Jindong Jiang
Research Scientist · NVIDIA Research
Email: jindongj at nvidia.com · Google Scholar · GitHub
About
I am a Research Scientist at NVIDIA Research. Prior to joining NVIDIA, I was a PhD student at Rutgers University under the supervision of Prof. Sungjin Ahn. My research interests lie at the intersection of representation learning and visual reasoning, with a strong interests in developing novel architectures that can improve agent's visual reasoning capabilities.
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.
Currently, I am focusing on Multimodal LLMs, Vision Foundation Models, and their synergy.
Interests: Multimodal LLMs, Image/Video Perception, Diffusion Models, State Space ModelsNews
- May 2025: I joined
Learning and Perception Research Group as a Research
Scientist.
- April 2025: I successfully completed my Ph.D. defense at
Rutgers University.
- Mar 2025: Preprint of our new work, Token-Efficient Long Video Understanding for Multimodal LLMs, for long-video Multimodal LLMs, is out on arXiv.
- Sep 2024: Our Slot State Space Models is accepted to NeurIPS 2024.
- June 2024: Preprint of our new work, Slot State Space Models, for modular sequence modeling, is out on arXiv.
- June 2024: I joined
Learning and Perception Research Group as a Research
Intern in the Summer of 2024.
- Feb 2024: Our Layout-Agnostic Scene Text Image Synthesis with Diffusion Models is accepted to CVPR 2024.
- Sep 2023: Our Object-Centric Slot Diffusion is accepted to NeurIPS 2023 as a 🌟Spotlight🌟 paper.
- Apr 2023: Our Object-Centric Slot Diffusion for Unsupervised Compositional Generation, is accepted to CVPR 2023 GCV Workshop.
- Feb 2023: I will be joining
as a Research
Scientist Intern in the Summer of 2023.
Publications
-
Token-Efficient Long Video Understanding for Multimodal LLMs
-
Slot State Space Models
-
SceneTextGen: Layout-Agnostic Scene Text Image Synthesis with Diffusion Models
- Qilong Zhangli, Jindong Jiang, Di Liu, Licheng Yu, Xiaoliang Dai, Ankit Ramchandani, Guan Pang, Dimitris N. Metaxas, Praveen Krishnan
- CVPR 2024 [paper]
-
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 Name
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.