Zhe Fu — accepted AI-conference papers

2026

(U)NFV: Supervised and Unsupervised Neural Finite Volume Methods for Solving Hyperbolic PDEs

Nathan Lichtlé, Alexi Canesse, Zhe Fu, HOSSEIN NICK ZINAT MATIN, Maria Laura Delle Monache, Alexandre M Bayen

ICLR 2026poster

We introduce (U)NFV, a modular neural network architecture that generalizes classical finite volume (FV) methods for solving hyperbolic conservation laws. Hyperbolic partial differential equations (PDEs) are challenging to solve, particularly conservation laws whose physically relevant solutions con…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Fine-tuning LLMs with Cross-Attention-based Weight Decay for Bias Mitigation

Farsheed Haque, Zhe Fu, Depeng Xu, Shuhan Yuan, Xi Niu

EMNLP 2025

Large Language Models (LLMs) excel in Natural Language Processing (NLP) tasks but often propagate societal biases from their training data, leading to discriminatory outputs. These biases are amplified by the models’ self-attention mechanisms, which disproportionately emphasize biased correlations w

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

KFCalibNet: A KansFormer-Based Self-Calibration Network for Camera and LiDAR

Zejing Xu, Yiqing Liu, Ruipeng Gao, Dan Tao, Peng Qi, Ning Zhao +1

ICRA 2025

In autonomous driving and robotic navigation, multi-sensor fusion technology has become increasingly mainstream, with precise sensor calibration as its foundation. Traditional calibration methods rely on manual effort or specific targets, limiting adaptability to complex environments. Learning-based

Cited by 0 Source ↗Scholar ↗

2020

Fourth Order Cumulant Based Active Direction of Arrival Estimation Using Coprime Arrays

Zhe Fu, Pascal Chargé, Yide Wang

ICASSP 2020accepted

Higher order cumulants based direction of arrival (DOA) estimation has attracted increasing attention since several years. However, higher order cumulants for the active DOA estimation has not been thoroughly studied. In this paper, we investigate the fourth order cumulant for active DOA estimation.…

Cited by 0 Source ↗Scholar ↗