From 57707a77de6f821b3e45c2f7f9ded1a99f93b315 Mon Sep 17 00:00:00 2001 From: Daizong Liu Date: Thu, 4 Sep 2025 12:48:32 +0800 Subject: [PATCH] update 9.4.2025 --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 27655fb..0dadfcf 100644 --- a/README.md +++ b/README.md @@ -568,7 +568,7 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍. * [ICCV2025] https://arxiv.org/abs/2501.04003 ## Benchmarks -* **Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study** | # +* **Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study** | [Github](https://github.com/oneonlee/Meme-Safety-Bench) # * DongGeon Lee, Joonwon Jang, Jihae Jeong, Hwanjo Yu * POSTECH, LG AI Research - * [Arxiv2025] https://arxiv.org/abs/2505.15389 + * [EMNLP2025] https://arxiv.org/abs/2505.15389