Jung Hyun Lee

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling

LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs

Unified Progressive Quantization toward 2-bit Instruction-Tuned LLMs

Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models