Yang Song

Yang Song

Lead Data Scientist | LLM Finetuning & Agentic Systems

Full publications (Google Scholar Profile)

Selected Publications

Autonomous Coding Agents

  1. NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agents
    Y. Song, A. Vyas, Z. Wei, S. Khoshfetrat Pakazad, H. Ohlsson, and G. Neubig
    Proc. International Conference on Machine Learning (ICML), 2026.

Adversarial Robustness

  1. Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach
    K. Zhao, Q. Kang, Y. Song, R. She, S. Wang, and W. P. Tay
    Advances in Neural Information Processing Systems (NeurIPS), 2023. (Spotlight)

  2. On the robustness of graph neural diffusion to topology perturbations
    Y. Song* , Q. Kang, S. Wang, K. Zhao*, and W. P. Tay
    Advances in Neural Information Processing Systems (NeurIPS), 2022. (*Equal Contribution)

  3. Stable neural ODE with Lyapunov-stable equilibrium points for defending against adversarial attacks
    Q. Kang*, Y. Song*, Q. Ding, and W. P. Tay
    Advances in Neural Information Processing Systems (NeurIPS), Dec. 2021. (*Equal Contribution)

  4. Error-correcting output codes with ensemble diversity for robust learning in neural networks
    Y. Song* , Q. Kang*, and W. P. Tay
    Proc. AAAI Conference on Artificial Intelligence, 2021. (*Equal Contribution)

Graph Neural Diffusion

  1. Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND
    Q. Kang, K. Zhao, Q. Ding, F. Ji, X. Li, W. Liang, Y. Song, and W. P. Tay
    Proc. International Conference on Learning Representations (ICLR), Vienna, Austria, May 2024. (Spotlight)

  2. Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Study
    Q. Kang, K. Zhao, Y. Song, Y. Xie, Y. Zhao, S. Wang, R. She, and W. P. Tay
    Proc. AAAI Conference on Artificial Intelligence, 2024.

  3. Graph neural convection-diffusion with heterophily
    K. Zhao, Q. Kang, Y. Song , R. She, S. Wang, and W. P. Tay
    Proc. International Joint Conference on Artificial Intelligence (IJCAI), Macao, China, Aug. 2023.

  4. Node embedding from neural Hamiltonian orbits in graph neural networks
    Q. Kang, K. Zhao, Y. Song , S. Wang, and W. P. Tay
    Proc. International Conference on Machine Learning (ICML), Hawaii, USA, Jul. 2023.

Privacy-Aware Signal Processing

  1. Preserving trajectory privacy in driving data release
    Y. Xu, C. X. Wang, Y. Song, and W. P. Tay
    Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), 2022.

  2. Arbitrarily strong utility-privacy tradeoff in multi-agent systems
    C. X. Wang, Y. Song, and W. P. Tay
    IEEE Transactions on Information Forensics and Security, vol. 16, pp. 671 – 684, 2021.

  3. Compressive privacy for a linear dynamical system
    Y. Song, C. X. Wang, and W. P. Tay,
    IEEE Transactions on Information Forensics and Security, vol. 15, pp. 895 – 910, 2020.

Sensor Fusion and Localization

  1. HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion
    S. Wang, Q. Kang, R. She, W. Wang, K. Zhao, Y. Song, and W. P. Tay
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

  2. PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations
    R. She, S. Wang, Q. Kang, K. Zhao, Y. Song, W. P. Tay, T. Geng, and X. Jian
    Proc. AAAI Conference on Artificial Intelligence, 2024.

  3. DistilVPR: Cross-Modal Knowledge Distillation for Visual Place Recognition
    S. Wang, R. She, Q. Kang, X. Jian, K. Zhao, Y. Song, and W. P. Tay
    Proc. AAAI Conference on Artificial Intelligence, 2024.

  4. UWB/LiDAR fusion for cooperative range-only SLAM
    Y. Song* , M. Guan*, W. P. Tay, C. L. Law, and C. Wen
    Int. Conf. on Robotics and Automation (ICRA), Montreal, Canada, May 2019. (*Equal Contribution)

Multi-Modal Data Analysis

  1. Canonical Correlation Analysis of High-Dimensional Data with Very Small Sample Suppor
    Y. Song, P. Schreier, D. Ramirez and T. Hasija,
    Signal Processing, vol. 128, pp. 449-458, Nov. 2016.

  2. Sample-poor Estimation of Order and Common Signal Subspace with Application to Fusion of Medical Imaging Data
    Y. Levin-Schwartz, Y. Song, P. Schreier, V. D. Calhoun and T. Adali,,
    NeuroImage, vol. 134, pp. 486-493, July 2016.

Acoustic Signal Processing

  1. Higher-Order Figure-8 Microphones/Hydrophones Collocated as a Perpendicular Triad – Their “Spatial-Matched-Filter” Beam Steering
    S. Du, K. T. Wong, Y. Song, C. J. NNONYELU and Y. Wu,
    The Journal of the Acoustical Society of America, 2021.

  2. A multilinear approach of direction finding using a sensor-array with multiple scales of spatial invariance
    S. Miron, Y. Song, D. Brie and K. T. Wong,
    EEE Transactions on Aerospace and Electronic Systems, vol. 51, no. 3, pp.2057-2070, July 2015.

  3. Quasi-Blind” Calibration of an Array of Acoustic Vector-Sensors that are Subject to Gain Errors / Mis-Location / Mis-Orientation
    Y. Song, K. T. Wong and F. J. Chen,
    IEEE Transactions on Signal Processing,, vol. 62, no. 9, pp. 2330-2344, May 2014.