← Search

Robert Gmyr

2 accepted papers

2024

i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data

NAACL 2024findings

The convergence of text, visual, and audio data is crucial towards human-like artificial intelligence, however the current Vision-Language-Speech landscape is dominated by encoder-only models that lack generative abilities. We propose closing this gap with i-Code V2, one of the first models capable…

Cited by 3SourcePDFScholar
2023

i-Code: An Integrative and Composable Multimodal Learning Framework

AAAI 2023technical

Human intelligence is multimodal; we integrate visual, linguistic, and acoustic signals to maintain a holistic worldview. Most current pretraining methods, however, are limited to one or two modalities. We present i-Code, a self-supervised pretraining framework where users may flexibly combine the m…