TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models
1citations
Project1
Citations
#760
in ICCV 2025
of 2701 papers
5
Authors
4
Data Points
Citation History
Jan 24, 2026
0
Jan 26, 2026
0
Jan 26, 2026
0
Jan 27, 2026
1+1