{"total":10,"rows":[{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2112.01922","title":"MetaQA: Combining Expert Agents for Multi-Skill Question Answering","created":"2021-12-03","cited_by_count":15,"area":null},{"id":"2306.01709","title":"Distilling Efficient Language-Specific Models for Cross-Lingual Transfer","created":"2023-06-02","cited_by_count":6,"area":null},{"id":"2310.08797","title":"A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2312.04720","title":"From Big to Small Without Losing It All: Text Augmentation with ChatGPT for Efficient Sentiment Analysis","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2306.11426","title":"Exploring the Performance and Efficiency of Transformer Models for NLP on Mobile Devices","created":"2023-06-20","cited_by_count":4,"area":null},{"id":"2311.10770","title":"Exponentially Faster Language Modelling","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2211.15927","title":"Compressing Cross-Lingual Multi-Task Models at Qualtrics","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2409.01089","title":"CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single- and Multi-DNN Workloads","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2603.18676","title":"MANAR: Memory-augmented Attention with Navigational Abstract Conceptual Representation","created":"2026-03-19","cited_by_count":0,"area":null}],"next_cursor":null}