Jang's picture

5

Jang

Hyeongwon

·

HyeongWon-Jang

AI & ML interests

None yet

Recent Activity

upvoted a paper 6 days ago

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

upvoted a paper 17 days ago

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

upvoted a paper 28 days ago

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

View all activity

Organizations

models 0

None public yet

datasets 0

None public yet