用大模型压缩科学数据，保证误差不超限，效果比现有方法好30%。
LLMComp: A Language Modeling Paradigm for Error-Bounded Scientific Data Compression (Technical Report)
- 将三维数据转为离散符号，用空间序曲线保持局部性，提升模型建模效率。
- 训练自回归模型预测数据符号，压缩时只存排名索引和修正值，误差严格可控。
- 适合需要高保真、低误差的科学数据压缩，如气候模拟与天文观测。
高分辨率科学模拟与观测系统正产生海量时空数据，高效且误差有界的压缩日益重要。本文提出一种基于解码器仅有的大语言模型（LLM）的新型有损压缩范式 LLMCOMP。该方法首先将三维场量化为离散标记，通过 Z-order 曲线排列以保留局部性，并采用覆盖引导采样提升训练效率。随后使用带时空嵌入的自回归变换器建模标记转移。压缩阶段，模型执行 top-k 预测，仅存储排名索引与回退修正值，确保严格误差约束。在多个再分析数据集上的实验表明，LLMCOMP 持续优于当前最优压缩器，在严格误差限制下最高实现 30% 的压缩率提升。结果凸显了大语言模型作为通用高保真科学数据压缩工具的潜力。
原文摘要 · Abstract (English)
The rapid growth of high-resolution scientific simulations and observation systems is generating massive spatiotemporal datasets, making efficient, error-bounded compression increasingly important. Meanwhile, decoder-only large language models (LLMs) have demonstrated remarkable capabilities in modeling complex sequential data. In this paper, we propose LLMCOMP, a novel lossy compression paradigm that leverages decoder-only large LLMs to model scientific data. LLMCOMP first quantizes 3D fields into discrete tokens, arranges them via Z-order curves to preserve locality, and applies coverage-guided sampling to enhance training efficiency. An autoregressive transformer is then trained with spatial-temporal embeddings to model token transitions. During compression, the model performs top-k prediction, storing only rank indices and fallback corrections to ensure strict error bounds. Experiments on multiple reanalysis datasets show that LLMCOMP consistently outperforms state-of-the-art compressors, achieving up to 30% higher compression ratios under strict error bounds. These results highlight the potential of LLMs as general-purpose compressors for high-fidelity scientific data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。