English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this work, we introduce Vision-Language Generative Pre-trained Transformer(VL-GPT), a transformer model proficient at concurrently perceiving andgenerating visual and linguistic data. VL-GPT achieves a unified pre-trainingapproach for both image and text modalities by employing a straightforwardauto-regressive objective, thereby enabling the model to process image and textas seamlessly as a language model processes text. To accomplish this, weinitially propose a novel image tokenizer-detokenizer framework for visualdata, specifically designed to transform raw images into a sequence ofcontinuous embeddings and reconstruct them accordingly. In combination with theexisting text tokenizer and detokenizer, this framework allows for the encodingof interleaved image-text data into a multimodal sequence, which cansubsequently be fed into the transformer model. Consequently, VL-GPT canperform large-scale pre-training on multimodal corpora utilizing a unifiedauto-regressive objective (i.e., next-token prediction). Upon completion ofpre-training, VL-GPT exhibits remarkable zero-shot and few-shot performanceacross a diverse range of vision and language understanding and generationtasks, including image captioning, visual question answering, text-to-imagegeneration, and more. Additionally, the pre-trained model retrains in-contextlearning capabilities when provided with multimodal prompts. We further conductinstruction tuning on our VL-GPT, highlighting its exceptional potential formultimodal assistance. The source code and model weights shall be released.

VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation