Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

2 articles · 2 sources · updated 8 hours ago

Recent

machinebrief.comMultimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks8 hours ago · By Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu, Vaidehi Patil

0

modus-multimodal.epfl.chMODUS: A Unified Decoder-Only Model for Any-to-Any Multimodal Generationyesterday

0

Posts from social

François Fleuret@francoisfleuretMODUS: Decoder-only Any-to-Any Modeling of Diverse ModalitiesPosted on X· 103 likes· yesterday