M.Phil. student in Artificial Intelligence · The Chinese University of Hong Kong, Shenzhen
I am an M.Phil. student at the School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen. My advisor is Prof. Zhizheng Wu.
- M.Phil. in Artificial Intelligence (Expected), The Chinese University of Hong Kong, Shenzhen (2026.09 – 2028.06)
- B.Eng. in Artificial Intelligence, Wuhan University (2022.09 – 2026.06)
My research focuses on speech language models (SLM), emotion understanding and generation, and interactive models. During my undergraduate years, I worked on the safety of multimodal large language models — especially representation-level calibration and steering (MMAligner, ACM CCS 2026).
| Memento Skill |
|---|
| Controlled external memory for agents: separate facts from beliefs, keep only high-gradient evidence hot, and recall archives only with a trigger. |
npx skills add waterdrop26651/Memento-skill |
| Spider Memory | MMSteer | Ouroboros Transformer |
|---|---|---|
| Graph-based associative memory for agent conversations, with weighted recall, reflection, and cold-layer archival. | Multimodal model safety research for Qwen2.5-VL-class systems, centered on safety representations and preventative steering. | A cyclic Transformer architecture experiment where independent blocks form a ring and information flows through repeated loops. |
Do not let every note become a tattoo.