{"total":30,"rows":[{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254,"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":"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":"2310.08184","title":"Learning from models beyond fine-tuning","created":"2023-10-12","cited_by_count":48,"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":"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":"2403.19390","title":"Checkpoint Merging via Bayesian Optimization in LLM Pretraining","created":"2024-03-28","cited_by_count":27,"area":null},{"id":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23,"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":"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":"2511.18903","title":"How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining","created":"2025-11-24","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":"2404.08634","title":"When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models","created":"2024-04-12","cited_by_count":12,"area":null},{"id":"2406.12023","title":"LiLiuM: eBay's Large Language Models for e-commerce","created":"2024-06-17","cited_by_count":10,"area":null},{"id":"2602.03702","title":"Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging","created":"2026-02-03","cited_by_count":10,"area":null},{"id":"2506.16506","title":"Subspace-Boosted Model Merging","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2404.07815","title":"Post-Hoc Reversal: Are We Selecting Models Prematurely?","created":"2024-04-11","cited_by_count":8,"area":null},{"id":"2502.06761","title":"When, Where and Why to Average Weights?","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2509.14008","title":"Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale","created":"2025-09-17","cited_by_count":5,"area":null},{"id":"2604.11446","title":"Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration","created":"2026-04-13","cited_by_count":4,"area":null},{"id":"2407.03641","title":"Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy","created":"2024-07-04","cited_by_count":3,"area":null},{"id":"2605.26484","title":"Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2502.01015","title":"Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2510.09295","title":"MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2606.03681","title":"Speedrunning Tabular Foundation Model Pretraining","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.10959","title":"WSqD: A Horizon-Free Learning Rate Schedule for Large Model Training","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2609.25482","title":"Terminal Shrinkage Averaging Reveals a Schedule-Estimator Interaction in LLM Pretraining","created":"2026-09-21","cited_by_count":0,"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}