Yi Jiang

This publication record appears to combine work from multiple researchers sharing the name Yi Jiang, spanning topics such as image and video understanding, multimodal AI models, wireless communications, and unrelated applied fields like electric vehicles, medical imaging, and shale gas exploration. Within the computer vision and multimodal machine learning thread, the work focuses on image tokenization, object detection, grounding of multimodal large language models, and image generation techniques. Because the bibliographic data mixes several distinct research areas, it is difficult to characterize a single coherent research agenda from this record alone.​

Publication output has grown over the last decade, rising from just a few papers per year in 2017-2019 to a peak of 15 in 2025, with an average of about 8.4 publications per year over the last five years.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026