@article{whenandwhatdiffusiongroundedvideollmwith,
  title = {When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding},
  author = {Pengcheng Fang and Yuxia Chen and Rui Guo},
  year = {2025},
  eprint = {2508.15641},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.15641},
}