Sungjun Cho

8

Papers

39

Total Citations

Papers (8)

Learning Equi-angular Representations for Online Continual Learning

Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs

3D Denoisers Are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation

Rebalancing Batch Normalization for Exemplar-Based Class-Incremental Learning

Learning to Unlearn: Instance-Wise Unlearning for Pre-trained Classifiers

Equivariant Hypergraph Neural Networks

Pure Transformers are Powerful Graph Learners

Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost