Showing 1–12 of 12 results
/ Date/ Name
Jun 20, 2024Fantastic Copyrighted Beasts and How (Not) to Generate ThemMar 21, 2025The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least PrivilegeJun 26, 2024CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMsJan 27, 2023Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness InterventionsApr 1, 2024What is in Your Safe Data? Identifying Benign Data that Breaks SafetySep 1, 2025Statutory Construction and Interpretation for Artificial IntelligenceMay 29, 2024AI Risk Management Should Incorporate Both Safety and SecurityDec 18, 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and SkillsJan 3, 2025Metadata Conditioning Accelerates Language Model Pre-trainingJun 20, 2024SORRY-Bench: Systematically Evaluating Large Language Model Safety RefusalDec 10, 2024On Evaluating the Durability of Safeguards for Open-Weight LLMsMar 20, 2026DataProphet: Demystifying Supervision Data Generalization in Multimodal LLMs