Zichen Tian (Jason)

PhD candidate in Artificial Intelligence at Singapore Management University (SMU CVML Lab, advised by Prof. Qianru Sun). Previously research associate at S-Lab, Nanyang Technological University, and at Tsinghua University.

I study the irreducible: what the known cannot explain, and how knowledge grows from it. Specifically, I study how pretrained models learn beyond their prior: finding the underlying structure of knowledge, and directing rare observations to where they matter most. This line of work includes debLoRA (NeurIPS 2024), MetaPEFT (CVPR 2025 Highlight) and mtLoRA (ICLR 2026). Methods: parameter-efficient fine-tuning (LoRA, PEFT), long-tailed and multi-task adaptation, remote-sensing foundation models.

Honors

Selected Publications

All papers · llms.txt

Profiles: ORCID · Google Scholar · Semantic Scholar · OpenAlex · DBLP · Hugging Face · ResearchGate · GitHub