{"total":12,"rows":[{"id":"2203.10705","title":"Compression of Generative Pre-trained Language Models via Quantization","created":"2022-03-21","cited_by_count":79,"area":null},{"id":"2105.14444","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","created":"2021-05-30","cited_by_count":56,"area":null},{"id":"2411.15927","title":"Generative Prompt Internalization","created":"2024-11-24","cited_by_count":8,"area":null},{"id":"2103.11083","title":"Compacting Deep Neural Networks for Internet of Things: Methods and Applications","created":"2021-03-20","cited_by_count":6,"area":null},{"id":"2410.00362","title":"FedPT: Federated Proxy-Tuning of Large Language Models on Resource-Constrained Edge Devices","created":"2024-10-01","cited_by_count":5,"area":null},{"id":"2503.19123","title":"Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2505.12043","title":"MoL for LLMs: Dual-Loss Optimization to Enhance Domain Expertise While Preserving General Capabilities","created":"2025-05-17","cited_by_count":3,"area":null},{"id":"2206.15014","title":"Compressing Pre-trained Transformers via Low-Bit NxM Sparsity for Natural Language Understanding","created":"2022-06-30","cited_by_count":2,"area":null},{"id":"2604.09066","title":"Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2407.03387","title":"ConCodeEval: Evaluating Large Language Models for Code Constraints in Domain-Specific Languages","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2110.00929","title":"Scheduling Optimization Techniques for Neural Network Training","created":"2021-10-03","cited_by_count":0,"area":null},{"id":"2606.23124","title":"PRIDE: Privileged Information-enhanced Distillation for Empathetic Dialogue Generation","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":null}