logo
today local_bar
Vision-Language Alignment

2 papers across 1 session

Poster Session 4

2 papers
Thursday, December 4, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability
#4704 · Jonggwon Park, Byungmu Yoon, Soobum Kim, Kyoyun Choi
VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
#4616 · Shufan Shen, Junshu Sun, Qingming Huang, Shuhui Wang

We propose a sparse autoencoder that maps the semantics of vision and language representations into a unified concept set.