Tianyu Chen

Mechanized Type Safety for Gradual Information Flow

2021

We model a security-typed language with gradual information flow labels in a proof assistant, demonstrate its potential application to parsing and securing sensitive user input data, present the semantics as a definitional interpreter, and prove …

MoEC: Mixture of Expert Clusters

2022 · arXiv (Cornell University)

Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead. MoE converts dense layers into sparse experts, and utilizes a gated routing network to make experts …

Learning Sequence Recommendation Algorithm Based on Learner Interest and Neighborhood Information

2024

Now, most of the sequential recommendation algorithms model learner interests and course information based on the current learner's learning sequence, lacking the use of course order information and mining course information in the neighborhood sequence, …