Scalable Multi-Task Low-Rank Model Adaptation
Paper • 2603.01526 • Published • 1
Zichen Tian
doem1997
AI & ML interests
I study how pretrained models learn beyond their prior: finding the underlying structure of knowledge, and spending rare observations where they matter most. This line of work includes debLoRA (NeurIPS 2024), MetaPEFT (CVPR 2025 Highlight) and mtLoRA (ICLR 2026).
Recent Activity
authored a paper 2 days ago
Scalable Multi-Task Low-Rank Model Adaptation authored a paper 2 days ago
Learning De-Biased Representations for Remote-Sensing Imagery authored a paper 2 days ago
Meta-Learning Hyperparameters for Parameter Efficient Fine-TuningOrganizations
None yet
authored 3
papers 2 days ago
upvoted 3
papers 2 days ago
updated a
dataset 2 days ago
updated a
model 2 days ago
updated a
dataset 2 days ago
upvoted a paper 5 months ago
updated a
dataset 10 months ago
published a
dataset 10 months ago
published a
dataset 12 months ago
updated a
dataset about 1 year ago
published a
dataset about 1 year ago
liked 2
datasets over 1 year ago
liked a
model over 1 year ago
published a
dataset over 1 year ago
liked a
model about 3 years ago
