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 1 day ago

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

liked a dataset 1 day ago

hollyming/HABIT-Bench

authored a paper 2 days ago

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

View all activity

Organizations

upvoted a paper 1 day ago

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

Paper • 2610.24520 • Published 10 days ago • 84

upvoted a paper 7 days ago

Deep Search in Real-World Web Environments

Paper • 2610.30181 • Published 11 days ago • 188

upvoted a paper 3 months ago

When Does Muon Help Agentic Reinforcement Learning?

Paper • 2607.16169 • Published Jul 17 • 15

upvoted a paper 7 months ago

Internal Safety Collapse in Frontier Large Language Models

Paper • 2603.23509 • Published Mar 4 • 31

upvoted a paper 8 months ago

OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens

Paper • 2603.02138 • Published Mar 2 • 151