Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
AlphaUncommon

xid32/NAACL_2025_TWM

We introduce temporal working memory (TWM), which aims to enhance the temporal modeling capabilities of Multimodal foundation models (MFMs). This plug-and-play module can be easily integrated into existing MFMs. With our TWM, nine state-of-the-art models exhibit significant performance improvements…

Owner
xid32 (personal account)
Stars
Stars: 317
Forks
Forks: 30
Language
Python
License
None
Created
2025
Topics
multimodal-foundation-modelmultimodal-large-language-modelsaudio-visual-learningquestion-answeringvideo-captioningvideo-text-retrievalworking-memory
Tier
Alpha (250 to 699 ★) What this tier means
View on GitHub

More repos by xid32

All 2 repos by xid32

Nearby in Python

All Python repos