Cheng

RosyCheng

5 1

·

https://scholar.google.com/citations?user=smUBVOQAAAAJ&hl=en

Rosy0912

AI & ML interests

LLM Alignment&Security

Recent Activity

upvoted a paper 2 days ago

HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory

liked a dataset 3 days ago

hollyming/HABIT-Bench

authored a paper 3 days ago

Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models

View all activity

Organizations

Papers 14

arxiv:2610.24520

arxiv:2610.30181

arxiv:2610.21569

arxiv:2608.07531

models 0

None public yet

datasets 0

None public yet