Seonil Son

sonsus

·

AI & ML interests

LLM alignment and evals.

Recent Activity

liked a model about 15 hours ago

DaehanKim/korjev-26b4a-v1

upvoted a paper 2 days ago

Q-Learning with Scalar Adjoint Matching

upvoted a paper 3 days ago

RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning

View all activity

Organizations

None yet

Papers 5

arxiv:2411.01281

arxiv:2403.01479

arxiv:2211.12118

arxiv:2209.10922

spaces 1

HaRiM+

models 1

sonsus/gemma-3-0.7b-vlm-custom

0.7B • Updated Dec 24, 2025 • 11

datasets 0

None public yet