Jongheon Kim's picture

4

Jongheon Kim

jhkim631

·

AI & ML interests

LLM

Recent Activity

upvoted a paper 18 days ago

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

upvoted a paper about 1 month ago

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

upvoted a paper about 1 month ago

Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning

View all activity

Organizations

None yet

models 3

jhkim631/klue-roberta-small-cross-encoder

jhkim631/klue-roberta-base-klue-sts-mrc

Sentence Similarity • 0.1B • Updated Feb 2 • 4

jhkim631/klue-roberta-base-klue-sts

Sentence Similarity • 0.1B • Updated Feb 1 • 2

datasets 0

None public yet