{"total":49,"rows":[{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"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":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121,"area":null},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2304.08442","title":"The MiniPile Challenge for Data-Efficient Language Models","created":"2023-04-17","cited_by_count":75,"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":"2310.04742","title":"Parameter Efficient Multi-task Model Fusion with Partial Linearization","created":"2023-10-07","cited_by_count":65,"area":null},{"id":"2310.08184","title":"Learning from models beyond fine-tuning","created":"2023-10-12","cited_by_count":48,"area":null},{"id":"2303.05470","title":"Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases","created":"2023-03-09","cited_by_count":41,"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":"2302.01107","title":"A Survey on Efficient Training of Transformers","created":"2023-02-02","cited_by_count":39,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"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":"2312.06173","title":"Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion","created":"2023-12-11","cited_by_count":37,"area":null},{"id":"2502.15015","title":"Accelerating Neural Network Training: An Analysis of the AlgoPerf Competition","created":"2025-02-20","cited_by_count":32,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2401.09135","title":"Asynchronous Local-SGD Training for Language Modeling","created":"2024-01-17","cited_by_count":26,"area":null},{"id":"2507.20016","title":"FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging","created":"2025-07-26","cited_by_count":25,"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":"2301.02312","title":"Training trajectories, mini-batch losses and the curious role of the learning rate","created":"2023-01-05","cited_by_count":21,"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":"2410.13910","title":"Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace","created":"2024-10-17","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":"2210.15282","title":"Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition","created":"2022-10-27","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":"2402.09240","title":"Switch EMA: A Free Lunch for Better Flatness and Sharpness","created":"2024-02-14","cited_by_count":9,"area":null},{"id":"2408.10174","title":"SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models","created":"2024-08-19","cited_by_count":9,"area":null},{"id":"2310.01366","title":"Window-based Model Averaging Improves Generalization in Heterogeneous Federated Learning","created":"2023-10-02","cited_by_count":7,"area":null},{"id":"2406.14878","title":"MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection","created":"2024-06-21","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":"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":"2411.13169","title":"A Unified Analysis for Finite Weight Averaging","created":"2024-11-20","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":"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":"2405.19590","title":"Weights Augmentation: it has never ever ever ever let her model down","created":"2024-05-30","cited_by_count":1,"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":"2505.24452","title":"Stepsize anything: A unified learning rate schedule for budgeted-iteration training","created":"2025-05-30","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":"2602.03237","title":"Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2606.25086","title":"Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.11997","title":"Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2601.21690","title":"A Unified Generalization Framework for Model Merging: Trade-offs, Non-Linearity, and Scaling Laws","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2606.03681","title":"Speedrunning Tabular Foundation Model Pretraining","created":"2026-06-02","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}],"next_cursor":null}