Cheng

RosyCheng

4

·

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

Rosy0912

AI & ML interests

LLM Alignment&Security

Recent Activity

authored a paper about 5 hours ago

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

authored a paper about 5 hours ago

Steering the Verifiability of Multimodal AI Hallucinations

authored a paper 1 day ago

Deep Search in Real-World Web Environments

View all activity

Organizations

RosyCheng 's papers 14

arxiv:2610.24520

arxiv:2610.30181

arxiv:2610.21569

arxiv:2608.07531

arxiv:2605.25377

arxiv:2604.06714

arxiv:2511.11301

arxiv:2509.01909

arxiv:2503.18991

arxiv:2412.05892

arxiv:2410.18371

arxiv:2409.04340

arxiv:2405.14517

arxiv:2404.10160