{"total":18,"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":"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":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48,"area":null},{"id":"2404.08763","title":"CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models","created":"2024-04-12","cited_by_count":41,"area":null},{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39,"area":null},{"id":"2205.01500","title":"Meta Learning for Natural Language Processing: A Survey","created":"2022-05-03","cited_by_count":26,"area":null},{"id":"2308.07120","title":"Position: Key Claims in LLM Research Have a Long Tail of Footnotes","created":"2023-08-14","cited_by_count":20,"area":null},{"id":"2310.09499","title":"One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models","created":"2023-10-14","cited_by_count":16,"area":null},{"id":"2504.15027","title":"DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models","created":"2025-04-21","cited_by_count":10,"area":null},{"id":"2205.00258","title":"EasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing","created":"2022-04-30","cited_by_count":9,"area":null},{"id":"2210.09922","title":"Few-Shot Learning of Compact Models via Task-Specific Meta Distillation","created":"2022-10-18","cited_by_count":5,"area":null},{"id":"2502.10284","title":"A Hybrid Cross-Stage Coordination Pre-ranking Model for Online Recommendation Systems","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2502.14910","title":"EvoP: Robust LLM Inference via Evolutionary Pruning","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2501.15278","title":"PIP: Perturbation-based Iterative Pruning for Large Language Models","created":"2025-01-25","cited_by_count":1,"area":null},{"id":"2510.13832","title":"Entropy Meets Importance: A Unified Head Importance-Entropy Score for Stable and Efficient Transformer Pruning","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2305.14208","title":"Domain Private Transformers for Multi-Domain Dialog Systems","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2511.22955","title":"Experts are all you need: A Composable Framework for Large Language Model Inference","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2607.09936","title":"SMETA-ZSL:Semantic Meta-Alignment for Zero-Shot Threat Classification","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}