Xiangfu Meng

2 accepted papers

2026

APIC: Orthogonalized Neuro-Symbolic Modeling for Nonlinear Dissipative Dynamics

Yanhui Zhu, Chen Zhao, Yinhao Li, Xiangfu Meng

ICML 2026poster

Current data-driven scientific modeling struggles with a functional dichotomy: neural operators exhibit spectral bias in high-frequency regimes, while physics-constrained paradigms suffer from optimization pathologies. To bridge this gap, we propose Adaptive Physics-Informed Computing (APIC), a neur…

Cited by 0 Source ↗Scholar ↗

2026

DiffVec: Diffusion Model for Trajectory Vector Recovery

Jiaqi Duan, Shengwei Tian, Long Yu, Xiangfu Meng, Ya Zhang

IJCAI 2026

The increasing availability of trajectory data is often hampered by sparsity and noise. Existing trajectory recovery methods are further limited by either information loss from coordinate discretization into location IDs, or the inefficiency of conventional diffusion models that require a lengthy de

Cited by 0 Scholar ↗