Intelligence Representation & Reasoning Lab

Gwangju Institute of Science and Technology (GIST)

How to build a single accumulative intelligence for more general and wider problems?

Main page img modified at Jun 23, 2021


Notice

We are always looking for strongly self-motivated students who want to dive into research for deep and fundamental understanding of AI.


News

24.01.20: ICLR 2024, “Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation”
24.01.20: ICLR 2024, “Output-Domain Focused Inductive Bias on Latent Feature Clusters in Visual Classification.”
23.07.10: ESWA, “Feature Structure Distillation with Centered Kernel Alignment in BERT Transferring”
22.09.15: NeuRIPS2022, “Spherization Layer: Representation Using Only Angles” from NeurIPS 2022.