Diving into Self-Evolving Training for Multimodal Reasoning

@misc{he2025divingselfevolvingtraining,
      title={Diving into Self-Evolving Training for Multimodal Reasoning},
      author={Junxian He and Xiwen Zhang and Fan Zhou and Junlong Li and Wei Liu and Yu Cheng},
      year={2025},
      eprint={2412.17451},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.17451},
}