Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reasoning
Yaning Jia, Chunhui Zhang, Wenxuan Xu +3
Supervised fine-tuning (SFT) applies a uniform cross-entropy loss to all target tokens, even though different tokens provide unequal learning signals for mathematical reasoning. Th…
cs.LG2026
Kernel-Complexity Edge Sanitization for Training-Free Defense against Structural Graph Attacks
Yaning Jia, Shenyang Deng, Yaoqing Yang +3
Graph Neural Networks (GNNs) have achieved remarkable success across diverse applications, yet they remain highly vulnerable to adversarial attacks that maliciously perturb graph s…