{"total":10,"rows":[{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"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":"2402.10787","title":"Squat: Quant Small Language Models on the Edge","created":"2024-02-16","cited_by_count":16,"area":null},{"id":"2412.01129","title":"RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy","created":"2024-12-02","cited_by_count":9,"area":null},{"id":"2506.09104","title":"Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2404.16898","title":"How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2510.13998","title":"BitNet Distillation","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2504.13471","title":"From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2508.19087","title":"APT-LLM: Exploiting Arbitrary-Precision Tensor Core Computing for LLM Acceleration","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2609.33601","title":"JustQuant: You Don't Need Smoothing, SVD, or Rotation for 4-Bit Activation Quantization","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}