Asja Fischer

The paper introduces SAMSEM, a generalized and scalable model based on SAM2, which significantly improves metal line segmentation across diverse and unseen integrated circuit (IC) samples.

This paper proposes using random sampling of prediction precision during inference to significantly enhance the adversarial robustness of Automatic Speech Recognition (ASR) systems.

This paper analyzes existing watermarking schemes for autoregressive image generators and demonstrates that they are vulnerable to various removal and forgery attacks, suggesting they are unreliable for content detection and dataset filtering.