RioJune

RioJune

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 8 hours ago

Self-Distillation with Verbal Regularization

upvoted a paper 4 months ago

STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability

upvoted a paper 5 months ago

RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation

View all activity

Organizations

RioJune 's models 1

RioJune/AG-KD

Zero-Shot Object Detection • 0.3B • Updated Aug 7, 2025 • 24