{"total":20,"rows":[{"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":"2405.15682","title":"The Road Less Scheduled","created":"2024-05-24","cited_by_count":163,"area":null},{"id":"2411.18704","title":"Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits","created":"2024-11-27","cited_by_count":71,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2306.03241","title":"Early Weight Averaging meets High Learning Rates for LLM Pre-training","created":"2023-06-05","cited_by_count":37,"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":"2501.18965","title":"The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training","created":"2025-01-31","cited_by_count":33,"area":null},{"id":"2507.17634","title":"WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training","created":"2025-07-23","cited_by_count":23,"area":null},{"id":"2510.06213","title":"Training Dynamics Impact Post-Training Quantization Robustness","created":"2025-10-07","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":"2411.05239","title":"ZipNN: Lossless Compression for AI Models","created":"2024-11-07","cited_by_count":14,"area":null},{"id":"2507.09846","title":"Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training","created":"2025-07-14","cited_by_count":9,"area":null},{"id":"2502.06761","title":"When, Where and Why to Average Weights?","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2605.19095","title":"ScheduleFree+: Scaling Learning-Rate-Free & Schedule-Free Learning to Large Language Models","created":"2026-05-18","cited_by_count":7,"area":null},{"id":"2404.15198","title":"Lossless and Near-Lossless Compression for Foundation Models","created":"2024-04-05","cited_by_count":5,"area":null},{"id":"2512.17131","title":"Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs","created":"2025-12-18","cited_by_count":5,"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":"2505.22085","title":"PADAM: Parallel averaged Adam reduces the error for stochastic optimization in scientific machine learning","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2609.35168","title":"QAM: Quadratic-Accurate Checkpoint Merging via Sequential Consistency","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.05329","title":"Understanding the Weight Averaging Mechanism in LLM Training for Post-Training Quantization","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}