About
Experience
Publications
Activities
Light
Dark
Automatic
SignRot: LLM Quantization with Massive Outlier-Aware Sign-Adjusted Rotation
Jaehun Gim
,
Jaewoo Kim
,
Gyuwan Kim
,
Seo Yeon Park
September 2026
Type
Conference paper
LLMs
Quantization
Efficiency
Related
CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG
PPA-Plan: Proactive Pitfall Avoidance for Reliable Planning in Long-Context LLM Reasoning
Lost in Mimicry: Verified Training-Free Post-Editing for LLM Translationese
Global Optimization and Inference-Time Region Grafting for Agentic Workflows
KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
Cite
×