Request for BDD-100k and LIS Evaluation Code and Prompt Details

[sohyun-l]

Hi, Thank you for your great work.
I’m interested in how you conducted your evaluations on the BDD-100k and LIS datasets.

Could you please share the code you used to run the evaluations on these datasets?
Any specific instructions would be really helpful.

Did you perform your inference on the validation set of these datasets?
I want to know the exact protocol you followed for reproducibility.

I’m also curious about the prompts you used when running inference.
Could you share any files showing how you generated or stored these prompts?

Thank you so much in advance for your help!