News
News & blog posts
-
24.01.20: Congratulations on ICLR 2024 acceptance of “Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation”
-
24.01.20: Congratulations on ICLR 2024 acceptance of “Output-Domain Focused Inductive Bias on Latent Feature Clusters in Visual Classification.”
-
23.07.10: Congratulations on the acceptance of the regular paper, “Feature Structure Distillation with Centered Kernel Alignment in BERT Transferring” from ELSEVIER Expert Systems with Applications.
-
22.09.15: Congratulations on the acceptance of the regular paper, “Spherization Layer: Representation Using Only Angles” from NeurIPS 2022.
TMLR, "CFASL: Composite Factor-Aligned Symmetry Learning for Disentanglement in Variational AutoEncoder"
November 06, 2024
Symmetries of input and latent vectors have provided valuable insights for disentanglement learning in VAEs. However, only a few works...
ACL 2024 Findings, "Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction"
August 11, 2024
Video will be uploaded after conference! Summary & Contribution We reveal two problem “Structural Optimization Ambiguity” and “Structural Simplicity Bias”...
ICLR 2024, "Label-Focused Inductive Bias over Latent Object Features in Visual Classification"
January 20, 2024
No contents
ICLR 2024, "Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation"
January 20, 2024
FNO classifier makes the LPM achieve the global optimality even in inducing the max-margin decision while satisfying the properties of...
ESWA, "Feature Structure Distillation with Centered Kernel Alignment in BERT Transferring"
July 10, 2023
No contents
NeurIPS 2022, "Spherization Layer: Representation Using Only Angles"
September 15, 2022
Spherization layer is an explicit solution for the dispersion to completely eliminate the interference of the Euclidean norms in training...