{"ID":2848032,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.26446","arxiv_id":"2510.26446","title":"1+1\u003e2: A Synergistic Sparse and Low-Rank Compression Method for Large Language Models","abstract":"Large Language Models (LLMs) have demonstrated remarkable proficiency in language comprehension and generation; however, their widespread adoption is constrained by substantial bandwidth and computational demands. While pruning and low-rank approximation have each demonstrated promising performance individually, their synergy for LLMs remains underexplored. We introduce \\underline{S}ynergistic \\underline{S}parse and \\underline{L}ow-Rank \\underline{C}ompression (SSLC) methods for LLMs, which leverages the strengths of both techniques: low-rank approximation compresses the model by retaining its essential structure with minimal information loss, whereas sparse optimization eliminates non-essential weights, preserving those crucial for generalization. Based on theoretical analysis, we first formulate the low-rank approximation and sparse optimization as a unified problem and solve it by iterative optimization algorithm. Experiments on LLaMA and Qwen2.5 models (7B-70B) show that SSLC, without any additional training steps, consistently surpasses standalone methods, achieving state-of-the-arts results. Notably, SSLC compresses Qwen2.5 by 50\\% with no performance drop and achieves at least 1.63$\\times$ speedup, offering a practical solution for efficient LLM deployment.","short_abstract":"Large Language Models (LLMs) have demonstrated remarkable proficiency in language comprehension and generation; however, their widespread adoption is constrained by substantial bandwidth and computational demands. While pruning and low-rank approximation have each demonstrated promising performance individually, their...","url_abs":"https://arxiv.org/abs/2510.26446","url_pdf":"https://arxiv.org/pdf/2510.26446v1","authors":"[\"Zeliang Zong\",\"Kai Zhang\",\"Zheyang Li\",\"Wenming Tan\",\"Ye Ren\",\"Yiyan Zhai\",\"Jilin Hu\"]","published":"2025-10-30T12:50:30Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}