E. Serpedin

Retaining even a single structural relative slashes post-deletion retraining loss by $8\times$, revealing that target accuracy after unlearning is often driven by intrinsic dataset redundancy rather than unlearning failure.

A model-free benchmark reveals that vision-language models often misread rather than misreason, exposing a performance gap that a supervised vision model can surpass.

Integrating prompt-conditioned channel attention can boost segmentation accuracy by over 23% in challenging medical imaging tasks.