Jun Yan

The paper proposes a novel data transformation framework that creates semantically rich, privacy-preserving numeric views of EHR data, enabling large-scale research while provably breaking patient linkage.

The paper investigates how dynamic adversarial fine-tuning (R2D2) reorganizes the internal mechanisms (refusal geometry) of safety-aligned language models, finding that it shifts the optimal refusal control carrier from late to early layers along a robustness-utility frontier.

This paper analyzes the multi-regime behavior of Scientific Machine Learning (SciML) models, finding that optimization effectiveness is regime-specific and that failure modes require a unified, regime-aware diagnostic approach.

RecGPT-V3 is a stateful, hybrid-modal recommender system that uses a Memory Hub for user memory and a Hybrid-modal Foundation Model for joint reasoning over text tags and Semantic IDs, achieving consistent gains in user experience and commercial outcomes.

This paper analyzes the non-monotonic relationship between perturbation power and the probability of delaying the first error position in finite-length PE-SC decoding. It proposes an efficient perturbation power selection algorithm to maximize the delay probability.