2 papers
cs.CL2026
When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP
Shota Sato, Hajime Kiyama, Tosho Hirasawa +1
Reducing the modality gap between image and text representations in CLIP is widely expected to improve cross-modal alignment and downstream performance. However, a smaller average…
cs.CL2025
Analyzing Continuous Semantic Shifts with Diachronic Word Similarity Matrices
Hajime Kiyama, Taichi Aida, Mamoru Komachi +3
The meanings and relationships of words shift over time. This phenomenon is referred to as semantic shift. Research focused on understanding how semantic shifts occur over multiple…