💭 About me

I am an undergraduate student in Software Engineering at Tongji University and an incoming Ph.D. student at Shanghai Jiao Tong University, jointly trained at Shanghai Innovation Institute. My research interests include multimodal large language models, video understanding, video generation, and world models.

• Expected 2027.09: Incoming Jointly Trained Ph.D. Student, Shanghai Innovation Institute.
• Expected 2027.09: Incoming Ph.D. Student, Shanghai Jiao Tong University.
• 2023.09 - 2027.06 (expected): B.Eng., Software Engineering, Tongji University.

• [09/2026] To Think or Not to Think was accepted to NeurIPS 2026 - our work on pre-decisional reasoning budgets for referring audio-visual segmentation.
• [08/2026] PosterMELD is on arXiv - a multi-agent paper-to-poster system with controllable design diversity and editable, print-ready outputs.
• [08/2026] Listening to the Motion released - code and paper page for audio-conditioned kinematic verification in audio-visual segmentation.
• [08/2026] To Think or Not to Think released - paper page and full reproduction docs for pre-decisional reasoning budgets in Ref-AVS.
• [06/2026] DraftCode placed third at the AWS Summit Shanghai hackathon and advanced to the Macau round.
• [05/2026] VoxSprite released - turning any voice into a playable instrument with Web Audio, an ESP32-S3, physical keys, and reactive LEDs.