新的LLM压缩技术利用了先进的数学和图像适应性

报道来源 [6]

1. Hugging Face Daily Papers TIER_1 English(EN) · 2026-07-09 08:16

   LUMI：基于LLM的无损图像压缩，不依赖分词器

   Large language model (LLM)-based lossless image compression methods typically represent pixel data through the native text interface of a pretrained model, converting pixel values into token sequences that the LLM processes through its vocabulary head. This design shows that pret…

2. arXiv cs.LG TIER_1 English(EN) · Tycho F. A. van der Ouderaa, Mart van Baalen, Paul Whatmough, Markus Nagel · 2026-07-08 04:00

   Leech Lattice Vector Quantization for Efficient LLM Compression

   arXiv:2603.11021v2 Announce Type: replace Abstract: Scalar quantization of large language models (LLMs) is fundamentally limited by information-theoretic bounds. While vector quantization (VQ) overcomes these limits by encoding blocks of parameters jointly, practical implementati…

3. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Stefan Josef · 2026-07-07 09:12

   学习池化：灵活多向量压缩的轻量级微调

   Late interaction models have shown strong generalization capabilities, often outperforming much larger dense embedding models. One challenge to their widespread deployment is the large number of token vectors they produce per document and the associated storage and memory costs. …

4. arXiv cs.AI TIER_1 English(EN) · Zhuowen Liu, Longkun Hao, Shiyu Feng, Xiaowen Chang, Ruiqun Li, Changqun Li · 2026-07-07 04:00

   LACE-SVD：面向LLM压缩的具有累积误差校正的损失感知SVD

   arXiv:2607.03057v1 Announce Type: cross Abstract: The rapid growth in the parameter scale of large language models (LLMs) has created a strong demand for efficient compression techniques. As a hardware-agnostic and highly compatible approach, low-rank compression has been widely …

5. arXiv cs.CV TIER_1 English(EN) · Chris Xing Tian, Chengkai Wu, Ziyu Wang, Rongqun Lin, Kecheng Chen, Xiandong Meng, Haoliang Li, Shiqi Wang, Siwei Ma · 2026-07-10 04:00

   LUMI：基于LLM的无损图像压缩，不依赖分词器

   arXiv:2607.08221v1 Announce Type: new Abstract: Large language model (LLM)-based lossless image compression methods typically represent pixel data through the native text interface of a pretrained model, converting pixel values into token sequences that the LLM processes through …

6. arXiv cs.CV TIER_1 English(EN) · Siwei Ma · 2026-07-09 08:16

   LUMI：基于LLM的无损图像压缩，不依赖分词器

   Large language model (LLM)-based lossless image compression methods typically represent pixel data through the native text interface of a pretrained model, converting pixel values into token sequences that the LLM processes through its vocabulary head. This design shows that pret…