2 papers
cs.CV2026
Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack
Nanxiang Jiang, Zhaoxin Fan, Enhan Kang +6
Recent advances in text-to-image (T2I) diffusion models have enabled impressive generative capabilities, but they also raise significant safety concerns due to the potential to pro…
cs.CV2025
SparseFocus: Learning-based One-shot Autofocus for Microscopy with Sparse Content
Yongping Zhai, Xiaoxi Fu, Qiang Su +8
Autofocus is necessary for high-throughput and real-time scanning in microscopic imaging. Traditional methods rely on complex hardware or iterative hill-climbing algorithms. Recent…