PPaperPicks

Wei Wang

5 papers at tracked venues · 4 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models
  2. QAQ: Quality Adaptive Quantization for LLM KV Cache
  3. ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression
  4. Security Attacks on LLM-based Code Completion Tools
  5. Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models