Blog Tags GitHub

multimodal-llm

2 posts tagged with "multimodal-llm"

OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models

免训练的两阶段渐进式 token 压缩框架：LLM 前的模态特异结构压缩 + LLM 内的查询条件音视协同精炼

token-compression omni-modal multimodal-llm audio-visual-understanding efficient-inference training-free

HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation

HAM-VLN 为 zero-shot VLN agent 提供决策耦合的层次化记忆系统，通过世界图存储导航历史，结合动态门控检索，在无需训练的情况下超越现有方法

vision-language-navigation vln embodied-ai multimodal-llm agentic-memory zero-shot robotics world-graph