Wei Wang, Ming Yan, Fei Huang, Jingren Zhou, Luo Si, Ji Zhang, Songfang Huang, Haiyang Xu, Jiabo Ye, Chenliang Li, Zheng Cao, Guohai Xu, and 2 more
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large-scale pre-trained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks. This paper presents mPLUG, a new vision-language foundation model for both cross-modal understanding and generation. Most existing pre-trained models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in crossmodal alignment. To address both problems, mPLUG introduces an effective and efficient vision-language architecture with novel crossmodal skip-connections. mPLUG is pre-trained end-to-end on largescale image-text pairs with both discriminative and generative objectives. It achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering. mPLUG also demonstrates strong zero-shot transferability on visionlanguage and video-language tasks. The code and pre-trained models are available at https://github.com/alibaba/AliceMind.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2205.12005")
get_code_for_paper("2205.12005")
have("2205.12005")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2205.12005.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2205.12005)
Connect an agent — have() is free.