{"total":5,"rows":[{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650,"area":null},{"id":"2305.10013","title":"When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2407.11902","title":"Encapsulating Knowledge in One Prompt","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2406.15476","title":"Self-Regulated Data-Free Knowledge Amalgamation for Text Classification","created":"2024-06-16","cited_by_count":1,"area":null},{"id":"2111.10951","title":"Can depth-adaptive BERT perform better on binary classification tasks","created":"2021-11-22","cited_by_count":0,"area":null}],"next_cursor":null}