作者位次 #2/5ICML 2026Poster· Deep Learning / Robustness
Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
Blaise Delattre · Hengyu WU · Paul Caillon · Wei Yang Bryan Lim · YANG CAO
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Blaise Delattre · Hengyu WU · Paul Caillon · Wei Yang Bryan Lim · YANG CAO
Hengyu WU · YANG CAO
Training data is a critical and often proprietary asset in Large Language Model (LLM) development, motivating the use of data watermarking to embed model-transferable signals for usage verification. We identify low coverage as a vital yet largely overlooked requirement for practicality, as indivi...