Gorilla-Lab-SCUT / PaDT
[ICLR 2026] Official implementation of "Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs"
Why this job: works in the areas we cover, but does not say which job it does
What it does
We are pleased to introduce Patch-as-Decodable Token (PaDT), a unified paradigm that enables multimodal large language models (MLLMs) to directly generate both textual and visual outputs.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 months ago
- Stars
- 167
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 92% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 40% closed
- 15 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| FoundationVision / Liquid | 641 | 5 months ago | MIT | No downloads |
| THU-SI / Spatial-MLLM | 497 | 9 months ago | MIT | No downloads |
| aurelio-labs / semantic-router | 4,035 | 3 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 92%
- Shell 8%
Topics
- computer-vision
- large-language-models
- machine-learning
- multimodal-large-language-models
- patch-as-decodable-token
Project record
- JobOther AI tools
- StatusListed
- Commits13
- Forks12
- Watching2
- Stars in 28 days+1
- CreatedSep 26, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026