Xiangyu Yin

ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning

Wenjie Ruan, Sihao Wu, Xiangyu Yin, 2023, AAAI.

Boosting Adversarial Training via Fisher-Rao Norm-based Regularization

Xiangyu Yin, Wenjie Ruan, 2024, ArXiv.

Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming

Sihao Wu, Xiangyu Yin, Jiaxu Liu, 2024, 2405.12604.

Continuous Geometry-Aware Graph Diffusion via Hyperbolic Neural PDE

Sihao Wu, Xiangyu Yin, Jiaxu Liu, 2024, 2406.01282.