Early-stage prototypes used to validate system ideas across collaborative inference and conversational AI infrastructure. (Some demos are maintained on student project pages.)
This prototype demonstrates pipeline-style inference split across multiple edge devices. It is a lightweight implementation intended to validate cross-device execution and dataflow for LLM inference.
Note: current prototype focuses on multi-device execution; it does not yet model network variability or bandwidth-aware scheduling.
An internal prototype demonstrating an end-to-end AI application for conversational behavioral health support.
Our proposal was selected as one of 3 awards out of 59 submissions in a highly competitive internal review.
This system is currently maintained as an internal research prototype for behavioral health.