Search Results - Zhu, Tianshu

  • Showing 1 - 5 results of 5
Refine Results
  1. 1
    Cover Image

    QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning Autoría: Rajabzadeh, Hossein, Valipour, Mojtaba, Zhu, Tianshu, Tahaei, Marzieh, Kwon, Hyock Ju, Ghodsi, Ali, Chen, Boxing, Rezagholizadeh, Mehdi

    Published 2024
    Fuente: arXiv
    Tipo de material: Preprint
    Acceso al recurso
    Enlace del recurso

    Save to List
    Saved in:
  2. 2
    Cover Image

    WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games Autoría: Zhang, Wenyu, You, Guoliang, Tianlun, Zhao, Haotian, Zhu, Tianshu, Wang, Haoran, Tang, Xiaoxuan, Dai, Mingyang, Gu, Jingnan, Dong, Daxiang, Wu, Jianmin

    Published 2026
    Fuente: arXiv
    Tipo de material: Preprint
    Acceso al recurso
    Enlace del recurso

    Save to List
    Saved in:
  3. 3
    Cover Image

    Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime Autoría: Zhu, Tianshu, Zhang, Wenyu, Zuo, Xiaoying, Tian, Lun, Zhao, Haotian, Zeng, Yucheng, Gu, Jingnan, Dong, Daxiang, Wu, Jianmin, Yin, Dawei, Shen, Dou

    Published 2026
    Fuente: arXiv
    Tipo de material: Preprint
    Acceso al recurso
    Enlace del recurso

    Save to List
    Saved in:
  4. 4
    Cover Image

    AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning Autoría: Zhao, Haotian, Zhou, Songlin, Zhang, Yuxin, Yau, Stephen S. -T., Zhang, Wenyu, Tian, Lun, Zhu, Tianshu, Huang, Yifeng, Zeng, Yucheng, Gu, Jingnan, Dong, Daxiang, Wu, Jianmin

    Published 2026
    Fuente: arXiv
    Tipo de material: Preprint
    Acceso al recurso
    Enlace del recurso

    Save to List
    Saved in:
  5. 5
    Cover Image

    SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks Autoría: Zeng, Yucheng, Li, Shupeng, Dong, Daxiang, Xu, Ruijie, Chen, Zimo, Zheng, Liwei, Li, Yuxuan, Zhou, Zhe, Zhao, Haotian, Tian, Lun, Xiao, Heng, Zhu, Tianshu, Hao, Longkun, Wu, Jianmin

    Published 2026
    Fuente: arXiv
    Tipo de material: Preprint
    Acceso al recurso
    Enlace del recurso

    Save to List
    Saved in:

Search Tools: