Hyun Ryu

hyun1905

·

AI & ML interests

AI for Law & Philosophy, critical thinking, logical reasoning

Recent Activity

authored a paper 1 day ago

Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL

upvoted a paper 4 days ago

Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs

upvoted a paper 8 days ago

Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL

View all activity

Organizations

Papers 7

arxiv:2610.33512

arxiv:2603.17432

arxiv:2509.21679

arxiv:2505.17225

models 2

hyun1905/qwen3-4b-instruct-2507-soundness-judge-sft

Text Generation • 4B • Updated Aug 20 • 151

hyun1905/qwen3-4b-instruct-2507-review-point-oneshot-sft

Text Generation • 4B • Updated Aug 20 • 1.34k

datasets 0

None public yet