CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation
Abstract We present CoDi-2 a Multimodal Large Language Model (MLLM) for learning in-
context interleaved multimodal representations. By aligning modalities with language for …
context interleaved multimodal representations. By aligning modalities with language for …
CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation
Z Tang, Z Yang, M Khademi, Y Liu, C Zhu… - arXiv e …, 2023 - ui.adsabs.harvard.edu
We present CoDi-2, a versatile and interactive Multimodal Large Language Model (MLLM)
that can follow complex multimodal interleaved instructions, conduct in-context learning …
that can follow complex multimodal interleaved instructions, conduct in-context learning …
CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation
Z Tang, Z Yang, M Khademi, Y Liu, C Zhu… - arXiv preprint arXiv …, 2023 - arxiv.org
We present CoDi-2, a versatile and interactive Multimodal Large Language Model (MLLM)
that can follow complex multimodal interleaved instructions, conduct in-context learning …
that can follow complex multimodal interleaved instructions, conduct in-context learning …