6 papers
CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions
Xinyang Liao, Lingyu Li, Kaicheng Shen +4
AI companions provide users with emotional support and ongoing companionship, but their sustained relational interactions also introduce distinct safety risks. Prior work largely t…
LD-EnFF: Latent-Dynamics Ensemble Flow Filtering for Data Assimilation with Sparse Observations
Ziyu Tian, Kaichen Shen, Wenbo Hao +3
Data assimilation combines model forecasts with noisy, incomplete observations to estimate the evolving state of a dynamical system. Existing methods face two compounding challenge…
Long-Term Simulation Exposes Cognitive-Developmental Risks in AI Companions
Kaicheng Shen, Lingyu Li, Wen Wu +3
AI companions powered by large language models increasingly interact with cognition-developing users, including children and adolescents, creating risks that may accumulate over ti…
Sequential Bayesian Optimal Experimental Design in Infinite Dimensions via Policy Gradient Reinforcement Learning
Kaichen Shen, Peng Chen
Sequential Bayesian optimal experimental design (SBOED) for PDE-governed inverse problems is computationally challenging, especially for infinite-dimensional random field parameter…
Latent Nonlinear Denoising Score Matching for Enhanced Learning of Structured Distributions
Kaichen Shen, Wei Zhu
Score-based generative models commonly employ linear forward diffusions with Gaussian reference distributions, limiting their ability to directly incorporate structural information…
MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs
Liang Shan, Kaicheng Shen, Wen Wu +9
Ensuring the safety of Large Language Models (LLMs) is critical for real-world deployment. However, current safety measures often fail to address implicit, domain-specific risks. T…