Hi, I’m Jinsung
I am currently a Ph.D candidate at POSTECH CVLab (Advisor: Prof. Suha Kwak), where I am having fun doing research!
I am interested in designing a compressive neural networks that extract the most informative features within a fixed space of limited complexity. I believe that state-space models (SSMs) offer valuable properties for achieving this goal, and I am actively exploring their application in my work. Previously, I worked on video understanding tasks, such as human action recognition and long-term context modeling.
Updates
Structured State-Space Regularization for Generation-Friendly Image Tokenization
One of my favorite papers has been accepted to the Conference on Neural Information Processing Systems (NeurIPS) 2026 !
New blog series released: Towards 2-Dimensional State-Space Models
I spent months trying to build a better 2D SSM…
but what if it turned out that we do not need an SSM architecture at all to achieve it?
Past notices
Structured State-Space Regularization for Generation-Friendly Image Tokenization
Check out my new paper that introduces an intriguing way to extend SSMs toward multi-dimensional inputs, which reveals a surprising connection to image generation!
Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model
A paper on efficient tokenizer has been accepted to the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026.
Exploring State-Space Models for Data-Specific Neural Representations
A paper on state-space model has been accepted to the International Conference on Learning Representations (ICLR) 2026.
Improving Target Presence and Plurality Recognition for Generalized Referring Image Segmentation
A paper on referring image segmentation has been accepted to the AAAI Conference on Artificial Intelligence (AAAI) 2026.
Planning in 16 Tokens: A Compact Discrete Tokenizer for Latent World Model
A paper on compact tokenizer for world model has been accepted to the Conference on Robot Learning Workshop (CoRLW) 2025.
From HiPPO to Mamba: A Beginner’s Guide to State-Space Models
A new blog post that shares my understanding of State-Space Models (SSMs) has been released!
