title":"Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning","created":"2025-10-19","cited_by_count":15,"area":null},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2506.02281","title":"Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2309.11197","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","created":"2023-09-20","cited_by_count":10,"area":null},{"id":"2402.05913","title":"Efficient Stagewise Pretraining via Progressive Subnetworks","created":"2024-02-08","cited_by_count":10,"area":null},{"id":"2309.02373","title":"nanoT5: A PyTorch Framework for Pre-training and Fine-tuning T5-style Models with Limited Resources","created":"2023-09-05","cited_by_count":7,"area":null},{"id":"2410.23261","title":"$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2507.08472","title":"Pre-Training LLMs on a budget: A comparison of three optimizers","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2311.03233","title":"Navigating Scaling Laws: Compute Optimality in Adaptive Model Training","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2407.12220","title":"Questionable practices in machine learning","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2402.17227","title":"Efficient Backpropagation with Variance-Controlled Adaptive Sampling","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2403.11026","title":"EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration","created":"2024-03-16","cited_by_count":3,"area":null},{"id":"2508.00180","title":"EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes","created":"2025-07-31","cited_by_count":3,"area":null},{"id":"2407.15516","title":"Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2409.07925","title":"A framework for measuring the training efficiency of a neural architecture","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2510.13680","title":"Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2410.07880","title":"Unsupervised Data Validation Methods for Efficient Model Training","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2412.02153","title":"Revisiting the Initial Steps in Adaptive Gradient Descent Optimization","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2312.05021","title":"A Negative Result on Gradient Matching for Selective Backprop","created":"2023-12-08","cited_by_count":0,"area":null},{"id":"2609.13922","title":"Minibatch persistency, eight years later: what batch reuse costs in steps and joules, and what it saves in data","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":null}