PPaperPicks

Janghwan Lee

3 papers at tracked venues · 3 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference
    ACL 2025 · Janghwan Lee
  2. RILQ: Rank-Insensitive LoRA-Based Quantization Error Compensation for Boosting 2-Bit Large Language Model Accuracy
  3. Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment
    ACL 2024 · Janghwan Lee