add vinoground #326
Merged
add vinoground #326
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
|
Hi thanks for this PR, can you also pin a result screenshot for a random model? Also there are some linting issues may need to use |
Contributor
Author
|
Contributor
Author
|
I have just ran pre-commit and fixed the linting. |
Luodian
approved these changes
Oct 16, 2024
KairuiHu
pushed a commit
that referenced
this pull request
Oct 24, 2024
Co-authored-by: jzhang2427 <[email protected]>
ZhaoCinyu
pushed a commit
to ZhaoCinyu/lmms-eval
that referenced
this pull request
Dec 9, 2024
Co-authored-by: jzhang2427 <[email protected]>
MichalCiesiolka
pushed a commit
to MichalCiesiolka/lmms-eval-llmzszl
that referenced
this pull request
Apr 3, 2025
Co-authored-by: jzhang2427 <[email protected]>
dadwadw233
pushed a commit
to dadwadw233/lmms-eval
that referenced
this pull request
Apr 28, 2025
Co-authored-by: jzhang2427 <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hi, I want to add our video benchmark Vinoground to the lmms-eval database. This temporal counterfactual benchmark contains 1000 short and natural video-caption pairs. The best model, GPT-4o, can only perform at 35% on one of our metrics, while humans can achieve ~90% at ease. I have been able to reproduce our results with the code provided here on LLaVA-Video-7B-Qwen2. I believe that more models should be allowed to evaluate on Vinoground to truly test their dense temporal reasoning capabilities, and hence i find lmms-eval a great platform to do so.