PrototypeCommon
Fanziyang-v/FlashVID
[ICLR 2026 Oral] FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
- Owner
- Fanziyang-v (personal account)
- Stars
- Stars: 125
- Forks
- Forks: 6
- Language
- Python
- License
- MIT
- Created
- 2026
- Topics
- efficiencymultimodaltoken-compressionvideo-llmsflashvid
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- paraboy-s/mcd-meal-pairingStars: 125PythonPrototype
- ilAoC/mcd-gacha-collectorStars: 125PythonPrototype
- adhiprib/humanizer-indonesiaStars: 125PythonPrototype
- dokterbob/django-agendaStars: 125PythonPrototype
- garethr/django-project-templatesStars: 125PythonPrototype
- jezdez/django-staticfilesStars: 125PythonPrototype