{"total":21,"rows":[{"id":"2410.19735","title":"Model merging with SVD to tie the Knots","created":"2024-10-25","cited_by_count":122,"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":"2504.08165","title":"Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2025-04-10","cited_by_count":88,"area":null},{"id":"2308.11696","title":"Efficient Benchmarking of Language Models","created":"2023-08-22","cited_by_count":71,"area":null},{"id":"2302.04863","title":"Knowledge is a Region in Weight Space for Fine-tuned Language Models","created":"2023-02-09","cited_by_count":58,"area":null},{"id":"2410.03617","title":"What Matters for Model Merging at Scale?","created":"2024-10-04","cited_by_count":55,"area":null},{"id":"2212.01378","title":"ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning","created":"2022-12-02","cited_by_count":52,"area":null},{"id":"2407.00066","title":"Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead","created":"2024-06-17","cited_by_count":24,"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":"2306.04529","title":"Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models","created":"2023-06-07","cited_by_count":15,"area":null},{"id":"2404.17401","title":"Evaluation of Geographical Distortions in Language Models","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2303.01593","title":"QAID: Question Answering Inspired Few-shot Intent Detection","created":"2023-03-02","cited_by_count":5,"area":null},{"id":"2410.23660","title":"Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2303.00333","title":"Competence-Based Analysis of Language Models","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2307.07331","title":"How Different Is Stereotypical Bias Across Languages?","created":"2023-07-14","cited_by_count":4,"area":null},{"id":"2401.04025","title":"IDoFew: Intermediate Training Using Dual-Clustering in Language Models for Few Labels Text Classification","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2601.06672","title":"Will it Merge? On The Causes of Model Mergeability","created":"2026-01-10","cited_by_count":4,"area":null},{"id":"2307.05741","title":"Towards Robust and Efficient Continual Language Learning","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2308.01080","title":"Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generation","created":"2023-08-02","cited_by_count":1,"area":null},{"id":"2601.22157","title":"Discovering Hidden Gems in Model Repositories","created":"2026-01-29","cited_by_count":1,"area":null}],"next_cursor":null}