Yi Gu

CapSeal introduces a capability-sealed secret mediation architecture that replaces direct secret exposure to AI agents with constrained, non-exportable action capabilities mediated by a local trusted broker.

This paper demonstrates a novel attack against the shuffling defense used in secure Transformer inference, showing that randomly permuted activations can still be exploited to recover model weights.

AutoSci is a memory-centric agentic system designed to automate the entire scientific research lifecycle by integrating structured memory, multi-stage execution, and continuous self-improvement.

The paper introduces HomeFlow, a verifiable data flywheel that procedurally generates high-quality, multi-turn training data for smart home agents, achieving state-of-the-art performance on smart home tasks.

The paper introduces SMH-Bench, a comprehensive benchmark built on a simulator to rigorously test LLM agents' ability to perform complex, environment-grounded reasoning and actions in realistic smart-home scenarios.