Jiawei

Hi, @wutaiqiang . Have you compare the performance with and without `-title`. Indeed, in my experiment, I found without `-title` would have a higher BLEU score(14.37) which is closed to...

Hi, @menggehe .Have you changed the `path` according to this [issue](https://github.com/rikdz/GraphWriter/issues/1#issuecomment-553706542)? As I can remember, I have only modified the code for this issue.

Hi, @prach6i. The CTS mask is employed exclusively during the training, and it is not utilized during inference. You can find the pseudocode for the CTS mask in our paper,...

Hi @prach6i We have recently released the training pipeline for our repo. The code for the loss function can be found in the `src/vdr/training/loss.py` [here](https://github.com/jzhoubu/VDR/blob/master/src/vdr/training/loss.py).

Hi @hetong007 . Thank you for your interest in our work and for reaching out. We do have plans to make them available. However, we haven't set a specific timeline...

Hi @hetong007 We have recently released the training scripts for this repo. If you have any further questions or need more assistance, feel free to open a new issue.