#continual-learning3 articles

3 articles

AIBullisharXiv – CS AI · 4h ago3

🧠

Enhancing Continual Learning for Software Vulnerability Prediction: Addressing Catastrophic Forgetting via Hybrid-Confidence-Aware Selective Replay for Temporal LLM Fine-Tuning

Researchers developed Hybrid Class-Aware Selective Replay (Hybrid-CASR), a continual learning method that improves AI-based software vulnerability detection by addressing catastrophic forgetting in temporal scenarios. The method achieved 0.667 Macro-F1 score while reducing training time by 17% compared to baseline approaches on CVE data from 2018-2024.

AIBullisharXiv – CS AI · 4h ago6

🧠

Activation Function Design Sustains Plasticity in Continual Learning

Researchers from arXiv demonstrate that activation function design is crucial for maintaining neural network plasticity in continual learning scenarios. They introduce two new activation functions (Smooth-Leaky and Randomized Smooth-Leaky) that help prevent models from losing their ability to adapt to new tasks over time.

$LINK

AINeutralarXiv – CS AI · 4h ago0

🧠

SegReg: Latent Space Regularization for Improved Medical Image Segmentation

Researchers propose SegReg, a latent-space regularization framework for medical image segmentation that improves model generalization and continual learning capabilities. The method operates on U-Net feature maps and demonstrates consistent improvements across prostate, cardiac, and hippocampus segmentation tasks without adding extra parameters.