1 citations · 1 across the 1 of their papers we have counts for
2 papers
cs.CL2026
Text-Only vs. Image-Aware VLM Judges for Manga Translation Evaluation
Subaru Kimura, Jun Suzuki
In manga translation, visual context outside speech-bubble text, including speaker identities, referents, and scene tone, is depicted in page images, making it natural to refer to…
cs.CL2024★ 1 cited
Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injection
Subaru Kimura, Ryota Tanaka, Shumpei Miyawaki +2
We explore visual prompt injection (VPI) that maliciously exploits the ability of large vision-language models (LVLMs) to follow instructions drawn onto the input image. We propose…