Skip to yearly menu bar Skip to main content


Towards More Unified In-context Visual Understanding

Dianmo Sheng · Dongdong Chen · Zhentao Tan · Qiankun Liu · Qi Chu · Jianmin Bao · Tao Gong · Bin Liu · Shengwei Xu · Nenghai Yu

Arch 4A-E Poster #359
[ ]
Thu 20 Jun 10:30 a.m. PDT — noon PDT


The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domain. Recently, ICL has been employed in visual understanding tasks, such as semantic segmentation and image captioning, yielding promising results. However, existing visual ICL framework can not enable producing content across multiple modalities, which limits their potential usage scenarios. To address this issue, we present a new ICL framework for visual understanding with multi-modal output enabled. First, we quantize and embed both text and visual prompt into a unified representational space, structured as interleaved in-context sequences. Then a decoder-only sparse transformer architecture is employed to perform generative modeling on them, facilitating in-context learning. Thanks to this design, the model is capable of handling in-context vision understanding tasks with multimodal output in a unified pipeline. Experimental results demonstrate that our model achieves competitive performance compared with specialized models and previous ICL baselines. Overall, our research takes a further step toward unified multimodal in-context learning.

Live content is unavailable. Log in and register to view live content