Junshu Sun

Pre-training Pure GNNs as Graph Learners

Enhancing Pre-trained Representation Classifiability can Boost its Interpretability

Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs

Relieving the Over-Aggregating Effect in Graph Transformers

VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set

Learning Fine-Grained Representations through Textual Token Disentanglement in Composed Video Retrieval