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
- Google PhD Fellowship 2026
- SMU Presidential Doctoral Fellowship 2026 and 2025
- SMU SCIS Dean's List 2026 and 2025
- CVPR 2025 Highlight (top 3% of submissions)
Selected Publications
- Scalable Multi-Task Low-Rank Model Adaptation (mtLoRA). Zichen Tian, Antoine Ledent, Qianru Sun. ICLR 2026. Scales multi-task LoRA to 15-25 tasks with Spectral-Aware Regularization, Block-Level Adaptation and Fine-Grained Routing.
- Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning (MetaPEFT / MetaLoRA). Zichen Tian, Yaoyao Liu, Qianru Sun. CVPR 2025 Highlight. Meta-learns PEFT module insertion, layer selection and module-wise learning rates for long-tailed remote-sensing adaptation.
- Learning De-Biased Representations for Remote-Sensing Imagery (debLoRA). Zichen Tian, Zhaozheng Chen, Qianru Sun. NeurIPS 2024. Unsupervised, LoRA-agnostic de-biasing of long-tailed remote-sensing features.
Profiles: ORCID · Google Scholar · Semantic Scholar · OpenAlex · DBLP · Hugging Face · ResearchGate · GitHub