{"total":15,"rows":[{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2212.10670","title":"In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models","created":"2022-12-20","cited_by_count":37,"area":null},{"id":"2302.03773","title":"What Matters In The Structured Pruning of Generative Language Models?","created":"2023-02-07","cited_by_count":30,"area":null},{"id":"2309.03824","title":"Training Acceleration of Low-Rank Decomposed Networks using Sequential Freezing and Rank Quantization","created":"2023-09-07","cited_by_count":8,"area":null},{"id":"2309.12412","title":"Speeding up Resnet Architecture with Layers Targeted Low Rank Decomposition","created":"2023-09-21","cited_by_count":8,"area":null},{"id":"2401.15293","title":"SkipViT: Speeding Up Vision Transformers with a Token-Level Skip Connection","created":"2024-01-27","cited_by_count":5,"area":null},{"id":"2310.05484","title":"IDTraffickers: An Authorship Attribution Dataset to link and connect Potential Human-Trafficking Operations on Text Escort Advertisements","created":"2023-10-09","cited_by_count":3,"area":null},{"id":"2311.15134","title":"SwiftLearn: A Data-Efficient Training Method of Deep Learning Models using Importance Sampling","created":"2023-11-25","cited_by_count":3,"area":null},{"id":"2403.07921","title":"Merino: Entropy-driven Design for Generative Language Models on IoT Devices","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2507.10880","title":"Domain-Adaptive Small Language Models for Structured Tax Code Prediction","created":"2025-07-15","cited_by_count":3,"area":null},{"id":"2304.07258","title":"Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games","created":"2023-04-14","cited_by_count":2,"area":null},{"id":"2309.03965","title":"Improving Resnet-9 Generalization Trained on Small Datasets","created":"2023-09-07","cited_by_count":2,"area":null},{"id":"2405.17333","title":"Generating Accurate Synthetic Survival Data by Conditioning on Outcomes","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2606.07857","title":"Model Multiplicity for Adversarial Detection in Small Language Model Training on Edge Devices","created":"2026-06-05","cited_by_count":0,"area":null}],"next_cursor":null}