https://c-allergic.github.io/2026-05-11T00:00:00+08:00https://c-allergic.github.io/tags/benchmarking/2026-05-11T00:00:00+08:00https://c-allergic.github.io/blog/2026-05-11T00:00:00+08:00https://c-allergic.github.io/tags/caption-evaluation/2026-05-11T00:00:00+08:00https://c-allergic.github.io/categories/2026-05-11T00:00:00+08:00https://c-allergic.github.io/tags/generative-models/2026-05-11T00:00:00+08:00https://c-allergic.github.io/blog/reproducing-capsbench/2026-05-11T00:00:00+08:00https://c-allergic.github.io/categories/research/2026-05-11T00:00:00+08:00https://c-allergic.github.io/tags/2026-05-11T00:00:00+08:00https://c-allergic.github.io/home/home/https://c-allergic.github.io/home/