31 citations · 31 across the 3 of their papers we have counts for
3 papers
cs.LG2026
Controllable Diversity in Normalization-Based Implicit Ensembles via Softmax-Temperature Modulation
Mihai Suteu, Ovidiu Serban
Deep ensembles provide the most reliable uncertainty estimates in deep learning, but their cost grows linearly with the number of members. Implicit ensembles lower this cost by sha…
cs.LG2025
Simplifying Multi-Task Architectures Through Task-Specific Normalization
Mihai Suteu, Ovidiu Serban
Multi-task learning (MTL) aims to leverage shared knowledge across tasks to improve generalization and parameter efficiency, yet balancing resources and mitigating interference rem…
cs.LG2019★ 31 cited
Regularizing Deep Multi-Task Networks using Orthogonal Gradients
Mihai Suteu, Yike Guo
Deep neural networks are a promising approach towards multi-task learning because of their capability to leverage knowledge across domains and learn general purpose representations…