PrototypeCommon
HumanMLLM/LLaVA-Scissor
The official code for the paper: LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs
- Owner
- HumanMLLM (organization)
- Stars
- Stars: 122
- Forks
- Forks: 3
- Language
- Python
- License
- None
- Created
- 2025
- Topics
- connected-componentsmllmmultimodal-large-language-modelstoken-compressionvideo-language-understandingvideo-understanding
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by HumanMLLM
All 5 repos by HumanMLLM- HumanMLLM/R1-OmniStars: 1,025PythonBeta
- HumanMLLM/HumanOmniStars: 242PythonPrototype
- HumanMLLM/HumanOmniV2Stars: 165PythonPrototype
- HumanMLLM/SWIMStars: 100PythonPrototype
Nearby in Python
All Python repos- CRFXN5C/mcd-mcp-kitStars: 122PythonPrototype
- aarsaputra/php2shellStars: 122PythonPrototype
- lillyguisnet/sam3-segmentationStars: 122PythonPrototype
- svetlyak40wt/django-fieldsStars: 122PythonPrototype
- metajack/notify-webhookStars: 122PythonPrototype
- bmander/graphserverStars: 122PythonPrototype