Yuhang Wen

ABOUT ME

I’m an LLM Post-Training Engineer at RedNote (Xiaohongshu) Dots. Previously, I obtained my Master’s degree at Sun Yat-sen University, and gained industry experience at Qwen Large Model Application Team and Moonshot AI. My research focuses on Agentic RL and RL Post-Training. I am particularly interested in exploring CLI agents.

EDUCATION

Sun Yat-sen University, Master's, 2023 - 2026
Sun Yat-sen University, BEng, 2019 - 2023

EXPERIENCE

RedNote (Xiaohongshu) Hi Lab, LLM Post-Training Engineer
Qwen Large Model Application Team (previously Alibaba QuarkLLM), Research Intern
Moonshot AI, RL Team, Research Intern

ACADEMIC SERVICE

Reviewer: NeurIPS 2025, ACM Multimedia 2025 & 2026

selected publications

ICLR

Search Self-play: Pushing the Frontier of Agent Capability without Supervision

Hongliang Lu^*, Yuhang Wen^*, Pengyu Cheng^†, Ruijin Ding, Jiaqi Guo, Haotian Xu, Chutian Wang, Haonan Chen, Xiaoxi Jiang, and Guanjun Jiang

In International Conference on Learning Representations (ICLR), 2026

arXiv Bib Code

@inproceedings{lu2026searchselfplay,
  title = {Search Self-play: Pushing the Frontier of Agent Capability without Supervision},
  author = {Lu, Hongliang and Wen, Yuhang and Cheng, Pengyu and Ding, Ruijin and Guo, Jiaqi and Xu, Haotian and Wang, Chutian and Chen, Haonan and Jiang, Xiaoxi and Jiang, Guanjun},
  year = {2026},
  booktitle = {International Conference on Learning Representations (ICLR)},
  volume = {},
  number = {},
  dimensions = {true},
}

TNNLS

Surfer: A World Model-Based Framework for Vision-Language Robot Manipulation

Pengzhen Ren^*, Kaidong Zhang^*, Hetao Zheng, Zixuan Li, Yuhang Wen, Fengda Zhu, Shikui Ma, and Xiaodan Liang^†

IEEE Transactions on Neural Networks and Learning Systems, 2025

arXiv Bib PDF Code Website

@article{ren2025surfer,
  title = {Surfer: A World Model-Based Framework for Vision-Language Robot Manipulation},
  author = {Ren, Pengzhen and Zhang, Kaidong and Zheng, Hetao and Li, Zixuan and Wen, Yuhang and Zhu, Fengda and Ma, Shikui and Liang, Xiaodan},
  year = {2025},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  volume = {},
  number = {},
  doi = {10.1109/TNNLS.2025.3594117},
  dimensions = {true},
}

NeurIPS

CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition

Yuhang Wen, Mengyuan Liu^†, Songtao Wu, and Beichen Ding^†

In Advances in Neural Information Processing Systems (NeurIPS), 2024

arXiv Bib PDF Code Website

@inproceedings{wen2024chase,
  author = {Wen, Yuhang and Liu, Mengyuan and Wu, Songtao and Ding, Beichen},
  title = {CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  pages = {9388--9420},
  volume = {37},
  publisher = {Curran Associates, Inc.},
  url = {https://proceedings.neurips.cc/paper_files/paper/2024/file/11f5520daf9132775e8604e89f53925a-Paper-Conference.pdf},
  dimensions = {true},
}