Hidetaka Kamigaito

Experimental results and analyses show that IMFD improves multi-face forgery detection by integrating face bounding boxes into the instruction, and consistently outperforms various state-of-the-art methods.

SVD-MBR reveals that by filtering out metric noise, we can significantly improve text generation quality while avoiding the pitfalls of overfitting.

Text-to-image models consistently misinterpret similes, revealing a critical gap in their understanding of figurative language that could undermine their effectiveness in creative applications.