Jiang Ruixiang (江睿翔)

Currently I am a research assistant at The Hong Kong Polytechnic University (PolyU), mentored by Prof. Chen Changwen. I have just obtained my Bsc. degree at PolyU with first class honor, and my major is Computer Science .

My research interests primarily lie in Computer Graphics, Computer Vision and the intersection between them, with a focus on neural rendering and 3D content generation. Besides, I am also interested in Multimodal AI, especially in vision-language models (VLMs). My goal is to build AI systems that understand and manipulate 3D content with natural language.

Currently, I am looking for phd positions starting from 2023/2024.

Email: rui-x [d] jiang [AT] connect [d] polyu [d] hk.

Email  /  CV  /  Github  /  Google Scholar

We design a prompt-tuning method for multimodal fusion, achieving similar result with fine-tuning while only require 0.7% trainable parameters.

We propose the first end-to-end object counting model that count anything using text prompt.

We propose the first complete pipeline for creating, editing and animating neural human avatars.

We stylize neural implicit scene to a specific art style by a text prompt.

We propose to leverage toon-shading and model outlining priors to better encode non-photorealistic scene with neural implicit fields.

A pencil-sketch (a.k.a. hatching) style shader for Unity.

Last updated: Dec 9, 2023,

Theme from jonbarron 's website,