publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. arXiv
    Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning
    Yijia Fan, Ziqi Huang, Zhongang Cai, and 5 more authors
    arXiv preprint arXiv:2609.35767, 2026
    arXiv Code Website
  2. arXiv
    Resource2Skill: Distilling Executable Agent Skills from Human-Created Multimodal Resources
    Yijia Fan, Zonglin Di, Zimo Wen, and 8 more authors
    arXiv preprint arXiv:2606.29538, 2026
    arXiv Code Website
  3. arXiv
    Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks
    Boxiu Li, Zimo Wen, Yijia Fan, and 24 more authors
    arXiv preprint arXiv:2608.05144, 2026
    arXiv Website
  4. arXiv
    Beyond Text Conditioning: A Systematic Study of MLLM-DiT Fusion for Video Generation
    Yanbo Ding, Yijia Fan, Caihua Shan, and 8 more authors
    arXiv preprint arXiv:2608.14043, 2026
    arXiv
  5. arXiv
    Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
    Miaosen Zhang, Xiaohan Zhao, Zhihong Tan, and 14 more authors
    arXiv preprint arXiv:2605.12501, 2026
    arXiv
  6. arXiv
    UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?
    Zimo Wen, Boxiu Li, Wanbo Zhang, and 11 more authors
    arXiv preprint arXiv:2603.03241, 2026
    arXiv Code