arxiv:2607.24645
Phu Gia Hoang
phusroyal
AI & ML interests
Mechanistic Interpretability
Recent Activity
authored a paper 4 days ago
Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects authored a paper 4 days ago
Vietnamese Hate and Offensive Detection using PhoBERT-CNN and Social
Media Streaming Data authored a paper 4 days ago
VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for
Vietnamese Natural Language UnderstandingOrganizations
None yet