Google Scholar" />

publications

Here is a list of my publications, you can also find me in Google Scholar

2026

  1. Ttrl: Test-time reinforcement learning
    Yuxin Zuo, Kaiyan Zhang, Li Sheng, and 8 more authors
    Advances in Neural Information Processing Systems, 2026
  2. Simplevla-rl: Scaling vla training via reinforcement learning
    Haozhan Li, Yuxin Zuo, Jiale Yu, and 8 more authors
    In International Conference on Learning Representations, 2026
  3. MARCH: Scaling Recurrent Memory with Content-Routed State Anchors
    Ming Zhang, Kaisen Yang, Shu Yu, and 6 more authors
    2026
  4. Post-Trained MoE Can Skip Half Experts via Self-Distillation
    Xingtai Lv, Li Sheng, Kaiyan Zhang, and 12 more authors
    2026
  5. Position: Safe AI Should be Resistant and Resilient in an Evolving World
    Youbang Sun, Xiang Wang, Jie Fu, and 2 more authors
    In Forty-third International Conference on Machine Learning Position Paper Track, 2026

2025

  1. A survey of reinforcement learning for large reasoning models
    Kaiyan Zhang, Yuxin Zuo, Bingxiang He, and 8 more authors
    arXiv preprint arXiv:2509.08827, 2025
  2. Towards a unified view of large language model post-training
    Xingtai Lv, Yuxin Zuo, Youbang Sun, and 8 more authors
    arXiv preprint arXiv:2509.04419, 2025

2024

  1. Provably fast convergence of independent natural policy gradient for markov potential games
    Youbang Sun, Tao Liu, Ruida Zhou, and 2 more authors
    Advances in Neural Information Processing Systems, 2024
  2. Improving LoRA in Privacy-preserving Federated Learning
    Youbang Sun, Zitao Li, Yaliang Li, and 1 more author
    arXiv preprint arXiv:2403.12313, 2024
  3. Global Convergence of Decentralized Retraction-Free Optimization on the Stiefel Manifold
    Youbang Sun, Shixiang Chen, Alfredo Garcia, and 1 more author
    arXiv preprint arXiv:2405.11590, 2024
  4. Linear Convergence of Independent Natural Policy Gradient in Games with Entropy Regularization
    Youbang Sun, Tao Liu, PR Kumar, and 1 more author
    arXiv preprint arXiv:2405.02769, 2024
  5. Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization
    Ermo Hua, Che Jiang, Xingtai Lv, and 7 more authors
    arXiv preprint arXiv:2412.17739, 2024

2023

  1. On the stability analysis of open federated learning systems
    Youbang Sun, Heshan Fernando, Tianyi Chen, and 1 more author
    In 2023 American Control Conference (ACC), 2023

2022

  1. On centralized and distributed mirror descent: Convergence analysis using quadratic constraints
    Youbang Sun, Mahyar Fazlyab, and Shahin Shahrampour
    IEEE Transactions on Automatic Control, 2022

2021

  1. Linear convergence of distributed mirror descent with integral feedback for strongly convex problems
    Youbang Sun, and Shahin Shahrampour
    In 2021 60th IEEE Conference on Decision and Control (CDC), 2021
  2. Distributed Mirror Descent with Integral Feedback: Convergence Analysis from a Dynamical System Perspective
    Youbang Sun, and Shahin Shahrampour
    In 2021 55th Annual Conference on Information Sciences and Systems (CISS), 2021

2020

  1. Distributed mirror descent with integral feedback: Asymptotic convergence analysis of continuous-time dynamics
    Youbang Sun, and Shahin Shahrampour
    IEEE Control Systems Letters, 2020

2018

  1. Can I trust you more? Model-agnostic hierarchical explanations
    Michael Tsang, Youbang Sun, Dongxu Ren, and 1 more author
    arXiv preprint arXiv:1812.04801, 2018