{"total":19,"rows":[{"id":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124,"area":null},{"id":"2310.02980","title":"Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors","created":"2023-10-04","cited_by_count":34,"area":null},{"id":"2212.00768","title":"Simplifying and Understanding State Space Models with Diagonal Linear RNNs","created":"2022-12-01","cited_by_count":23,"area":null},{"id":"2510.14865","title":"Midtraining Bridges Pretraining and Posttraining Distributions","created":"2025-10-16","cited_by_count":12,"area":null},{"id":"2212.10173","title":"On the Role of Parallel Data in Cross-lingual Transfer Learning","created":"2022-12-20","cited_by_count":11,"area":null},{"id":"2407.08716","title":"A Taxonomy for Data Contamination in Large Language Models","created":"2024-07-11","cited_by_count":11,"area":null},{"id":"2407.16891","title":"Cultural Value Differences of LLMs: Prompt, Language, and Model Size","created":"2024-06-17","cited_by_count":10,"area":null},{"id":"2601.21725","title":"Procedural Pretraining: Warming Up Language Models with Abstract Data","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2212.11937","title":"Efficient Induction of Language Models Via Probabilistic Concept Formation","created":"2022-12-22","cited_by_count":9,"area":null},{"id":"2305.10015","title":"Utility Theory of Synthetic Data Generation","created":"2023-05-17","cited_by_count":8,"area":null},{"id":"2502.10760","title":"Why is prompting hard? Understanding prompts on binary sequence predictors","created":"2025-02-15","cited_by_count":4,"area":null},{"id":"2210.13086","title":"Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2212.03760","title":"Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning","created":"2022-12-07","cited_by_count":2,"area":null},{"id":"2310.17271","title":"Understanding the Role of Input Token Characters in Language Models: How Does Information Loss Affect Performance?","created":"2023-10-26","cited_by_count":2,"area":null},{"id":"2405.06636","title":"Federated Document Visual Question Answering: A Pilot Study","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2605.21070","title":"Towards Understanding Self-Pretraining for Sequence Classification","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2305.08017","title":"How to Train Your CheXDragon: Training Chest X-Ray Models for Transfer to Novel Tasks and Healthcare Systems","created":"2023-05-13","cited_by_count":0,"area":null},{"id":"2505.24455","title":"Domain Pre-training Impact on Representations","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2507.22250","title":"Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training","created":"2025-07-29","cited_by_count":0,"area":null}],"next_cursor":null}