VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression

  • 类型:arxiv
  • 标识:2607.12756
  • 链接:https://arxiv.org/abs/2607.12756
  • 主分类:multimodal
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar
  • S2被引:0
  • 影响力被引:0
  • TLDR:VisCo is a training-efficient self-compression framework that reuses the pretrained VLM itself as an intrinsic compressor that compresses visual information using a small set of memory tokens and transfers hierarchical information from encoding to decoding.
  • 副分类:engineering
  • 待LLM分类:否
  • 标题中文:VisCo:利用大语言模型作为视觉 token 压缩的内在编码器
  • TLDR中文:VisCo 是一个训练高效的自压缩框架,复用预训练 VLM 本身作为内在压缩器,使用少量 memory token 压缩视觉信息,并将层次化信息从编码传递到解码。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-27-agent-rag-longcontext-candidates.json
  • [S2 enrich]