الباحثون

Zhi Li

المنشورات 2

نسخة أولية وصول مفتوح

Collaboratively Guided Adversarial Robust Distillation with Teacher-Favorable Examples

Zhi Li, Haowei Liu, Hongchen Yang وآخرون · 2026

Adversarial distillation transfers robustness from high-capacity teachers to compact students. Existing adversarial distillation methods mainly use teacher predictions on clean or adversarial examples to supervise student learning. However, teacher-favorable supervision within the perturbation neighborhood remains unde …

نسخة أولية وصول مفتوح

HERO: Histology Encoder for Robust Representation in Oncology

Zhi Li, Eghbal Amidi, Yating Cheng وآخرون · 2026

Foundation models trained on large pathology image corpora now provide strong, transferable representations for computational pathology. Over the past few years a series of such models has been released, each trained on more slides than the last; on standard classification and segmentation benchmarks, the leading model …

المؤلفون المشاركون