Repository navigation
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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, thank you for maintaining this list!
This PR updates the existing GroundingJev entry, accepted in #250, to the project's current name, Jag, along with its repository URL, paper link, and current evaluation result.
Jag is a compact Qwen3.5-0.8B visual grounding model that predicts a continuous bounding box in one forward pass. Its published evaluation reports a 3.62× single-request speedup over LocateAnything. The paper, code, weights, and demo are available.
The model does not call the TypeSafe Jev API or use Jev weights. This change updates the previously accepted entry without implying such an integration; please let me know if you would prefer a different category or treatment under the current inclusion rules.
Validation: regenerated the README from the category source, checked deterministic output and entry tags, passed all 34 upstream offline tests, and checked whitespace. Only the existing entry and its generated README line are changed.
AI assistance was used for documentation editing in this PR.