Selected Publications

For a complete list of my research works, please lookup my Google Scholar.

OLA-VLM: Elevating Perception in Multimodal LLMs with Auxiliary Embedding Distillation
VCoder: Versatile Vision Encoders for Multimodal Large Language Models
OneFormer: One Transformer to Rule Universal Image Segmentation
Keys to Better Image Inpainting: Structure and Texture Go Hand in Hand
SeMask: Semantically Masked Transformers for Semantic Segmentation