{"total":24,"rows":[{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2206.09755","title":"Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold","created":"2022-06-20","cited_by_count":29,"area":null},{"id":"2305.01628","title":"The Benefits of Bad Advice: Autocontrastive Decoding across Model Layers","created":"2023-05-02","cited_by_count":29,"area":null},{"id":"2202.07101","title":"A Survey on Dynamic Neural Networks for Natural Language Processing","created":"2022-02-15","cited_by_count":24,"area":null},{"id":"2210.11292","title":"Late Prompt Tuning: A Late Prompt Could Be Better Than Many Prompts","created":"2022-10-20","cited_by_count":23,"area":null},{"id":"2202.04350","title":"pNLP-Mixer: an Efficient all-MLP Architecture for Language","created":"2022-02-09","cited_by_count":19,"area":null},{"id":"2209.09480","title":"Unsupervised Early Exit in DNNs with Multiple Exits","created":"2022-09-20","cited_by_count":10,"area":null},{"id":"2401.10541","title":"I-SplitEE: Image classification in Split Computing DNNs with Early Exits","created":"2024-01-19","cited_by_count":9,"area":null},{"id":"2412.12948","title":"MOPO: Multi-Objective Prompt Optimization for Affective Text Generation","created":"2024-12-17","cited_by_count":9,"area":null},{"id":"2307.09701","title":"Efficiency Pentathlon: A Standardized Arena for Efficiency Evaluation","created":"2023-07-19","cited_by_count":7,"area":null},{"id":"2205.14570","title":"MiniDisc: Minimal Distillation Schedule for Language Model Compression","created":"2022-05-29","cited_by_count":5,"area":null},{"id":"2212.01340","title":"Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking","created":"2022-12-02","cited_by_count":4,"area":null},{"id":"2409.12175","title":"Expanding Expressivity in Transformer Models with M\\\"obiusAttention","created":"2024-09-08","cited_by_count":4,"area":null},{"id":"2503.01488","title":"InversionGNN: A Dual Path Network for Multi-Property Molecular Optimization","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2210.07126","title":"Challenges in Explanation Quality Evaluation","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2508.14170","title":"Comparing energy consumption and accuracy in text classification inference","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2304.12764","title":"Test-Time Adaptation with Perturbation Consistency Learning","created":"2023-04-25","cited_by_count":0,"area":null},{"id":"2306.10056","title":"Generate to Understand for Representation","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2311.07204","title":"On Elastic Language Models","created":"2023-11-13","cited_by_count":0,"area":null},{"id":"2510.27400","title":"Balancing Knowledge Updates: Toward Unified Modular Editing in LLMs","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2608.14550","title":"FLOPs vs Real Work: The Importance of Replication in AI Efficiency Assessment","created":"2026-04-30","cited_by_count":0,"area":null}],"next_cursor":null}