search

mertyg / vision-language-models-are-bows

Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023
MIT License
261 stars 15 forks source link

When can you provide code and dataset？ #2

Closed BigHyf closed 1 year ago

BigHyf commented 1 year ago

Great job! But it has been a long time, I would like to ask when you can provide the source code, or you can provide your data set first？ Thank you very much！

vinid commented 1 year ago

Hello,

Like mentioned in the other thread, we will need more time for the release.

Thank you for your patience.

BigHyf commented 1 year ago

Thank you for your reply

But wasn't it said a few weeks ago that it would be announced in a week or two weeks, before the camera was ready, was there some kind of accident?

vinid commented 1 year ago

Please wait a little more.

As explained in the thread of the other open issue (see here) we will need more time due to the recent events.

mertyg commented 1 year ago

Hi @BigHyf ,

Thank you for your patience. I apologize for the delay in releasing the code and the camera-ready version, this was completely on me. I am currently in Turkey after the Turkey-Syria earthquake, thus haven't been able to finish this release so I've just released what we've prepared so far. Please let us know here if there are things we missed, we will do our best to complete the missing bits.

I wrote this to the other thread as well, but want to reiterate. Please consider donating, and please consider asking your friends with connections to the regions how they are doing, and if they need help.

BigHyf commented 1 year ago

I am sorry to hear that!

I wish you all the best and look forward to your update!