Bayesian Coreset Optimization for Personalized Federated Learning
机构 * Department of Computer Science（计算机科学系） ； Indian Institute of Technology Bombay（印度理工学院班加罗尔）
Comments 9 pages, 5 figures, ICLR 2024
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time
机构 * University College London（伦敦大学学院） ； Center on Long-Term Risk（长期风险中心） ； McGill University（麦吉尔大学） ； UK AI Security Institute（英国人工智能安全研究所）
Comments 40 pages, 22 figures. Under review at ICLR 2026
What's the next frontier for Data-centric AI? Data Savvy Agents
机构 * University of Cambridge（剑桥大学） ； Tsinghua University（清华大学）
Comments Presented at ICLR 2025 Data-FM. Seedat & Liu contributed equally
Trustworthy AI Must Account for Interactions
机构 * Jesse C. Cresswell（独立研究者）
Comments Presented at the ICLR 2025 Workshop on Bidirectional Human-AI Alignment
Targeted Attack Improves Protection against Unauthorized Diffusion Customization
机构 * Shanghai Jiao Tong University（上海交通大学） ； University of Southern California（南加州大学）
Comments ICLR 2025 (Spotlight)
