VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
Paper
•
2510.21323
•
Published
•
3
•
1
Shufan Shen
shufanshen
·
AI & ML interests
Interpretable machine learning, parameter-efficient fine-tuning.
Organizations
Add pipeline tag and enrich model card content
1
#1 opened 2 months ago
by
nielsr
commented
a
paper
2 months ago