Publications

Published papers and preprints. Project summaries are on the Projects page.

* Equal contribution (co-first authors).

Published Papers

2026

  1. TRACE: Training-time Report-guided and Clinically Ordered Concept Editing
    W. Yue*, Tianyou Lai*, J. Luo, and 4 more authors
    In ACM International Conference on Multimedia (ACM MM), Rio de Janeiro, Brazil, 2026
  2. FREDNet: A Frequency and Decomposed-Spatial Network for Industrial Defect Signal Detection
    H. Zhou*, Tianyou Lai*, C. Hao, and 3 more authors
    In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, 2026
  3. A Review of Federated Learning under Data Heterogeneity
    W. Yue, Tianyou Lai, Q. Mao, and 2 more authors
    Expert Systems, 2026

2025

  1. Deep Learning-Based Inverse Design of Broadband Metasurface Polarization Converter
    Y. Zhou, Tianyou Lai, and X. He
    AIP Advances, 2025
  2. A Modularity-Enhanced Echo State Network for Nonlinear Wind Energy Predicting
    S. Yue, Z. Zhao, Tianyou Lai, and 1 more author
    Energies, 2025

Preprints

2026

  1. Which Differences Matter? Controlled Tests of Rule Transfer, Joint Reliability, and Information Use in Decision Models
    Tianyou Lai*, W. Yue*, Z. Zuo, and 1 more author
    arXiv, 2026
  2. Correct Choices, Failed Sequences: Choice2Seq Benchmarks Correctness Retention Across Output Interfaces
    Tianyou Lai, W. Yue, Z. Deng, and 1 more author
    arXiv, 2026
  3. FedSAP: Federated Learning with Structured Adaptive Partitioning for Multi-Domain Heterogeneous Edge Devices
    W. Yue, Tianyou Lai, H. Li, and 2 more authors
    arXiv, 2026
  4. After Cooperation Is Learned: Gradient Routing and Optimizer-Dependent Maintenance in Multi-Agent Reinforcement Learning
    C. Hao, W. Yue, Tianyou Lai, and 4 more authors
    arXiv, 2026
  5. Beyond Domain-Level Adaptation: Margin-Oriented Semantic-Appearance Interaction Correction for Personalized Federated Vision-Language Models
    W. Yue, Q. Mao, Tianyou Lai, and 2 more authors
    arXiv, 2026
  6. ReLaMix: Residual Latency-Aware Mixing for Delay-Robust Financial Time-Series Forecasting
    Tianyou Lai*, W. Yue*, J. Zhou, and 5 more authors
    arXiv, 2026
  7. Depth as a Candidate Source: Portfolio Allocation for Recurrent Test-Time Scaling in Large Language Models
    Chaoyuan Hao, Wentao Yue, Yanyan Wu, Tianyou Lai, and 5 more authors
    arXiv, 2026

Visit History

Loading visit history…