{"total":23,"rows":[{"id":"2308.13111","title":"Bayesian Low-rank Adaptation for Large Language Models","created":"2023-08-24","cited_by_count":115,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"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":"2205.13532","title":"Selective Prediction via Training Dynamics","created":"2022-05-26","cited_by_count":20,"area":null},{"id":"2210.11803","title":"Revisiting Checkpoint Averaging for Neural Machine Translation","created":"2022-10-21","cited_by_count":13,"area":null},{"id":"2403.04085","title":"Don't Blame the Data, Blame the Model: Understanding Noise and Bias When Learning from Subjective Annotations","created":"2024-03-06","cited_by_count":10,"area":null},{"id":"2102.12254","title":"NLRG at SemEval-2021 Task 5: Toxic Spans Detection Leveraging BERT-based Token Classification and Span Prediction Techniques","created":"2021-02-24","cited_by_count":6,"area":null},{"id":"2410.06431","title":"Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2411.04358","title":"Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation","created":"2024-11-07","cited_by_count":6,"area":null},{"id":"2402.00853","title":"LTAU-FF: Loss Trajectory Analysis for Uncertainty in Atomistic Force Fields","created":"2024-02-01","cited_by_count":4,"area":null},{"id":"2510.04848","title":"Instability in Downstream Task Performance During LLM Pretraining","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2204.01505","title":"Adaptive Network Combination for Single-Image Reflection Removal: A Domain Generalization Perspective","created":"2022-04-04","cited_by_count":3,"area":null},{"id":"2302.07845","title":"NL2CMD: An Updated Workflow for Natural Language to Bash Commands Translation","created":"2023-02-15","cited_by_count":3,"area":null},{"id":"2303.12992","title":"A Survey of Historical Learning: Learning Models with Learning History","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2301.08524","title":"Clustering Human Mobility with Multiple Spaces","created":"2023-01-20","cited_by_count":2,"area":null},{"id":"2501.14551","title":"Fairness of Deep Ensembles: On the interplay between per-group task difficulty and under-representation","created":"2025-01-24","cited_by_count":2,"area":null},{"id":"2506.11403","title":"A correlation-permutation approach for speech-music encoders model merging","created":"2025-06-13","cited_by_count":2,"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":"2210.01864","title":"Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints","created":"2022-10-04","cited_by_count":1,"area":null},{"id":"2603.29941","title":"Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2302.03120","title":"Studying Therapy Effects and Disease Outcomes in Silico using Artificial Counterfactual Tissue Samples","created":"2023-02-06","cited_by_count":0,"area":null},{"id":"2510.24633","title":"Symbolic Snapshot Ensembles","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2608.14373","title":"Boosting Data Augmentation with Stochastic Weight Averaging","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}