PhD Student · Rutgers University
Email: jindong.jiang at rutgers.edu · Google Scholar · GitHub
I am a PhD student at Rutgers University under the supervision of Prof. Sungjin Ahn. My research interests lie at the intersection of representation learning and generative AI, with a strong interests in developing unsupervised/self-supervised pre-training approaches to improves agent's reasoning abilities.
The long-term objective of my research is to develop artificial intelligence agents capable of human-like reasoning. This involves designing systems that can uncover latent structure of the physical world, predict future scenarios based on current states, infer the causality or correlation between events, and engage in logical planning to accomplish goals.
At current stage, I am focusing on developing scalable and efficient model designs for visual reasoning in multimodal large language models.
Interests. Multimodal LLMs, Image/Video Perception, Diffusion Models, State Space ModelsSlot State Space Models
SceneTextGen: Layout-Agnostic Scene Text Image Synthesis with Diffusion Models
Object-Centric Slot Diffusion
Generative Neurosymbolic Machines
Improving Generative Imagination in Object-Centric World Models
SCALOR: Generative World Models with Scalable Object Representations
SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition
My Chinese name is "江锦东", it can be pronounced as "Jiang Jindong" in Mandarin, and "Gong Kam Dong" in Guangdong dialect (also known as Cantonese). As ChatGPT once cleverly put it, "江" stands for river, giving a nice flow to the name, while "锦" jazzes things up, representing brocade or ornamental cloth. Then we've got "东" which means east, adding a sense of direction. So, when you put them all together, you end up with a quirky name that doesn't quite translate directly into English.