{"total":26,"rows":[{"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":"2306.12509","title":"Joint Prompt Optimization of Stacked LLMs using Variational Inference","created":"2023-06-21","cited_by_count":32,"area":null},{"id":"2506.12459","title":"Merlin: Multi-View Representation Learning for Robust Multivariate Time Series Forecasting with Unfixed Missing Rates","created":"2025-06-14","cited_by_count":20,"area":null},{"id":"2106.04563","title":"XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2106.02300","title":"AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER","created":"2021-06-04","cited_by_count":17,"area":null},{"id":"2206.02873","title":"No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval","created":"2022-06-06","cited_by_count":17,"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":"2211.02738","title":"Intriguing Properties of Compression on Multilingual Models","created":"2022-11-04","cited_by_count":15,"area":null},{"id":"2212.08985","title":"Efficient Image Captioning for Edge Devices","created":"2022-12-18","cited_by_count":14,"area":null},{"id":"2206.01838","title":"Differentially Private Model Compression","created":"2022-06-03","cited_by_count":13,"area":null},{"id":"2210.04573","title":"HumSet: Dataset of Multilingual Information Extraction and Classification for Humanitarian Crisis Response","created":"2022-10-10","cited_by_count":7,"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":"2103.06418","title":"LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation","created":"2021-03-11","cited_by_count":5,"area":null},{"id":"2110.11869","title":"FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution Networks","created":"2021-09-12","cited_by_count":5,"area":null},{"id":"2209.09593","title":"EffEval: A Comprehensive Evaluation of Efficiency for MT Evaluation Metrics","created":"2022-09-20","cited_by_count":4,"area":null},{"id":"2201.05767","title":"Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems","created":"2022-01-15","cited_by_count":3,"area":null},{"id":"2302.05454","title":"Distillation of encoder-decoder transformers for sequence labelling","created":"2023-02-10","cited_by_count":3,"area":null},{"id":"2412.04637","title":"Semantic Retrieval at Walmart","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2505.16463","title":"AnchorFormer: Differentiable Anchor Attention for Efficient Vision Transformer","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2501.05465","title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2506.06238","title":"Explaining Matters: Leveraging Definitions and Semantic Expansion for Sexism Detection","created":"2025-06-06","cited_by_count":2,"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":"2408.08684","title":"Research on Personalized Compression Algorithm for Pre-trained Models Based on Homomorphic Entropy Increase","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2109.08627","title":"Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications","created":"2021-09-17","cited_by_count":0,"area":null},{"id":"2301.13683","title":"Friend-training: Learning from Models of Different but Related Tasks","created":"2023-01-31","cited_by_count":0,"area":null}],"next_cursor":null}