2 papers
cs.CL2026
Selective Test-Time Debiasing for CLIP via Reward Gating
Jaeho Han, Jisoo Yang, Hyeondong Woo +3
Vision language models (VLMs) demonstrate strong zero-shot performance, but often perpetuate social stereotypes in person-centric queries, yielding skewed demographic distributions…
cs.CV2026
Language-Grounded Multi-Domain Image Translation via Semantic Difference Guidance
Jongwon Ryu, Joonhyung Park, Jaeho Han +4
Multi-domain image-to-image translation re quires grounding semantic differences ex pressed in natural language prompts into corresponding visual transformations, while preserving…