2 papers
cs.LG2026
GradientStabilizer:Fix the Norm, Not the Gradient
Tianjin Huang, Zhangyang Wang, Haotian Hu +10
Training instability in modern deep learning systems is frequently triggered by rare but extreme gradient-norm spikes, which can induce oversized parameter updates, corrupt optimiz…
cs.CE2026
Dual-Kernel Adapter: Expanding Spatial Horizons for Data-Constrained Medical Image Analysis
Ziquan Zhu, Hanruo Zhu, Siyuan Lu +8
Adapters have become a widely adopted strategy for efficient fine-tuning of large pretrained models, particularly in resource-constrained settings. However, their performance under…