VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
Paper
•
2510.21323
•
Published
•
3
Shufan Shen
shufanshen
·
AI & ML interests
Interpretable machine learning, parameter-efficient fine-tuning.
Recent Activity
new activity
about 1 month ago
shufanshen/VL-SAE:Add pipeline tag and enrich model card content
updated
a model
about 1 month ago
shufanshen/VL-SAE
authored
a paper
about 1 month ago
Kernelized Sparse Fine-Tuning with Bi-level Parameter Competition for
Vision Models
Organizations
upvoted
2
papers
about 1 month ago