Juhan Bae
5
Papers
3
Total Citations
2
Affiliations
Affiliations
University of TorontoVector Institute
Papers (5)
Better Training Data Attribution via Better Inverse Hessian-Vector Products
NeurIPS 2025arXiv
2
citations
IF-Guide: Influence Function-Guided Detoxification of LLMs
NeurIPS 2025arXiv
1
citations
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
ICLR 2025arXiv
0
citations
Accelerating neural network training: An analysis of the AlgoPerf competition
ICLR 2025arXiv
0
citations
Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective
ICML 2024arXiv
0
citations