arxiv:2607.24645
Phu Gia Hoang
phusroyal
AI & ML interests
Mechanistic Interpretability
Recent Activity
authored a paper about 21 hours ago
Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects authored a paper about 21 hours ago
Vietnamese Hate and Offensive Detection using PhoBERT-CNN and Social
Media Streaming Data authored a paper about 21 hours ago
VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for
Vietnamese Natural Language UnderstandingOrganizations
None yet
models 10
phusroyal/my-lightning-checkpoints
Updated
phusroyal/roberta-base-CoLA-finetuned-cola
Updated
phusroyal/deberta-large-finetuned-cola
Updated
phusroyal/bert-base-cased-finetuned-cola-finetuned-cola
Updated
phusroyal/bert-large-cased-massive_intent
Text Classification • 0.3B • Updated • 3
phusroyal/bert-base-cased-massive_intent
Text Classification • 0.1B • Updated • 3
phusroyal/seed_42-model_bert-base-cased-layers_8-nepoch_15-bs_16-lr_5e-06-es_3-massive_intent
81.2M • Updated
phusroyal/seed_42-model_bert-base-cased-layers_4-nepoch_15-bs_16-lr_5e-06-es_3-massive_intent
52.8M • Updated
phusroyal/seed_42-model_bert-base-cased-layers_2-nepoch_15-bs_16-lr_5e-06-es_3-massive_intent
38.6M • Updated
phusroyal/seed_42-model_bert-base-cased-layers_1-nepoch_1-bs_16-lr_5e-06-es_3-massive_intent
Updated