Gorilla-Lab-SCUT/PaDT

[ICLR 2026] Official implementation of "Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs"

42
/ 100
Emerging

This project helps visual content analysts and researchers accurately identify and segment objects within images based on text descriptions. You input an image and a natural language query about an object, and it outputs the exact location (bounding box) or pixel-level segmentation mask for that object, along with relevant textual responses. This is ideal for those who need precise visual grounding from text prompts across various image understanding tasks.

251 stars.

Use this if you need a multimodal AI model that can precisely identify and segment specific objects in images based on descriptive text queries, directly generating visual outputs rather than just coordinate numbers.

Not ideal if your primary need is general image captioning or if you don't require highly precise visual localization and segmentation tied to textual references.

object-detection image-segmentation visual-question-answering multimodal-analysis content-analysis
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 11 / 25

How are scores calculated?

Stars

251

Forks

13

Language

Python

License

Apache-2.0

Last pushed

Oct 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Gorilla-Lab-SCUT/PaDT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.