X-VILA: Cross-Modality Alignment for Large Language Model

Autor:	Ye, Hanrong, Huang, De-An, Lu, Yao, Yu, Zhiding, Ping, Wei, Tao, Andrew, Kautz, Jan, Han, Song, Xu, Dan, Molchanov, Pavlo, Yin, Hongxu
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	We introduce X-VILA, an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities. By aligning modality-specific encoders with LLM inputs and diffusion decoders with LLM outputs, X-VILA achieves cross-modality understanding, reasoning, and generation. To facilitate this cross-modality alignment, we curate an effective interleaved any-to-any modality instruction-following dataset. Furthermore, we identify a significant problem with the current cross-modality alignment method, which results in visual information loss. To address the issue, we propose a visual alignment mechanism with a visual embedding highway module. We then introduce a resource-efficient recipe for training X-VILA, that exhibits proficiency in any-to-any modality conversation, surpassing previous approaches by large margins. X-VILA also showcases emergent properties across modalities even in the absence of similar training data. The project will be made open-source. Comment: Technical Report
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2405.19335 Zobrazit plný text záznamu View this record from Arxiv