Login / Signup

EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting.

Zhongzhi YuZheng WangYuhan LiHaoran YouRuijie GaoXiaoya ZhouSreenidhi Reedy BommuYang Katie ZhaoYingyan Celine Lin
Published in: CoRR (2024)
Keyphrases
  • edge information
  • edge detection
  • language learning
  • image sequences
  • multi agent
  • natural language
  • image compression
  • computationally efficient
  • multiple scales
  • color images
  • weighted graph
  • edge points