Xiyu Deng — accepted AI-conference papers

2026

Training-Free Guided Diffusion for Planning: A Unified Framework via Doob’s h-Transform with Safety Guarantees

Kenta Hoshino, Yashaswi Shashank Aluru, Xiyu Deng, Yorie Nakahira

ICML 2026poster

This paper studies the theoretical foundations of guidance mechanisms in continuous-time score-based diffusion models. We adopt Doob’s h-transform as a principled framework for characterizing ideal guided diffusion processes and analyze the discrepancy between ideal and approximate guidance. Our ana…

Cited by 0 Source ↗Scholar ↗

2024

Physics-Informed Representation and Learning: Control and Risk Quantification

Zhuoyuan Wang, Reece Keller, Xiyu Deng, Kenta Hoshino, Takashi Tanaka, Yorie Nakahira

AAAI 2024technical

Optimal and safety-critical control are fundamental problems for stochastic systems, and are widely considered in real-world scenarios such as robotic manipulation and autonomous driving. In this paper, we consider the problem of efficiently finding optimal and safe control for high-dimensional syst…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗